CN103136280A - System and method of automatically searching hot point video - Google Patents
System and method of automatically searching hot point video Download PDFInfo
- Publication number
- CN103136280A CN103136280A CN 201110398215 CN201110398215A CN103136280A CN 103136280 A CN103136280 A CN 103136280A CN 201110398215 CN201110398215 CN 201110398215 CN 201110398215 A CN201110398215 A CN 201110398215A CN 103136280 A CN103136280 A CN 103136280A
- Authority
- CN
- China
- Prior art keywords
- video
- weight
- hot
- increment
- full dose
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a system and a device of automatically searching a hot point video. The system comprises a video information base, a population parameter statistics module, an increment statistics module and a hot point video computation module. The video information base stores a mass of video information. The population parameter statistics module is used for counting total statistical magnitude of each population parameter statistics item of each of the video information in the video information base. The increment statistics module is used for counting newly increased statistical magnitude of each increment statistics item of each of the video information in a particular time period. The hot point video computation module is used for calculating weight of each property of each of the video information, weight of each population parameter statistics item of the population parameter statistics module and weight of each increment statistics item of the increment statistics module by using each video-weight calculation model. Hot weight value of the video information is obtained through the hot point video computation module according to each weight result obtained by calculation. A hot point video list is selected to be displayed according to the hot weight value of the video information. The system and the device of automatically searching the hot point video is capable of automatically generating hot point video searching result through acquisition of clicking of a user.
Description
Technical field
The present invention relates to a kind of hot video commending system and method, particularly relate to a kind of hot video automatic mining system and method.
Background technology
The characteristic that height is universal, the internet is quick and borderless due to computer, the user of internet is and increases substantially, formed quantity surprising consumption group, the demand of internet has become indispensable part with using in modern science and technology society, make many industries have an optimistic view of the huge business opportunity that the internet is implied, for example, various types of ecommerce, online game, finance business on network, language learning and Online Video etc.
Yet along with the fast development of video website, the user finds that interested video is more and more difficult from a large amount of irrelevant information, and in this case, the user often needs video website to recommend some high-quality videos from multitude of video.One of way of recommending high-quality video from multitude of video commonly used is, and is high-quality or with the closely-related video of current events focus by the web editor manual markings, and is pushed to the homepage of website.But the bothersome effort of this way, efficient is low, low precision, and relies on editor individual's taste and eye, does not have an objectivity, often can not reflect user's real demand, therefore more and more is difficult to satisfy the demand that the netizen recommends video website
The another kind of way of high-quality video of recommending from multitude of video is, add up the click volume of each video of the past period by computer system, the video marker of excavating user's welcome is popular video, recommending the user watches, yet the shortcoming of this mode is, hot video is not always to give directions to hit the video of total amount maximum because click total amount often this video produce in accumulative process for a long time, might not represent that this video is current focus.The video of 9.11 events for example, out recommended but be re-used as hot video today so the click total amount of video is very high owing to being once at that time focus, be obviously inappropriate.
In sum, as can be known the video recommendation method of prior art have that efficient is low, low precision and the problem that can not meet consumers' demand, be necessary to propose improved technological means therefore in fact, solve this problem.
Summary of the invention
The deficiency that exists for overcoming above-mentioned prior art, fundamental purpose of the present invention is to provide a kind of hot video automatic mining system and method, it is clicked behavior and generates the focus recommendation results by obtaining the user, not only improve efficient and precision that video is recommended, and more can satisfy user's demand.
For reaching above-mentioned and other purpose, the invention provides a kind of hot video automatic mining system, comprise at least:
The video information storehouse stores many video datas, and wherein every video data has multiple attribute information;
The full dose statistical module is used for total statistic of this video information of statistics every, storehouse each full dose statistical items of video data;
The accrual accounting module is used for adding up the newly-increased statistic of every video data each accrual accounting item in section sometime; And
The hot video computing module, utilize each weight calculation model, respectively each attribute of every video data, each full dose statistical items of this full dose statistical module and each accrual accounting item of this accrual accounting module are calculated a weight, utilize a hot video computation model to obtain the popular weighted value of every video data according to calculating each weight result that obtains, and show according to the popular weighted value intercepting one hot video list of every video data.
Further, this full dose statistical items comprises the total amount of clicking total amount, the total amount of being pushed up, the total amount of being stepped on, the total amount of being collected and being commented on; This accrual accounting item comprises the increment that the increment of the interior click of section sometime, the increment that is pushed up, the increment of being stepped on, the increment of being collected and quilt are commented on.
Further, this hot video computing module utilizes respectively video duration weight calculation model, video uplink time weight calculation model, increment weight calculation model and full dose weight calculation model to carry out weight calculation to video duration, video uplink time, each accrual accounting item of this accrual accounting module and the full dose statistical items of this full dose statistical module of video data, obtains respectively video duration weight, video uplink time weight, increment weight and full dose weight.
Further, this hot video computation model is:
video_weight＝videotime_weight+uploadpoint+playpoint?1+playpoint2
Wherein, video_weight is popular weighted value, and videotime_weight, uploadpoint, playpoint 1, playpoint2 are respectively this video duration weight, this video uplink time weight, this increment weight and this full dose weight.
Further, this hot video automatic mining system also comprises a COLLECTIDN module, being responsible for receiving the video data of COLLECTIDN, and it is stored in a cms database.
Further, this hot video computing module calculates the CMS weight of every video data according to a CMS weight calculation model.
Further, this hot video computation model is:
video_weight＝videotime_weight+uploadpoint+playpoint?1+playpoint2+cmspoint
Wherein, video_weight is popular weighted value, and videotime_weight, uploadpoint, playpoint 1, playpoint2 and cmspoint are respectively this video duration weight, this video uplink time weight, this increment weight, this full dose weight and this CMS weight.
Further, this hot video automatic mining system also comprises candidate's list of videos generation module, be used for generating candidate's hot video list, simultaneously, this hot video computing module carries out popular weighted value to every video data in this candidate's hot video list respectively and calculates.
Further, this candidate's list of videos generation module generates this candidate's hot video list according to this COLLECTIDN module and this accrual accounting module.
Further, in this video information storehouse, the attribute information of every video data comprises at least uplink time, video title, the thumbnail path of duration that video continues, video and plays url.
For reaching above-mentioned and other purpose, the present invention also provides a kind of hot video automatic mining method, comprises the steps:
Set up the video information storehouse;
Total statistic of every each full dose statistical items of video data in statistics video information storehouse;
Add up every video data newly-increased statistic of each accrual accounting item in section sometime; And
Utilize each weight calculation model, respectively to attribute, each full dose statistical items and each accrual accounting item Determining Weights of every video data, and will calculate the result of acquisition according to the popular weighted value of every video data of a hot video computation model acquisition, the popular weighted value intercepting one hot video list of every video data of foundation shows.
Further, this full dose statistical items comprises the total amount of clicking total amount, the total amount of being pushed up, the total amount of being stepped on, the total amount of being collected and being commented on; This accrual accounting item comprises the increment that the increment of the interior click of section sometime, the increment that is pushed up, the increment of being stepped on, the increment of being collected and quilt are commented on.
Further, hot video computing module apportion utilizes video duration weight calculation model, video uplink time weight calculation model, increment weight calculation model and full dose weight calculation model to carry out weight calculation to video duration, video uplink time, each accrual accounting item and the full dose statistical items of every video data, obtains video duration weight, video uplink time weight, increment weight and full dose weight.
Further, before the step of calculating the popular weighted value of every video data, also comprise the step of setting up the CMS database, to receive the video data of COLLECTIDN, this hot video computing module calculates the CMS weight of every video data according to a CMS weight calculation model simultaneously.
Further, before the step of calculating the popular weighted value of every video data, comprise that also one generates the step of candidate's hot video list, simultaneously, this hot video computing module carries out popular weighted value to every video data in this candidate's hot video list respectively and calculates.
Further, the step of this generation candidate hot video list comprises the steps:
Obtain the N bar video that enters recently this CMS database by the time;
According to the accrual accounting amount of each accrual accounting item, and get from high to low the front N bar video of each classification; And
Deposit above all videos the set of in candidate's video, and go heavily.
Compared with prior art, the present invention a kind of hot video automatic mining system and method thereof are by full dose statistical module and accrual accounting module, and in conjunction with the feature (for example video duration and uplink time) of video in the video information storehouse, in time excavate most probable video popular with users for the previous period, generate focus Video Mining result, improve efficient and precision that hot video excavates, more met user's demand.
Description of drawings
Fig. 1 is a kind of hot video automatic mining of the present invention system of systems Organization Chart;
Fig. 2 is the flow chart of steps of a kind of hot video automatic mining of the present invention method.
Embodiment
Below by specific instantiation and accompanying drawings embodiments of the present invention, those skilled in the art can understand other advantage of the present invention and effect easily by content disclosed in the present specification.The present invention also can be implemented or be used by other different instantiation, and the every details in this instructions also can be based on different viewpoints and application, carries out various modifications and change under spirit of the present invention not deviating from.
Fig. 1 is a kind of hot video automatic mining of the present invention system of systems Organization Chart.As shown in Figure 1, a kind of hot video automatic mining of the present invention system comprises at least: video information storehouse 101, full dose statistical module 102, accrual accounting module 103 and hot video computing module 104.
Wherein, many video datas of video information storehouse 101 storages, every video data comprises the attribute informations such as uplink time, video title, thumbnail path and broadcast url (Uniform Resoure Locator uniform resource locator) of the lasting duration of video, video.In preferred embodiment of the present invention, video data adopts the key:value mode of NoSQL to deposit, and as key word (key) value, value is the various attribute informations of video data with the id (sign, the back is called vid) of video, for example,
Videotime: the duration that video continues, unit are second
Uploadtime: the uplink time of video
Title: video title
Picpath: thumbnail path
Playurl: play url.
Full dose statistical module 102, be used for adding up total statistic of every each statistical items of video data, each statistical items here comprises total amount likecount, the total amount dislikecount that is stepped on (expression is not liked), the total amount storecount that is collected that clicks total amount clickcount, pushed up (expression is liked) and the total amount commentcount that is commented on; Accrual accounting module 103 is used for adding up the newly-increased statistic of every video data each statistical items in section sometime, for example, measurement period be 1 hour once, statistics is gone over the click increment of 24 hours, symbolically is as follows:
Vid1.clickcount_hour1: be illustrated in over 1 hour in, the click volume that video vid1 is newly-increased.Video for example: http://v.ku6.com/show/t7TbsW09pjI9W2nY.html.If the current time is 15:20 in afternoon September 9, the measurement period of so front 1 hour is since 14:00 in afternoon September 9, finish to 15:00 one hour.This is clicked 1500 times in interval at 14:00-15:00 to suppose this video, vid1.clickcount_hour1=1500; By that analogy, vid1.clickcount_hour2 is the click increment in this time period of 13:00-14:00, and vid1.clickcount_hour3 is the click increment in this time period of 12:00-13:00
Accrual accounting is similar with clicking, and accrual accounting module 103 also records following statistic by the hour to other each statistical items (increment that is pushed up, the increment of being stepped on, the increment of being collected and by the increment of being commented on):
Likecount_hour[1-24]: the increment that is pushed up (expression is liked)
Dislikecount_hour[1-24]: the increment of being stepped on (expression is not liked)
Storecount_hour[1-24]: the increment of being collected
Commentcount_hour[1-24]: the increment of being commented on
Hot video computing module 104, utilize each weight calculation model, respectively to each statistical items Determining Weights of attribute, full dose statistical module 102 each statistical items and the accrual accounting module 103 of every video data, and obtain the popular weighted value of every video data according to a hot video computation model, show according to the popular weighted value intercepting one hot video list of every video data.
In preferred embodiment of the present invention, at first, hot video computing module 104 utilizes video duration weight calculation model, video duration to every video data carries out weight calculation, for example, videotime is video duration (unit is second), and videotime_weight is video duration weight, and video duration weight calculation model is as follows:
If videotime＞20, videotime_weight=100
If videotime＞60, videotime_weight=1000
If videotime＞180, videotime_weight=2000
Otherwise videotime_weight is 0
Secondly, hot video computing module 104 utilizes video uplink time weight calculation model, the video uplink time of every video data is carried out weight calculation, for example, uploadpoint is video uplink time weight, and video uplink time weight calculation model is as follows:
int?uploadpoint＝22000；
if(betweenhour＞＝1)uploadpoint＝20000；
if(betweenhour＞＝2)uploadpoint＝10000；
if(betweenhour＞＝3)uploadpoint＝7500；
if(betweenhour＞＝6)uploadpoint＝500；
if(betweenhour＞＝12)uploadpoint＝-1000；
if(betweenhour＞＝24)uploadpoint＝-10000；
if(betweenhour＞＝48)uploadpoint＝-50000；
if(betweenhour＞＝100)uploadpoint＝-100000；
if(betweenhour＞＝200)uploadpoint＝-150000；
if(betweenmonth＞＝1)uploadpoint＝-2500000；
if(betweenmonth＞＝12)uploadpoint＝-10000000；
Again, 104 pairs of every documents of hot video computing module utilize increment weight calculation model to carry out weight calculation to each accrual accounting item of accrual accounting module 103, and this increment weight calculation model is:
Playpoint1=clickcount_hour1+likecount_hour1*5+storecount _ hour1*2+commentcount_hour1*3, wherein, playpoint1 is the increment weight.
Then, 104 pairs of every documents of hot video computing module utilize full dose weight calculation model to carry out weight calculation to each full dose statistical items of full dose statistical module 102, and this full dose weight calculation model is:
Playpoint2=likecount*0.01+storecount*0.01+commentcount*0 .01, wherein playpoint2 is the full dose weight.
At last, 104 of hot video computing modules calculate the popular weighted value video_weight that obtains every video data according to a hot video computation model.This hot video computation model is:
video_weight＝videotime_weight+uploadpoint+playpoint?1+playpoint2。
After calculate obtaining the popular weighted value of every video data, 104 of hot video computing modules according to the descending sequence of video_weight, intercept front 10 results with video data, represent for the user on webpage.
better, the present invention's hot video automatic mining system also can comprise a COLLECTIDN module 105, this COLLECTIDN module 105 allows editor to carry out manual intervention, be responsible for receiving the video data of COLLECTIDN, and it is stored in a cms database, heat supply point video computing module 104 uses, it should be noted that at this, editor's recommendation herein only as a factor of focus in action, fully different with the mode of the artificial appointment of former direct editing, simultaneously, hot video computing module 104 also calculates its CMS weight cmspoint to every document according to a CMS weight calculation model, this CMS weight calculation model is:
If this video data is from CMS database, cmspoint=5000;
Otherwise, cmspoint=0.
Accordingly, at this moment, the hot video computation model of hot video computing module 104 is:
video_weight＝videotime_weight+uploadpoint+playpoint?1+playpoint2+cmspoint。
In addition, be to improve the present invention's automatic mining efficient, the present invention's hot video automatic mining system also can comprise candidate's list of videos generation module.This candidate's list of videos generation module is used for generating the list of candidate's hot video, heat supply point video computing module 104 uses, follow-up hot video computing module 104 needn't calculate the popular weighted value of every document in video database, and only need the popular weighted value of candidate's video in the list of calculated candidate hot video, and show according to the popular weighted value intercepting one hot video list of all candidate's videos.In the present invention's preferred embodiment, the generating mode of candidate's hot video list is as follows:
1, from COLLECTIDN module 105, according to the time, obtain the N bar video (as 20) that enters recently the CMS database;
2, from accrual accounting module 103, obtain respectively clickcount_hour1, clickcount_hour2, clickcount_hour3, storecount_hour1, storecount_hour2, storecount_hour3, the statistic of commentcount_hour1, commentcount_hour2, commentcount_hour3, and get from high to low the front N bar video (as 20) of each classification;
3, deposit above all videos the set of in candidate's video, and go heavily.
Fig. 2 is the flow chart of steps of a kind of hot video automatic mining of the present invention method, below will coordinate Fig. 2 that the present invention's hot video automatic mining method is described.As shown in Figure 2, the present invention's hot video automatic mining method comprises the steps:
Step 201 is set up the video information storehouse.In a video website, the video that the user uploads after audit, can import in the video information storehouse.in the video information storehouse, every video data comprises the duration videotime that video continues, the uplink time uploadtime of video, video title title, the attribute informations such as thumbnail path picpath and broadcast url (playurl), in this video information storehouse, video data adopts the key:value mode of NoSQL to deposit, id (sign with video, the back is called vid) as key word (key) value, value is the various attribute informations of video data, can inquire according to the vid of video video every attribute information (videotime uploadtime title picurl playurl),
Step 204, utilize each weight calculation model, respectively to each accrual accounting item Determining Weights of attribute, full dose statistical module 102 each full dose statistical items and the accrual accounting module 103 of every video data, and will calculate the result of acquisition according to the popular weighted value of every video data of a hot video computation model acquisition, the popular weighted value intercepting one hot video list of every video data of foundation shows.in preferred embodiment of the present invention, hot video computing module 104 apportions utilize video duration weight calculation model, video uplink time weight calculation model, increment weight calculation model and the full dose weight calculation model video duration to every video data, the video uplink time, each accrual accounting item of accrual accounting module 103 and the full dose statistical items of full dose statistical module 102 are carried out weight calculation, obtain video duration weight videotime_weight, video uplink time weight uploadpoint, increment weight playpoint1 and full dose weight playpoint2, and obtain the popular weighted value video_weight of every video data according to the hot video computation model, popular weighted value intercepting one hot video list according to every video data shows, for example, after obtaining the popular weighted value of every video data, 104 of hot video computing modules with video data according to the descending sequence of video_weight, intercept front 10 results, represent for the user on webpage.
Better, the present invention's hot video automatic mining method also comprised the step of setting up the cms database before step 204, receive the video data of artificial COLLECTIDN, the present invention than the Jia Sishi example in, in the cms data video data is by editor's the recommendation time, by new to old arrangement.It should be noted that, the recommendation of inediting of the present invention only as a factor of focus in action, and the mode of the artificial appointment of direct editing in the past is fully different.Accordingly, in step 204, need utilize a CMS weight calculation model to calculate the CMS weight cmspoint of every video data, the calculating of the popular weighted value video_weight of video data simultaneously adds considering CMS weight cmspoint.
In addition, the present invention's hot video automatic mining method comprised also that before step 204 one generates the step of candidate's hot video list, this candidate's hot video list heat supply point video computing module 104 uses, follow-up hot video computing module 104 needn't calculate the popular weighted value of every document in video database, and only need the popular weighted value of candidate's video in the list of calculated candidate hot video, and show according to the popular weighted value intercepting one hot video list of all candidate's videos.In the present invention's preferred embodiment, the generation method of candidate's hot video list comprises the steps:
Step 1 according to the time, is obtained the N bar video (as 20) that enters recently the CMS database;
Step 2, from accrual accounting module 103, obtain respectively each accrual accounting item clickcount_hour1, clickcount_hour2, clickcount_hour3, storecount_hour1, storecount_hour2, storecount_hour3, the accrual accounting amount of commentcount_hour1, commentcount_hour2, commentcount_hour3, and get from high to low the front N bar video (as 20) of each classification;
3, deposit above all videos the set of in candidate's video, and go heavily.
In sum, the present invention a kind of hot video automatic mining system and method thereof are by full dose statistical module and accrual accounting module, and in conjunction with the feature (for example video duration and uplink time) of video in the video information storehouse, in time excavate most probable video popular with users for the previous period, generate focus Video Mining result, improve efficient and precision that hot video excavates, more met user's demand.
Above-described embodiment is illustrative principle of the present invention and effect thereof only, but not is used for restriction the present invention.Any those skilled in the art all can under spirit of the present invention and category, modify and change above-described embodiment.Therefore, the scope of the present invention should be as listed in claims.
Claims (16)
1. hot video automatic mining system comprises at least:
The video information storehouse stores many video datas, and wherein every video data has multiple attribute information;
The full dose statistical module is used for total statistic of this video information of statistics every, storehouse each full dose statistical items of video data;
The accrual accounting module is used for adding up the newly-increased statistic of every video data each accrual accounting item in section sometime; And
The hot video computing module, utilize each weight calculation model, respectively each attribute of every video data, each full dose statistical items of this full dose statistical module and each accrual accounting item of this accrual accounting module are calculated a weight, utilize a hot video computation model to obtain the popular weighted value of every video data according to calculating each weight result that obtains, and show according to the popular weighted value intercepting one hot video list of every video data.
2. hot video automatic mining as claimed in claim 1 system, it is characterized in that: this full dose statistical items comprises the total amount of clicking total amount, the total amount of being pushed up, the total amount of being stepped on, the total amount of being collected and being commented on; This accrual accounting item comprises the increment that the increment of the interior click of section sometime, the increment that is pushed up, the increment of being stepped on, the increment of being collected and quilt are commented on.
3. hot video automatic mining as claimed in claim 1 system, it is characterized in that: this hot video computing module utilizes respectively video duration weight calculation model, video uplink time weight calculation model, increment weight calculation model and full dose weight calculation model to carry out weight calculation to video duration, video uplink time, each accrual accounting item of this accrual accounting module and the full dose statistical items of this full dose statistical module of video data, obtains respectively video duration weight, video uplink time weight, increment weight and full dose weight.
4. hot video automatic mining as claimed in claim 3 system, it is characterized in that: this hot video computation model is:
video_weight＝videotime_weight+uploadpoint+playpoint?1+playpoint2
Wherein, video_weight is popular weighted value, and videotime_weight, uploadpoint, playpoint 1, playpoint2 are respectively this video duration weight, this video uplink time weight, this increment weight and this full dose weight.
5. hot video automatic mining as claimed in claim 1 system is characterized in that: this hot video automatic mining system also comprises a COLLECTIDN module, being responsible for receiving the video data of COLLECTIDN, and it is stored in a cms database.
6. hot video automatic mining as claimed in claim 5 system, it is characterized in that: this hot video computing module calculates the CMS weight of every video data according to a CMS weight calculation model.
7. hot video automatic mining as claimed in claim 6 system, it is characterized in that: this hot video computation model is:
video_weight＝videotime_weight+uploadpoint+playpoint?1+playpoint2+cmspoint
Wherein, video_weight is popular weighted value, and videotime_weight, uploadpoint, playpoint 1, playpoint2 and cmspoint are respectively this video duration weight, this video uplink time weight, this increment weight, this full dose weight and this CMS weight.
8. hot video automatic mining as claimed in claim 7 system, it is characterized in that: this hot video automatic mining system also comprises candidate's list of videos generation module, be used for generating candidate's hot video list, simultaneously, this hot video computing module carries out popular weighted value calculating to every video data in this candidate's hot video list respectively.
9. hot video automatic mining as claimed in claim 8 system, it is characterized in that: this candidate's list of videos generation module generates this candidate's hot video list according to this COLLECTIDN module and this accrual accounting module.
10. hot video automatic mining as claimed in claim 1 system is characterized in that: in this video information storehouse, the attribute information of every video data comprises at least uplink time, video title, the thumbnail path of duration that video continues, video and plays url.
11. a hot video automatic mining method comprises the steps:
Set up the video information storehouse;
Total statistic of every each full dose statistical items of video data in statistics video information storehouse;
Add up every video data newly-increased statistic of each accrual accounting item in section sometime; And
Utilize each weight calculation model, respectively to attribute, each full dose statistical items and each accrual accounting item Determining Weights of every video data, and will calculate the result of acquisition according to the popular weighted value of every video data of a hot video computation model acquisition, the popular weighted value intercepting one hot video list of every video data of foundation shows.
12. a kind of hot video automatic mining method as claimed in claim 11 is characterized in that: this full dose statistical items comprises the total amount of clicking total amount, the total amount of being pushed up, the total amount of being stepped on, the total amount of being collected and being commented on; This accrual accounting item comprises the increment that the increment of the interior click of section sometime, the increment that is pushed up, the increment of being stepped on, the increment of being collected and quilt are commented on.
13. a kind of hot video automatic mining method as claimed in claim 11, it is characterized in that: hot video computing module apportion utilizes video duration weight calculation model, video uplink time weight calculation model, increment weight calculation model and full dose weight calculation model to carry out weight calculation to video duration, video uplink time, each accrual accounting item and the full dose statistical items of every video data, obtains video duration weight, video uplink time weight, increment weight and full dose weight.
14. a kind of hot video automatic mining method as claimed in claim 13, it is characterized in that: before the step of calculating the popular weighted value of every video data, also comprise the step of setting up the CMS database, to receive the video data of COLLECTIDN, this hot video computing module calculates the CMS weight of every video data according to a CMS weight calculation model simultaneously.
15. a kind of hot video automatic mining method as claimed in claim 14, it is characterized in that: before the step of calculating the popular weighted value of every video data, comprise that also one generates the step of candidate's hot video list, simultaneously, this hot video computing module carries out popular weighted value calculating to every video data in this candidate's hot video list respectively.
16. a kind of hot video automatic mining method as claimed in claim 15 is characterized in that, the step of this generation candidate hot video list comprises the steps:
Obtain the N bar video that enters recently this CMS database by the time;
According to the accrual accounting amount of each accrual accounting item, and get from high to low the front N bar video of each classification; And
Deposit above all videos the set of in candidate's video, and go heavily.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110398215 CN103136280A (en) | 2011-12-02 | 2011-12-02 | System and method of automatically searching hot point video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110398215 CN103136280A (en) | 2011-12-02 | 2011-12-02 | System and method of automatically searching hot point video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103136280A true CN103136280A (en) | 2013-06-05 |
Family
ID=48496112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201110398215 Pending CN103136280A (en) | 2011-12-02 | 2011-12-02 | System and method of automatically searching hot point video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103136280A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970813A (en) * | 2013-12-27 | 2014-08-06 | 乐视网信息技术（北京）股份有限公司 | Multimedia content searching method and system |
| CN104133823A (en) * | 2013-07-19 | 2014-11-05 | 腾讯科技（深圳）有限公司 | Method and device for recommending multimedia information |
| CN104268187A (en) * | 2014-09-17 | 2015-01-07 | 合一网络技术(北京)有限公司 | User feedback based multi-scenario supported online content optimization system |
| CN105007504A (en) * | 2015-07-13 | 2015-10-28 | 无锡天脉聚源传媒科技有限公司 | Browsing history processing method and device |
| CN105022801A (en) * | 2015-06-30 | 2015-11-04 | 北京奇艺世纪科技有限公司 | Hot video mining method and hot video mining device |
| CN105554529A (en) * | 2014-10-30 | 2016-05-04 | 深圳富泰宏精密工业有限公司 | On-line movie automatic series playing system and method |
| CN105981067A (en) * | 2013-07-26 | 2016-09-28 | 朱炫宣 | Device for providing comments and statistical information on respective sections of video and method for same |
| CN106339447A (en) * | 2016-08-23 | 2017-01-18 | 达而观信息科技（上海）有限公司 | System and method for automatically predicting hot videos |
| CN106682111A (en) * | 2016-12-06 | 2017-05-17 | 腾讯科技（深圳）有限公司 | Data recommendation method and equipment thereof |
| CN108881968A (en) * | 2017-05-15 | 2018-11-23 | 北京国双科技有限公司 | A kind of network video advertisement put-on method and system |
| CN109889891A (en) * | 2019-03-05 | 2019-06-14 | 腾讯科技（深圳）有限公司 | Obtain the method, apparatus and storage medium of target media file |
| CN111026991A (en) * | 2019-12-05 | 2020-04-17 | 中国银行股份有限公司 | Data display method and device and computer equipment |
| CN111048215A (en) * | 2019-12-13 | 2020-04-21 | 北京纵横无双科技有限公司 | CRM-based medical video production method and system |
| CN111104627A (en) * | 2018-10-29 | 2020-05-05 | 北京国双科技有限公司 | Hot event prediction method and device |
| CN116469039A (en) * | 2023-04-28 | 2023-07-21 | 青岛尘元科技信息有限公司 | Hot video event determination method and system, storage medium and electronic equipment |
-
2011
- 2011-12-02 CN CN 201110398215 patent/CN103136280A/en active Pending
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133823A (en) * | 2013-07-19 | 2014-11-05 | 腾讯科技（深圳）有限公司 | Method and device for recommending multimedia information |
| CN104133823B (en) * | 2013-07-19 | 2015-11-18 | 腾讯科技（深圳）有限公司 | A kind of method and apparatus recommending multimedia messages |
| CN105981067A (en) * | 2013-07-26 | 2016-09-28 | 朱炫宣 | Device for providing comments and statistical information on respective sections of video and method for same |
| CN103970813A (en) * | 2013-12-27 | 2014-08-06 | 乐视网信息技术（北京）股份有限公司 | Multimedia content searching method and system |
| CN104268187A (en) * | 2014-09-17 | 2015-01-07 | 合一网络技术(北京)有限公司 | User feedback based multi-scenario supported online content optimization system |
| CN105554529A (en) * | 2014-10-30 | 2016-05-04 | 深圳富泰宏精密工业有限公司 | On-line movie automatic series playing system and method |
| CN105022801B (en) * | 2015-06-30 | 2018-06-22 | 北京奇艺世纪科技有限公司 | A kind of hot topic video mining method and device |
| CN105022801A (en) * | 2015-06-30 | 2015-11-04 | 北京奇艺世纪科技有限公司 | Hot video mining method and hot video mining device |
| CN105007504A (en) * | 2015-07-13 | 2015-10-28 | 无锡天脉聚源传媒科技有限公司 | Browsing history processing method and device |
| CN106339447A (en) * | 2016-08-23 | 2017-01-18 | 达而观信息科技（上海）有限公司 | System and method for automatically predicting hot videos |
| CN106682111B (en) * | 2016-12-06 | 2019-09-13 | 腾讯科技（深圳）有限公司 | A kind of data recommendation method and its equipment |
| CN106682111A (en) * | 2016-12-06 | 2017-05-17 | 腾讯科技（深圳）有限公司 | Data recommendation method and equipment thereof |
| CN108881968A (en) * | 2017-05-15 | 2018-11-23 | 北京国双科技有限公司 | A kind of network video advertisement put-on method and system |
| CN108881968B (en) * | 2017-05-15 | 2020-10-30 | 北京国双科技有限公司 | Network video advertisement putting method and system |
| CN111104627A (en) * | 2018-10-29 | 2020-05-05 | 北京国双科技有限公司 | Hot event prediction method and device |
| CN111104627B (en) * | 2018-10-29 | 2023-04-07 | 北京国双科技有限公司 | Hot event prediction method and device |
| CN109889891A (en) * | 2019-03-05 | 2019-06-14 | 腾讯科技（深圳）有限公司 | Obtain the method, apparatus and storage medium of target media file |
| CN111026991A (en) * | 2019-12-05 | 2020-04-17 | 中国银行股份有限公司 | Data display method and device and computer equipment |
| CN111026991B (en) * | 2019-12-05 | 2023-08-18 | 中国银行股份有限公司 | Data display method and device and computer equipment |
| CN111048215A (en) * | 2019-12-13 | 2020-04-21 | 北京纵横无双科技有限公司 | CRM-based medical video production method and system |
| CN111048215B (en) * | 2019-12-13 | 2023-08-18 | 北京纵横无双科技有限公司 | Medical video production method and system based on CRM |
| CN116469039A (en) * | 2023-04-28 | 2023-07-21 | 青岛尘元科技信息有限公司 | Hot video event determination method and system, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103136280A (en) | System and method of automatically searching hot point video | |
| US11843651B2 (en) | Personalized recommendation method and system, and terminal device | |
| CN105404700B (en) | A kind of video column recommendation system and recommended method based on collaborative filtering | |
| US10417650B1 (en) | Distributed and automated system for predicting customer lifetime value | |
| US9712628B2 (en) | Click through rate estimation in varying display situations | |
| CA3076113C (en) | Methods and systems for creating a data-driven attribution model for assigning attribution credit to a plurality of events | |
| CN104602042B (en) | Label setting method based on user behavior | |
| KR101650117B1 (en) | Conversion path performance measures and reports | |
| CN103324718B (en) | Method and system based on humongous search Web log mining topic venation | |
| JP6267344B2 (en) | Content selection using quality control | |
| CN104035926B (en) | A kind of dispensing of internet information and system | |
| CN103136275A (en) | System and method for recommending personalized video | |
| CN103189856A (en) | Methods and apparatus to determine media impressions | |
| WO2021129055A1 (en) | Information prediction model training method and apparatus, information prediction method and apparatus, storage medium, and device | |
| CN105282565A (en) | Video recommendation method and device | |
| CN103942236A (en) | System and method for serving electronic content | |
| KR20140064958A (en) | System and method for indirectly classifying a computer based on usage | |
| US8799297B2 (en) | Evaluating supply of electronic content relating to keywords | |
| KR20190065181A (en) | System, method, and computer-readable medium recorded with program for mediation of advertising contracts and measurement of advertising performance | |
| WO2009026515A2 (en) | System and method for generating creatives using composite templates | |
| CN110880127B (en) | Consumption level prediction method and device, electronic equipment and storage medium | |
| CN103974097A (en) | Personalized user-generated video prefetching method and system based on popularity and social networks | |
| CN107493467B (en) | A kind of video quality evaluation method and device | |
| US20120260185A1 (en) | Path length selector | |
| CN107391681A (en) | Business datum ranks processing method and machinable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130605 |