CN104219575A - Related video recommending method and system - Google Patents
Related video recommending method and system Download PDFInfo
- Publication number
- CN104219575A CN104219575A CN201310373572.XA CN201310373572A CN104219575A CN 104219575 A CN104219575 A CN 104219575A CN 201310373572 A CN201310373572 A CN 201310373572A CN 104219575 A CN104219575 A CN 104219575A
- Authority
- CN
- China
- Prior art keywords
- video
- candidate
- list
- videos
- current
- 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
Abstract
The invention discloses a related video recommending method and system. The related video recommending method includes steps of acquiring current videos, analyzing text information of the current videos, extracting keywords and class information of the current videos, and acquiring a keyword list and the class information; automatically generating a plurality of query conditions according to the keyword list and the class information, indexing and integrating the videos on websites according to each query condition, acquiring a first alternation list and adding the same into an alternation video set; scoring quality of each alternation video in the alternation video set; calculating scores of the videos in the alternation video set according to quality scoring results, and acquiring a related recommending list of the current videos according to the scores of the videos. By the aid of the related video recommending method and system, high-quality videos can be provided for users, and requirements of the users can be sufficiently met.
Description
Technical field
The present invention, about a kind of Online Video technology, particularly relates to a kind of associated video recommend method and system.
Background technology
Along with the explosive increase of internet content, especially the fast development of video website and social network sites, has a large amount of fresh contents every day by production and consumption, meanwhile, concerning a user, from a large amount of irrelevant content, find that interested information is more and more difficult.
Concerning video website, commending system is very important part.First, the number of videos of domestic each large video website accumulation is usually at several order of magnitude of ten million, and concerning user's uploaded videos (ugc), the content of video embraces a wide spectrum of ideas, disperse very much and enrich, being difficult in user's short time find oneself real interested video; Secondly, it is long that user watches the time that a video spends, and adds that one section of advertisement can be play in most of website before displaying video, if the video inadequacy registered permanent residence taste recommended, is a very large injury to Consumer's Experience; Again, good commending system can attract user to watch more video, thus is website increase flow and income.
Visible, online associated video is recommended to be that video website helps user search and watch the Method and kit for of certain specific area video.Relative to traditional videogram browsing mode or video search mode, associated video is recommended can when the inappropriate search word of user, by analyzing user's historical behavior, find the specific area of user's request, recommend at this specific area, avoid the input of search word and the repeatedly click process of hierarchical directory, make to search and the video watching certain particular type is more easily simple.
Existing associated video recommended technology, mainly comprises two kinds of methods: based on video collaborative filtering recommending with based on user collaborative filtered recommendation.The former is by calculating the similarity of video and video, and the associated video the most similar to viewing recording of video is recommended user, and the latter is then based on viewing record, calculates user's similarity, the associated video that similar user has seen recently is recommended user.It is all that whole viewing records based on user are analyzed that these two kinds of modes are given tacit consent to, and the result returned is the video with all history video all similar, and for the user that hobby is more single, recommendation results is relatively good.Such as user has seen one or multi-section action movie, releases action movie the hottest recently, and user experiences can be relatively good.
But, along with the surf the Net behavior of viewing video of the development of internet video website and user increases, the demand of user to viewing video type and feature is more various, the video meeting all types and feature will not exist or may be second-rate, adopt said method to be likely to comprise compared with multiple features but the video of the outstanding feature of neither one, affect the interest of user.
Summary of the invention
For overcoming the deficiency that above-mentioned prior art exists, the object of the present invention is to provide a kind of associated video recommend method and system, by carrying out explication de texte to video subject and content, other video relevant in automatic discovery content, and the broadcasting record of user is analyzed, the preference of digging user, simultaneously also by edit list recommending module reduction playlist, acquisition candidate video combines, and generate final relevant associated video recommendation list in conjunction with the quality score of video, better for user provides high-quality video, fully meet the viewing demand of user.
For reaching above-mentioned and other object, the present invention proposes a kind of associated video recommend method, comprises the steps:
Step one, obtains current video;
Step 2, analyzes the text message of this current video, extracts keyword and the classification information of this current video, obtains lists of keywords and classification information;
Step 3, according to this lists of keywords and classification information, automatically generates some querying conditions, according to each querying condition, all videos on website is carried out to index and merge, obtaining the first candidate list, and being joined candidate video set;
Step 4, marks to the quality of each candidate video in this candidate video set;
Step 5, according to quality score result, after calculating, the relevance scores of each video in this candidate video set, obtains the associated recommendation list of this current video according to the relevance scores of each video.
Further, in step 5, to all videos of this candidate video set, a weight is given respectively according to rank, finally be multiplied by the quality score of video, obtain the relevance scores of each video, and the relevance scores of each video is sorted, choose the associated recommendation list of top n result as this current video.
Further, after step 5, also comprise the step of the associated recommendation list calculated being carried out to buffer memory.
Further, when the recommendation list of a request video, if there has been the recommendation results of this video in buffer memory, then the recommendation list in direct return cache.
Further, regularly take out the video play number and exceed certain number of times, the recommendation results of this video is recalculated to step 5 by step one, and upgrades buffer memory.
Further, if certain video is not play for a long time again, recommendation results will be removed from buffer memory.
Further, before step 4, also comprise the steps: the preference of digging user, obtain the co-occurrence video of this current video, form the second candidate list, and joined in this candidate collection.
Further, the step obtaining the co-occurrence video of current video comprises the steps:
First, all videos having co-occurrence with this current video are added up;
To the video V of each co-occurrence, calculate count(A, V)/count(V), wherein count(A, V) and be the number of times of A and V co-occurrence, count(V) be the broadcasting summation of V;
Get count(A, V)/count(V) the maximum several videos of value are this second candidate list.
Further, before step 4, also comprise the steps:
Check whether this current video is being edited in certain video play lists arranged;
If there is such playlist, then the video in the playlist relevant to this current video is taken out, composition the 3rd candidate list, and join in candidate collection.
Further, step one comprises the steps:
Chinese word segmentation is carried out to the text message of this current video, obtains the list of candidate word;
Whether then extract the part of speech of candidate word, length, occurrence number, be the features such as rubbish word, and be the scoring of each candidate word or imparting weight according to those characteristic synthetics, getting the candidate word that mark is higher or weighted value is high is the lists of keywords of video.
For reaching above-mentioned and other object, the present invention also provides a kind of associated video commending system, at least comprises:
Content analysis module, for analyzing the text message of current video, extracts keyword and the classification information of this current video, obtains lists of keywords and classification information;
Video search module, according to this lists of keywords and classification information, automatically generates some querying conditions, according to each querying condition, all videos on website is carried out to index and merge, obtaining the first candidate list, and being joined candidate video set;
Quality score module, for marking to the quality of each candidate video in candidate video set;
Result-generation module, according to quality score result, after calculating, the relevance scores of each video in this candidate video set, obtains the associated recommendation list of this current video according to the relevance scores of each video.
Further, this system also comprises a cache module, for carrying out buffer memory by the associated recommendation list calculated.
Further, this system also comprises an edit list recommending module, for checking certain video play lists whether current video arranges editor, and in time there is certain video play lists, video relevant to this current video in this list is taken out, forms the 3rd candidate list.
Further, this system also comprises a co-occurrence and excavates module, for the preference of digging user, obtains the co-occurrence video of this current video, forms this second candidate list.
Further, text information comprises video title, description, user tag, and the type information is the classified information that video uploader is selected.
Further, the foundation of this quality score module to the quality score of video comprises broadcasting time, comment number of times, definition, thumbnail definition, length for heading, video duration.
Compared with prior art, a kind of associated video recommend method of the present invention and system, by content analysis module, explication de texte is carried out to video subject and content, other video relevant in automatic discovery content, and analyzed by the broadcasting record of co-occurrence excavation module to user, the preference of digging user, simultaneously also by edit list recommending module reduction playlist, acquisition candidate video combines, and generate final relevant associated video recommendation list in conjunction with the quality score of video, can better for user recommends the video of applicable each user self.
Accompanying drawing explanation
Fig. 1 is the flow chart of steps of a kind of associated video recommend method of the present invention;
Fig. 2 is the schematic diagram extracting current video keyword in present pre-ferred embodiments;
Fig. 3 is the system architecture diagram of a kind of associated video commending system of the present invention.
Embodiment
Below by way of 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 is also implemented by other different instantiation or is applied, and the every details in this specification also can based on different viewpoints and application, carries out various modification and change not deviating under spirit of the present invention.
Fig. 1 is the flow chart of steps of a kind of associated video recommend method of the present invention.As shown in Figure 1, a kind of associated video recommend method of the present invention, comprises the steps:
Step 101, obtains current video A.
Step 102, analyzes the text message of video A, extracts keyword and the classification information of video A, obtains lists of keywords and classification information.Here, the text message of video A comprises video title, description, user tag etc.First analytic process will carry out Chinese word segmentation to text message, obtains the list of candidate word; Then extract the part of speech of candidate word, length, occurrence number, whether be the features such as rubbish word, and mark according to these characteristic synthetics, also can give each candidate word weight according to these features, getting the candidate word that mark is higher or weighted value is high is the lists of keywords of video.Fig. 2 is the schematic diagram extracting current video keyword in present pre-ferred embodiments.Such as, the video title of current video is " Chinese domestic aircraft carrier Shanghai Kai Zhong Air India mother " fights secretly " and builds speed raising ", be described as " the domestic aircraft carrier of India descends water recently; PLA's aircraft carrier watt good lattice complete third time sea examination; the Liang Ge big country in Asia; start on the road of aircraft carrier and fight secretly; make 3 aircraft carrier fleets in 2 years; whether so surprising speed can realize as scheduled ", user tag is " China, aircraft carrier, build, build ", and step 102 item is analyzed above-mentioned text message, obtains the lists of keywords of this video: aircraft carrier, fight secretly, middle print.Owing to can select a classification for video during video uploader uploaded videos, classification information can obtain thus.
Step 103, according to the lists of keywords obtained and classification information, automatically generates some querying conditions, according to each querying condition, all videos on website is carried out to index and merge, obtaining the first candidate list, and being joined maximally related candidate video set.In present pre-ferred embodiments, querying condition is the combination in any of each keyword in classification information and lists of keywords, and lists of keywords is " aircraft carrier, fight secretly, middle print ", and classification information is military, then querying condition can be:
1. classification=military and query word=aircraft carrier is fought secretly
2. print in classification=military and query word=aircraft carrier
3. classification=military and query word=aircraft carrier
To each querying condition, full-text search engine Lucene by increasing income carries out index to all videos, the list of videos returned is obtained from Lucene, and the video in each list returned each querying condition merges, obtain the first candidate list C1, join in candidate video set C.
Step 104, marks to the quality of each candidate video in candidate video set.In present pre-ferred embodiments, the quality score of video is made up of a few part: broadcasting time, comment number of times, definition, thumbnail definition, length for heading, video duration.Broadcasting time and comment number of times The more the better, definition and thumbnail definition more high better, meanwhile, length for heading and video duration can not be too short.
Step 105, to all videos of candidate video set, gives a weight respectively according to rank, finally be multiplied by the quality score of video, obtain the relevance scores of each video, and the relevance scores of each video is sorted, choose the associated recommendation list of top n result as current video A.In present pre-ferred embodiments, obtain the relevance scores of each video: Relative_score (v)=score_Ci (v) * score_Ri (v) * quality (v), wherein score_Ci (v) according to video v from which candidate list, score_Ri (v) is according to the rank of video at candidate list, and quality (v) is the quality score of video.
Then, relevance scores Relative_score (v) of video is sorted, choose the associated recommendation list of top n result as video.
Preferably, after step 105, the present invention can also following steps: carry out buffer memory to the associated recommendation list calculated.When the recommendation list of a request video, if there has been the recommendation results of this video in buffer memory, do not need double counting, the recommendation list in direct return cache.
Meanwhile, because there constantly have user to upload to be new for video that is better quality, the present invention needs the recommendation results of the video recalculated termly in buffer memory, and the associated video that these are new recommends user.Therefore the present invention regularly (each hour) can take out the video play number and exceed certain number of times, the recommendation results of these videos is recalculated, and upgrades buffer memory.The present invention also can check the video in buffer memory, if a video is not all play for a long time again, recommendation results will be removed from buffer memory.
Preferably, before step 104, the associated video recommend method of the present invention can also comprise the steps: to check whether current video A is editing in certain video play lists arranged; If there is such playlist, then the video in the playlist relevant to current video A is taken out, composition the 3rd candidate list C3, and join in candidate collection C.
For carrying out associated video recommendation to user better, before step 104, the associated video recommend method of the present invention can also comprise the steps: the preference of digging user, obtains the co-occurrence video of current video A, form the second candidate list C2, and joined candidate in conjunction with in C.In present pre-ferred embodiments, can be obtained by the broadcasting record adding up all users every day here.If after a user finishes watching A video, seen again the videos such as B, C, then claimed A and B co-occurrence once, in like manner, A and C also co-occurrence once, B and C also, is designated as (A, B), (A, C), (B, C).
Therefore digging user finishes watching the preference after current video A, and the step namely obtaining co-occurrence video also comprises the steps:
1, all videos having co-occurrence with A are first added up.
2, to the video V of each co-occurrence, count(A, V is calculated)/count(V).Wherein count(A, V) be the number of times of A and V co-occurrence, count(V) be the broadcasting summation of V.
3, count(A, V is got)/count(V) the maximum several videos of value are the second candidate list C2.
Visible, the associated video recommend method of the present invention, by carrying out explication de texte to video subject and content, finds other video relevant in content automatically; Meanwhile, also analyze the broadcasting record of user, the preference of digging user, namely user is after finishing watching some videos, to which video is most interested in; In addition, for the video that some are very popular, some playlists can be arranged by editor is manual, improve the recommendation quality of associated video further, such as " the Guo De guiding principle cross-talk collection of choice specimens " etc.; Finally, in conjunction with the quality score of video, generate final relevant associated video recommendation list, the present invention can better for user recommends the video of applicable each user self.
In addition, because the quantity of video is a lot, and playback volume is very large, can not be real-time be the list of all video generating recommendations.When after the associated video list calculating a video, list is cached in database by the present invention, to improve the performance of system.If this video is play within a certain period of time in a large number, system obtains nearest result by again settling accounts it; If again do not play in contrary a period of time, the buffer memory of its recommendation list will remove from database.
Fig. 3 is the system architecture diagram of a kind of associated video commending system of the present invention.As shown in Figure 3, a kind of associated video commending system of the present invention, at least comprises: content analysis module 301, video search module 302, quality score module 303 and result-generation module 304.
Wherein content analysis module 301 is for analyzing the text message of current displaying video A, extracts keyword and the classification information of video A, obtains lists of keywords and classification information.Here, the text message of current video A comprises video title, description, user tag etc.Fig. 2 is the schematic diagram extracting current video keyword in present pre-ferred embodiments.Such as, the video title of current video is " Chinese domestic aircraft carrier Shanghai Kai Zhong Air India mother " fights secretly " and builds speed raising ", be described as that " the domestic aircraft carrier of India descends water recently, PLA's aircraft carrier watt good lattice complete third time sea examination, the Liang Ge big country in Asia, the road of aircraft carrier starts and fights secretly, within 2 years, make 3 aircraft carrier fleets, whether so surprising speed can realize as scheduled ", user tag is " China, aircraft carrier, build, build ", first content analysis module 301 carries out Chinese word segmentation to text message, obtain the list of candidate word, then the part of speech of candidate word is extracted, length, occurrence number, whether be the features such as rubbish word, and mark according to these characteristic synthetics, also each candidate word weight can be given according to these features, get the lists of keywords that mark is higher or weighted value is high candidate word is video A: aircraft carrier, fight secretly, middle print.Owing to can select a classification for video during video uploader uploaded videos, classification information can obtain thus
Video search module 302, the lists of keywords obtained according to content analysis module 301 and classification information, the some querying conditions of automatic generation, according to each querying condition, all videos on website are carried out index and merged, obtain the first candidate list C1, and joined maximally related candidate video set.In present pre-ferred embodiments, querying condition is the combination in any of each keyword in classification information and lists of keywords, and if lists of keywords is " aircraft carrier, fight secretly, middle print ", classification information is military, then querying condition can be:
1. classification=military and query word=aircraft carrier is fought secretly
2. print in classification=military and query word=aircraft carrier
3. classification=military and query word=aircraft carrier
To each querying condition, full-text search engine Lucene by increasing income carries out index to all videos, the list of videos returned is obtained from Lucene, and the video in each list returned each querying condition merges, obtain the first candidate list C1, join in candidate video set C.
Quality score module 303, for marking to the quality of each candidate video in candidate video set.In present pre-ferred embodiments, the quality score of video is made up of a few part: broadcasting time, comment number of times, definition, thumbnail definition, length for heading, video duration.Broadcasting time and comment number of times The more the better, definition and thumbnail definition more high better, meanwhile, length for heading and video duration can not be too short.
Result-generation module 304, to all videos of candidate video set, a weight is given respectively according to rank, finally be multiplied by the quality score of video, obtain the relevance scores of each video, and the relevance scores of each video is sorted, choose the associated recommendation list of top n result as current video A.In present pre-ferred embodiments, the relevance scores of each video: Relative_score (v)=score_Ci (v) * score_Ri (v) * quality (v), wherein score_Ci (v) according to video v from which candidate list, score_Ri (v) is according to the rank of video at candidate list, and quality (v) is the quality score of video.
Preferably, the video system of the present invention also comprises a cache module 305, for carrying out buffer memory by the associated recommendation list calculated.Like this when the recommendation list of a request video, if there has been the recommendation results of this video in buffer memory, do not need double counting, the recommendation list in direct return cache.
Preferably, the video system of the present invention also comprises an edit list recommending module 307, for checking certain video play lists whether current video A arranges editor, and in time there is certain video play lists, video relevant to current video A in this list is taken out, form the 3rd candidate list C3, and join in candidate collection C.
Preferably, the video system of the present invention also comprises a co-occurrence and excavates module 306, for the preference of digging user, obtains the co-occurrence video of current video A, forms the second candidate list C2, and joined candidate in conjunction with in C.In present pre-ferred embodiments, can be obtained by the broadcasting record adding up all users every day here.If after a user finishes watching A video, seen again the videos such as B, C, then claimed A and B co-occurrence once, in like manner, A and C also co-occurrence once, B and C also, is designated as (A, B), (A, C), (B, C).Specifically, co-occurrence is excavated module 306 and is first added up all videos having co-occurrence with A, but the video V to each co-occurrence, calculate count(A, V)/count(V), get count(A, V)/count(V) the maximum several videos of value are the second candidate list C2, wherein count(A, V) be the number of times of A and V co-occurrence, count(V) be the broadcasting summation of V.
In sum, a kind of associated video recommend method of the present invention and system, by content analysis module, explication de texte is carried out to video subject and content, other video relevant in automatic discovery content, and analyzed by the broadcasting record of co-occurrence excavation module to user, the preference of digging user, simultaneously also by edit list recommending module reduction playlist, acquisition candidate video combines, and generate final relevant associated video recommendation list in conjunction with the quality score of video, can better for user recommends the video of applicable each user self.
Compared with prior art, the present invention has following advantage:
1, due to the quality score of the interest preference, the content of video, the suggestion of editor and the video that consider user in recommendation process, not only ensure that recommendation results is high-quality video, and fully can meet the viewing demand of user.
2, no matter have no precedent to one the video playing record, or had a large amount of popular video playing record, the present invention can both generate high-quality recommendation results, and therefore the present invention has good robustness.
3, because the present invention has fine caching mechanism, therefore not only there is good performance, also can ensure upgrading in time to popular video.
Above-described embodiment is illustrative principle of the present invention and effect thereof only, but not for limiting the present invention.Any those skilled in the art all without prejudice under spirit of the present invention and category, can carry out modifying to above-described embodiment and change.Therefore, the scope of the present invention, should listed by claims.
Claims (16)
1. an associated video recommend method, comprises the steps:
Step one, obtains current video;
Step 2, analyzes the text message of this current video, extracts keyword and the classification information of this current video, obtains lists of keywords and classification information;
Step 3, according to this lists of keywords and classification information, automatically generates some querying conditions, according to each querying condition, all videos on website is carried out to index and merge, obtaining the first candidate list, and being joined candidate video set;
Step 4, marks to the quality of each candidate video in this candidate video set;
Step 5, according to quality score result, after calculating, the relevance scores of each video in this candidate video set, obtains the associated recommendation list of this current video according to the relevance scores of each video.
2. a kind of associated video recommend method as claimed in claim 1, it is characterized in that: in step 5, to all videos of this candidate video set, a weight is given respectively according to rank, finally be multiplied by the quality score of video, obtain the relevance scores of each video, and the relevance scores of each video is sorted, choose the associated recommendation list of top n result as this current video.
3. a kind of associated video recommend method as claimed in claim 1, is characterized in that, after step 5, also comprises the step of the associated recommendation list calculated being carried out to buffer memory.
4. a kind of associated video recommend method as claimed in claim 3, is characterized in that: when the recommendation list of a request video, if there has been the recommendation results of this video in buffer memory, then and the recommendation list in direct return cache.
5. a kind of associated video recommend method as claimed in claim 4, is characterized in that: regularly take out the video play number and exceed certain number of times, the recommendation results of this video recalculated to step 5 by step one, and upgrade buffer memory.
6. a kind of associated video recommend method as claimed in claim 5, is characterized in that: if certain video is not play for a long time again, recommendation results will be removed from buffer memory.
7. a kind of associated video recommend method as claimed in claim 1, is characterized in that, before step 4, also comprise the steps: the preference of digging user, obtain the co-occurrence video of this current video, form the second candidate list, and joined in this candidate collection.
8. a kind of associated video recommend method as claimed in claim 7, is characterized in that, the step obtaining the co-occurrence video of current video comprises the steps:
First, all videos having co-occurrence with this current video are added up;
To the video V of each co-occurrence, calculate count(A, V)/count(V), wherein count(A, V) and be the number of times of A and V co-occurrence, count(V) be the broadcasting summation of V;
Get count(A, V)/count(V) the maximum several videos of value are this second candidate list.
9. a kind of associated video recommend method as claimed in claim 1, is characterized in that, before step 4, also comprise the steps:
Check whether this current video is being edited in certain video play lists arranged;
If there is such playlist, then the video in the playlist relevant to this current video is taken out, composition the 3rd candidate list, and join in candidate collection.
10. a kind of associated video recommend method as claimed in claim 1, it is characterized in that, step one comprises the steps:
Chinese word segmentation is carried out to the text message of this current video, obtains the list of candidate word;
Whether then extract the part of speech of candidate word, length, occurrence number, be the features such as rubbish word, and be the scoring of each candidate word or imparting weight according to those characteristic synthetics, getting the candidate word that mark is higher or weighted value is high is the lists of keywords of video.
11. 1 kinds of associated video commending systems, at least comprise:
Content analysis module, for analyzing the text message of current video, extracts keyword and the classification information of this current video, obtains lists of keywords and classification information;
Video search module, according to this lists of keywords and classification information, automatically generates some querying conditions, according to each querying condition, all videos on website is carried out to index and merge, obtaining the first candidate list, and being joined candidate video set;
Quality score module, for marking to the quality of each candidate video in candidate video set;
Result-generation module, according to quality score result, after calculating, the relevance scores of each video in this candidate video set, obtains the associated recommendation list of this current video according to the relevance scores of each video.
12. a kind of associated video commending systems as claimed in claim 11, is characterized in that: this system also comprises a cache module, for carrying out buffer memory by the associated recommendation list calculated.
13. a kind of associated video commending systems as claimed in claim 11, it is characterized in that: this system also comprises an edit list recommending module, for checking certain video play lists whether current video arranges editor, and in time there is certain video play lists, video relevant to this current video in this list is taken out, forms the 3rd candidate list.
14. a kind of associated video commending systems as claimed in claim 11, is characterized in that: this system also comprises a co-occurrence and excavates module, for the preference of digging user, obtains the co-occurrence video of this current video, forms this second candidate list.
15. a kind of associated video commending systems as claimed in claim 11, is characterized in that: text information comprises video title, description, user tag, and the type information is the classified information that video uploader is selected.
16. a kind of associated video commending systems as claimed in claim 11, is characterized in that: the foundation of this quality score module to the quality score of video comprises broadcasting time, comment number of times, definition, thumbnail definition, length for heading, video duration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310373572.XA CN104219575B (en) | 2013-05-29 | 2013-08-23 | Method and system for recommending related videos |
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013102068894 | 2013-05-29 | ||
| CN201310206889.4 | 2013-05-29 | ||
| CN201310206889 | 2013-05-29 | ||
| CN201310373572.XA CN104219575B (en) | 2013-05-29 | 2013-08-23 | Method and system for recommending related videos |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104219575A true CN104219575A (en) | 2014-12-17 |
| CN104219575B CN104219575B (en) | 2020-05-12 |
Family
ID=52100648
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310373572.XA Active CN104219575B (en) | 2013-05-29 | 2013-08-23 | Method and system for recommending related videos |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104219575B (en) |
Cited By (61)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834686A (en) * | 2015-04-17 | 2015-08-12 | 中国科学院信息工程研究所 | Video recommendation method based on hybrid semantic matrix |
| CN104951558A (en) * | 2015-06-30 | 2015-09-30 | 北京奇艺世纪科技有限公司 | Video to-be-improved item determining method and device |
| CN104994403A (en) * | 2015-07-13 | 2015-10-21 | 无锡天脉聚源传媒科技有限公司 | Video contrasting method and device |
| CN104994444A (en) * | 2015-07-06 | 2015-10-21 | 无锡天脉聚源传媒科技有限公司 | Method and device for displaying video summary information |
| CN105392027A (en) * | 2015-11-09 | 2016-03-09 | 天脉聚源(北京)传媒科技有限公司 | Method and apparatus for pushing instant news video |
| CN105516738A (en) * | 2015-12-04 | 2016-04-20 | 青岛海信传媒网络技术有限公司 | Video-on-demand processing method, device and equipment |
| CN105740468A (en) * | 2016-03-07 | 2016-07-06 | 达而观信息科技（上海）有限公司 | Individuation recommendation method and system combined with content publisher information |
| CN105843857A (en) * | 2016-03-16 | 2016-08-10 | 合网络技术（北京）有限公司 | Video recommendation method and device |
| CN105868377A (en) * | 2016-03-31 | 2016-08-17 | 北京奇艺世纪科技有限公司 | Method and device for pushing information |
| CN105912676A (en) * | 2016-04-13 | 2016-08-31 | 北京思特奇信息技术股份有限公司 | Method and system for identifying video preference based on Internet retrieval keywords |
| CN105916032A (en) * | 2015-12-08 | 2016-08-31 | 乐视网信息技术（北京）股份有限公司 | Video recommendation method and video recommendation terminal equipment |
| CN105930484A (en) * | 2016-04-29 | 2016-09-07 | 合网络技术（北京）有限公司 | Multimedia resource recommendation method and apparatus |
| WO2016188347A1 (en) * | 2015-05-26 | 2016-12-01 | 广州神马移动信息科技有限公司 | Network quality evaluation method and device, network content sorting method and system, computing apparatus and non-transitory machine-readable storage medium |
| CN106303719A (en) * | 2016-08-02 | 2017-01-04 | 合网络技术（北京）有限公司 | A kind of method and device recommending video in order |
| CN106303596A (en) * | 2015-05-15 | 2017-01-04 | 北京国双科技有限公司 | Video recommendation system, method and device |
| WO2017005054A1 (en) * | 2015-07-06 | 2017-01-12 | 腾讯科技（深圳）有限公司 | Video recommendation method, server and storage medium |
| CN106649848A (en) * | 2016-12-30 | 2017-05-10 | 合网络技术（北京）有限公司 | Video recommendation method and video recommendation device |
| CN106686414A (en) * | 2016-12-30 | 2017-05-17 | 合网络技术（北京）有限公司 | Video recommendation method and device |
| CN106791947A (en) * | 2016-12-28 | 2017-05-31 | 北京金山安全软件有限公司 | Method and device for transmitting network video and electronic equipment |
| CN106951494A (en) * | 2017-03-14 | 2017-07-14 | 腾讯科技（深圳）有限公司 | A kind of information recommendation method and device |
| CN107145571A (en) * | 2017-05-05 | 2017-09-08 | 广东艾檬电子科技有限公司 | A kind of searching method and device |
| CN107193927A (en) * | 2017-05-17 | 2017-09-22 | 深圳市茁壮网络股份有限公司 | Information recommendation method and device |
| WO2017166512A1 (en) * | 2016-03-31 | 2017-10-05 | 乐视控股（北京）有限公司 | Video classification model training method and video classification method |
| WO2017166477A1 (en) * | 2016-03-28 | 2017-10-05 | 乐视控股（北京）有限公司 | Method and device for obtaining video information |
| CN107251524A (en) * | 2014-12-29 | 2017-10-13 | 阿卡麦科技公司 | The mobile device user of management prognostic prefetching content is ordered and service preferences |
| CN107343209A (en) * | 2017-06-29 | 2017-11-10 | 达而观信息科技（上海）有限公司 | A kind of UGC associated video generation methods based on increment collaborative filtering |
| CN107451148A (en) * | 2016-05-31 | 2017-12-08 | 北京金山安全软件有限公司 | Video classification method and device and electronic equipment |
| CN107656938A (en) * | 2016-07-26 | 2018-02-02 | 北京搜狗科技发展有限公司 | It is a kind of to recommend method and apparatus, a kind of device for being used to recommend |
| CN107729486A (en) * | 2017-10-17 | 2018-02-23 | 北京奇艺世纪科技有限公司 | A kind of video searching method and device |
| CN107888982A (en) * | 2017-11-17 | 2018-04-06 | 北京小米移动软件有限公司 | Video information recommends method and device |
| CN107924401A (en) * | 2015-08-24 | 2018-04-17 | 谷歌有限责任公司 | Video recommendations based on video title |
| CN108055349A (en) * | 2017-12-28 | 2018-05-18 | 广州酷狗计算机科技有限公司 | Recommend the methods, devices and systems of k song audios |
| CN108462900A (en) * | 2017-02-22 | 2018-08-28 | 合网络技术（北京）有限公司 | Video recommendation method and device |
| CN108509457A (en) * | 2017-02-28 | 2018-09-07 | 阿里巴巴集团控股有限公司 | A kind of recommendation method and apparatus of video data |
| CN109151500A (en) * | 2018-09-29 | 2019-01-04 | 北京数美时代科技有限公司 | A kind of main broadcaster's recommended method, system and computer equipment for net cast |
| CN109325146A (en) * | 2018-11-12 | 2019-02-12 | 平安科技（深圳）有限公司 | A kind of video recommendation method, device, storage medium and server |
| CN109710828A (en) * | 2018-12-20 | 2019-05-03 | 中国联合网络通信集团有限公司 | Course resources management method, device and the equipment of Virtual Learning Environment |
| CN109729432A (en) * | 2019-01-28 | 2019-05-07 | 北京达佳互联信息技术有限公司 | Video recommendation method, device and server |
| CN109729392A (en) * | 2019-01-15 | 2019-05-07 | 深圳市云歌人工智能技术有限公司 | The method, apparatus and storage medium of video push |
| CN109800326A (en) * | 2019-01-24 | 2019-05-24 | 广州虎牙信息科技有限公司 | A kind of method for processing video frequency, device, equipment and storage medium |
| CN109829109A (en) * | 2019-01-28 | 2019-05-31 | 山西大学 | Recommended method based on Co-occurrence Analysis |
| 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 |
| CN109996125A (en) * | 2019-05-07 | 2019-07-09 | 北京字节跳动网络技术有限公司 | Generate method, apparatus, electronic equipment and the storage medium of video list |
| CN110019944A (en) * | 2017-12-21 | 2019-07-16 | 飞狐信息技术（天津）有限公司 | A kind of recommended method and system of video |
| CN110019941A (en) * | 2017-08-22 | 2019-07-16 | 飞狐信息技术（天津）有限公司 | Video recommendation method and system |
| CN110222233A (en) * | 2019-06-14 | 2019-09-10 | 北京达佳互联信息技术有限公司 | Video recommendation method, device, server and storage medium |
| CN110366043A (en) * | 2019-08-20 | 2019-10-22 | 北京字节跳动网络技术有限公司 | Method for processing video frequency, device, electronic equipment and readable medium |
| CN110598009A (en) * | 2019-09-12 | 2019-12-20 | 北京达佳互联信息技术有限公司 | Method and device for searching works, electronic equipment and storage medium |
| CN110858914A (en) * | 2018-08-23 | 2020-03-03 | 北京优酷科技有限公司 | Video material recommendation method and device |
| CN111400546A (en) * | 2020-03-18 | 2020-07-10 | 腾讯科技（深圳）有限公司 | Video recall method and video recommendation method and device |
| CN111541917A (en) * | 2020-05-08 | 2020-08-14 | 广州市百果园信息技术有限公司 | Determination method of recommended video, video playing method, device and equipment |
| CN111901629A (en) * | 2020-09-07 | 2020-11-06 | 三星电子（中国）研发中心 | Method and device for generating and playing video stream |
| CN112416987A (en) * | 2020-11-24 | 2021-02-26 | 致讯科技(天津)有限公司 | Experience quality determination method and device based on user portrait and electroencephalogram data |
| CN112637685A (en) * | 2020-12-11 | 2021-04-09 | 上海连尚网络科技有限公司 | Video processing method and device |
| CN113691831A (en) * | 2021-08-25 | 2021-11-23 | 深圳市视壮科技有限公司 | DVB (digital video broadcasting) playing content searching method and system |
| CN114095763A (en) * | 2021-11-25 | 2022-02-25 | 上海幻电信息科技有限公司 | Video list pushing method and playing quality evaluation method |
| CN114363660A (en) * | 2021-12-24 | 2022-04-15 | 腾讯科技（武汉）有限公司 | Video collection determining method and device, electronic equipment and storage medium |
| WO2022100273A1 (en) * | 2020-11-12 | 2022-05-19 | 海信视像科技股份有限公司 | Receiving device and generation method |
| CN114697748A (en) * | 2020-12-25 | 2022-07-01 | 深圳Tcl新技术有限公司 | Video recommendation method based on voice recognition and computer equipment |
| CN116910304A (en) * | 2023-09-06 | 2023-10-20 | 北京小糖科技有限责任公司 | Method, device, electronic equipment and storage medium for replacing video recommendation reason |
| WO2024082756A1 (en) * | 2022-10-17 | 2024-04-25 | 北京字跳网络技术有限公司 | Video search method and apparatus, server, and terminal device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1640117A (en) * | 2002-02-25 | 2005-07-13 | 皇家飞利浦电子股份有限公司 | Adaptive audio-video program recommendation system |
| CN101158971A (en) * | 2007-11-15 | 2008-04-09 | 深圳市迅雷网络技术有限公司 | Search result ordering method and device based on search engine |
| JP2009252186A (en) * | 2008-04-10 | 2009-10-29 | Ricoh Co Ltd | Information delivering device, information delivering method, information delivering program, and recording medium |
| CN101719167A (en) * | 2010-01-15 | 2010-06-02 | 北京暴风网际科技有限公司 | Interactive movie searching method |
| CN102253994A (en) * | 2011-07-08 | 2011-11-23 | 宇龙计算机通信科技(深圳)有限公司 | Automatic searching device and method |
| CN102279865A (en) * | 2010-06-08 | 2011-12-14 | 索尼公司 | Content recommendation device and content recommendation method |
| CN102521321A (en) * | 2011-12-02 | 2012-06-27 | 华中科技大学 | Video search method based on search term ambiguity and user preferences |
-
2013
- 2013-08-23 CN CN201310373572.XA patent/CN104219575B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1640117A (en) * | 2002-02-25 | 2005-07-13 | 皇家飞利浦电子股份有限公司 | Adaptive audio-video program recommendation system |
| CN101158971A (en) * | 2007-11-15 | 2008-04-09 | 深圳市迅雷网络技术有限公司 | Search result ordering method and device based on search engine |
| JP2009252186A (en) * | 2008-04-10 | 2009-10-29 | Ricoh Co Ltd | Information delivering device, information delivering method, information delivering program, and recording medium |
| CN101719167A (en) * | 2010-01-15 | 2010-06-02 | 北京暴风网际科技有限公司 | Interactive movie searching method |
| CN102279865A (en) * | 2010-06-08 | 2011-12-14 | 索尼公司 | Content recommendation device and content recommendation method |
| CN102253994A (en) * | 2011-07-08 | 2011-11-23 | 宇龙计算机通信科技(深圳)有限公司 | Automatic searching device and method |
| CN102521321A (en) * | 2011-12-02 | 2012-06-27 | 华中科技大学 | Video search method based on search term ambiguity and user preferences |
Cited By (89)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107251524A (en) * | 2014-12-29 | 2017-10-13 | 阿卡麦科技公司 | The mobile device user of management prognostic prefetching content is ordered and service preferences |
| CN104834686A (en) * | 2015-04-17 | 2015-08-12 | 中国科学院信息工程研究所 | Video recommendation method based on hybrid semantic matrix |
| CN106303596A (en) * | 2015-05-15 | 2017-01-04 | 北京国双科技有限公司 | Video recommendation system, method and device |
| WO2016188347A1 (en) * | 2015-05-26 | 2016-12-01 | 广州神马移动信息科技有限公司 | Network quality evaluation method and device, network content sorting method and system, computing apparatus and non-transitory machine-readable storage medium |
| CN104951558A (en) * | 2015-06-30 | 2015-09-30 | 北京奇艺世纪科技有限公司 | Video to-be-improved item determining method and device |
| CN104994444A (en) * | 2015-07-06 | 2015-10-21 | 无锡天脉聚源传媒科技有限公司 | Method and device for displaying video summary information |
| US10575037B2 (en) | 2015-07-06 | 2020-02-25 | Tencent Technology (Shenzhen) Company Limited | Video recommending method, server, and storage media |
| CN104994444B (en) * | 2015-07-06 | 2018-09-25 | 无锡天脉聚源传媒科技有限公司 | A kind of display methods and device of video summary information |
| WO2017005054A1 (en) * | 2015-07-06 | 2017-01-12 | 腾讯科技（深圳）有限公司 | Video recommendation method, server and storage medium |
| CN104994403A (en) * | 2015-07-13 | 2015-10-21 | 无锡天脉聚源传媒科技有限公司 | Video contrasting method and device |
| CN107924401A (en) * | 2015-08-24 | 2018-04-17 | 谷歌有限责任公司 | Video recommendations based on video title |
| CN105392027A (en) * | 2015-11-09 | 2016-03-09 | 天脉聚源(北京)传媒科技有限公司 | Method and apparatus for pushing instant news video |
| CN105392027B (en) * | 2015-11-09 | 2019-04-09 | 天脉聚源(北京)传媒科技有限公司 | A kind of method and device pushing lastest news video |
| CN105516738B (en) * | 2015-12-04 | 2019-08-06 | 聚好看科技股份有限公司 | Video on demand processing method, device and equipment |
| CN105516738A (en) * | 2015-12-04 | 2016-04-20 | 青岛海信传媒网络技术有限公司 | Video-on-demand processing method, device and equipment |
| CN105916032A (en) * | 2015-12-08 | 2016-08-31 | 乐视网信息技术（北京）股份有限公司 | Video recommendation method and video recommendation terminal equipment |
| CN105740468B (en) * | 2016-03-07 | 2019-10-18 | 达而观信息科技（上海）有限公司 | A kind of personalized recommendation method and system of combined content issuer information |
| CN105740468A (en) * | 2016-03-07 | 2016-07-06 | 达而观信息科技（上海）有限公司 | Individuation recommendation method and system combined with content publisher information |
| CN105843857B (en) * | 2016-03-16 | 2019-08-27 | 合一网络技术(北京)有限公司 | Video recommendation method and device |
| CN105843857A (en) * | 2016-03-16 | 2016-08-10 | 合网络技术（北京）有限公司 | Video recommendation method and device |
| WO2017166477A1 (en) * | 2016-03-28 | 2017-10-05 | 乐视控股（北京）有限公司 | Method and device for obtaining video information |
| CN105868377A (en) * | 2016-03-31 | 2016-08-17 | 北京奇艺世纪科技有限公司 | Method and device for pushing information |
| WO2017166512A1 (en) * | 2016-03-31 | 2017-10-05 | 乐视控股（北京）有限公司 | Video classification model training method and video classification method |
| CN105868377B (en) * | 2016-03-31 | 2019-05-10 | 北京奇艺世纪科技有限公司 | A kind of information-pushing method and device |
| CN105912676A (en) * | 2016-04-13 | 2016-08-31 | 北京思特奇信息技术股份有限公司 | Method and system for identifying video preference based on Internet retrieval keywords |
| CN105930484A (en) * | 2016-04-29 | 2016-09-07 | 合网络技术（北京）有限公司 | Multimedia resource recommendation method and apparatus |
| CN107451148A (en) * | 2016-05-31 | 2017-12-08 | 北京金山安全软件有限公司 | Video classification method and device and electronic equipment |
| CN107656938A (en) * | 2016-07-26 | 2018-02-02 | 北京搜狗科技发展有限公司 | It is a kind of to recommend method and apparatus, a kind of device for being used to recommend |
| CN106303719B (en) * | 2016-08-02 | 2019-09-17 | 优酷网络技术（北京）有限公司 | A kind of method and device for recommending video in order |
| CN106303719A (en) * | 2016-08-02 | 2017-01-04 | 合网络技术（北京）有限公司 | A kind of method and device recommending video in order |
| CN106791947A (en) * | 2016-12-28 | 2017-05-31 | 北京金山安全软件有限公司 | Method and device for transmitting network video and electronic equipment |
| CN106649848B (en) * | 2016-12-30 | 2020-12-29 | 阿里巴巴（中国）有限公司 | Video recommendation method and device |
| CN106686414B (en) * | 2016-12-30 | 2019-07-23 | 合一网络技术(北京)有限公司 | Video recommendation method and device |
| CN106686414A (en) * | 2016-12-30 | 2017-05-17 | 合网络技术（北京）有限公司 | Video recommendation method and device |
| CN106649848A (en) * | 2016-12-30 | 2017-05-10 | 合网络技术（北京）有限公司 | Video recommendation method and video recommendation device |
| CN108462900A (en) * | 2017-02-22 | 2018-08-28 | 合网络技术（北京）有限公司 | Video recommendation method and device |
| CN108462900B (en) * | 2017-02-22 | 2020-07-28 | 阿里巴巴（中国）有限公司 | Video recommendation method and device |
| TWI753044B (en) * | 2017-02-28 | 2022-01-21 | 香港商阿里巴巴集團服務有限公司 | Recommended method and apparatus for video material |
| WO2018157746A1 (en) * | 2017-02-28 | 2018-09-07 | 阿里巴巴集团控股有限公司 | Recommendation method and apparatus for video data |
| CN108509457A (en) * | 2017-02-28 | 2018-09-07 | 阿里巴巴集团控股有限公司 | A kind of recommendation method and apparatus of video data |
| CN106951494B (en) * | 2017-03-14 | 2022-01-04 | 腾讯科技（深圳）有限公司 | Information recommendation method and device |
| CN106951494A (en) * | 2017-03-14 | 2017-07-14 | 腾讯科技（深圳）有限公司 | A kind of information recommendation method and device |
| CN107145571B (en) * | 2017-05-05 | 2020-02-14 | 广东艾檬电子科技有限公司 | Searching method and device |
| CN107145571A (en) * | 2017-05-05 | 2017-09-08 | 广东艾檬电子科技有限公司 | A kind of searching method and device |
| CN107193927A (en) * | 2017-05-17 | 2017-09-22 | 深圳市茁壮网络股份有限公司 | Information recommendation method and device |
| CN107343209A (en) * | 2017-06-29 | 2017-11-10 | 达而观信息科技（上海）有限公司 | A kind of UGC associated video generation methods based on increment collaborative filtering |
| CN110019941A (en) * | 2017-08-22 | 2019-07-16 | 飞狐信息技术（天津）有限公司 | Video recommendation method and system |
| CN107729486A (en) * | 2017-10-17 | 2018-02-23 | 北京奇艺世纪科技有限公司 | A kind of video searching method and device |
| CN107729486B (en) * | 2017-10-17 | 2021-02-09 | 北京奇艺世纪科技有限公司 | Video searching method and device |
| CN107888982A (en) * | 2017-11-17 | 2018-04-06 | 北京小米移动软件有限公司 | Video information recommends method and device |
| CN110019944A (en) * | 2017-12-21 | 2019-07-16 | 飞狐信息技术（天津）有限公司 | A kind of recommended method and system of video |
| CN108055349A (en) * | 2017-12-28 | 2018-05-18 | 广州酷狗计算机科技有限公司 | Recommend the methods, devices and systems of k song audios |
| CN108055349B (en) * | 2017-12-28 | 2020-11-13 | 广州酷狗计算机科技有限公司 | Method, device and system for recommending K song audio |
| CN110858914A (en) * | 2018-08-23 | 2020-03-03 | 北京优酷科技有限公司 | Video material recommendation method and device |
| CN110858914B (en) * | 2018-08-23 | 2021-11-26 | 阿里巴巴（中国）有限公司 | Video material recommendation method and device |
| CN109151500A (en) * | 2018-09-29 | 2019-01-04 | 北京数美时代科技有限公司 | A kind of main broadcaster's recommended method, system and computer equipment for net cast |
| CN109325146A (en) * | 2018-11-12 | 2019-02-12 | 平安科技（深圳）有限公司 | A kind of video recommendation method, device, storage medium and server |
| CN109325146B (en) * | 2018-11-12 | 2024-05-07 | 平安科技（深圳）有限公司 | Video recommendation method and device, storage medium and server |
| CN109710828A (en) * | 2018-12-20 | 2019-05-03 | 中国联合网络通信集团有限公司 | Course resources management method, device and the equipment of Virtual Learning Environment |
| CN109729392A (en) * | 2019-01-15 | 2019-05-07 | 深圳市云歌人工智能技术有限公司 | The method, apparatus and storage medium of video push |
| CN109800326A (en) * | 2019-01-24 | 2019-05-24 | 广州虎牙信息科技有限公司 | A kind of method for processing video frequency, device, equipment and storage medium |
| CN109829109A (en) * | 2019-01-28 | 2019-05-31 | 山西大学 | Recommended method based on Co-occurrence Analysis |
| CN109829109B (en) * | 2019-01-28 | 2021-02-02 | 山西大学 | Recommendation method based on co-occurrence analysis |
| CN109729432A (en) * | 2019-01-28 | 2019-05-07 | 北京达佳互联信息技术有限公司 | Video recommendation method, device and server |
| 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 |
| CN109996125A (en) * | 2019-05-07 | 2019-07-09 | 北京字节跳动网络技术有限公司 | Generate method, apparatus, electronic equipment and the storage medium of video list |
| CN110222233A (en) * | 2019-06-14 | 2019-09-10 | 北京达佳互联信息技术有限公司 | Video recommendation method, device, server and storage medium |
| CN110366043A (en) * | 2019-08-20 | 2019-10-22 | 北京字节跳动网络技术有限公司 | Method for processing video frequency, device, electronic equipment and readable medium |
| CN110598009B (en) * | 2019-09-12 | 2022-04-22 | 北京达佳互联信息技术有限公司 | Method and device for searching works, electronic equipment and storage medium |
| CN110598009A (en) * | 2019-09-12 | 2019-12-20 | 北京达佳互联信息技术有限公司 | Method and device for searching works, electronic equipment and storage medium |
| CN111400546B (en) * | 2020-03-18 | 2020-12-01 | 腾讯科技（深圳）有限公司 | Video recall method and video recommendation method and device |
| CN111400546A (en) * | 2020-03-18 | 2020-07-10 | 腾讯科技（深圳）有限公司 | Video recall method and video recommendation method and device |
| CN111541917B (en) * | 2020-05-08 | 2022-06-10 | 广州市百果园信息技术有限公司 | Determination method of recommended video, video playing method, device and equipment |
| CN111541917A (en) * | 2020-05-08 | 2020-08-14 | 广州市百果园信息技术有限公司 | Determination method of recommended video, video playing method, device and equipment |
| CN111901629A (en) * | 2020-09-07 | 2020-11-06 | 三星电子（中国）研发中心 | Method and device for generating and playing video stream |
| WO2022100273A1 (en) * | 2020-11-12 | 2022-05-19 | 海信视像科技股份有限公司 | Receiving device and generation method |
| CN112416987A (en) * | 2020-11-24 | 2021-02-26 | 致讯科技(天津)有限公司 | Experience quality determination method and device based on user portrait and electroencephalogram data |
| CN112637685B (en) * | 2020-12-11 | 2024-01-30 | 上海连尚网络科技有限公司 | Video processing method and device |
| CN112637685A (en) * | 2020-12-11 | 2021-04-09 | 上海连尚网络科技有限公司 | Video processing method and device |
| CN114697748A (en) * | 2020-12-25 | 2022-07-01 | 深圳Tcl新技术有限公司 | Video recommendation method based on voice recognition and computer equipment |
| CN114697748B (en) * | 2020-12-25 | 2024-05-03 | 深圳Tcl新技术有限公司 | Video recommendation method and computer equipment based on voice recognition |
| CN113691831A (en) * | 2021-08-25 | 2021-11-23 | 深圳市视壮科技有限公司 | DVB (digital video broadcasting) playing content searching method and system |
| CN114095763B (en) * | 2021-11-25 | 2024-03-12 | 上海幻电信息科技有限公司 | Video list pushing method and play quality assessment method |
| CN114095763A (en) * | 2021-11-25 | 2022-02-25 | 上海幻电信息科技有限公司 | Video list pushing method and playing quality evaluation method |
| CN114363660A (en) * | 2021-12-24 | 2022-04-15 | 腾讯科技（武汉）有限公司 | Video collection determining method and device, electronic equipment and storage medium |
| CN114363660B (en) * | 2021-12-24 | 2023-09-08 | 腾讯科技（武汉）有限公司 | Video collection determining method and device, electronic equipment and storage medium |
| WO2024082756A1 (en) * | 2022-10-17 | 2024-04-25 | 北京字跳网络技术有限公司 | Video search method and apparatus, server, and terminal device |
| CN116910304B (en) * | 2023-09-06 | 2023-12-08 | 北京小糖科技有限责任公司 | Method, device, electronic equipment and storage medium for replacing video recommendation reason |
| CN116910304A (en) * | 2023-09-06 | 2023-10-20 | 北京小糖科技有限责任公司 | Method, device, electronic equipment and storage medium for replacing video recommendation reason |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104219575B (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104219575A (en) | Related video recommending method and system | |
| CN102929928B (en) | Multidimensional-similarity-based personalized news recommendation method | |
| CN105142028B (en) | The content of TV program search of triple play oriented is with recommending method | |
| CN102929873B (en) | Method and device for extracting searching value terms based on context search | |
| Firan et al. | Bringing order to your photos: event-driven classification of flickr images based on social knowledge | |
| Awad et al. | Trecvid semantic indexing of video: A 6-year retrospective | |
| JP5409268B2 (en) | Information presenting apparatus and portable terminal | |
| CN105975472A (en) | Method and device for recommendation | |
| KR101252670B1 (en) | Apparatus, method and computer readable recording medium for providing related contents | |
| CN105378720A (en) | Media content discovery and character organization techniques | |
| CN101551825A (en) | Personalized film recommendation system and method based on attribute description | |
| Sen et al. | Video skimming: Taxonomy and comprehensive survey | |
| Liu et al. | Query sensitive dynamic web video thumbnail generation | |
| CN106354860A (en) | Method for automatically labelling and pushing information resource based on label sets | |
| Chiny et al. | Netflix recommendation system based on TF-IDF and cosine similarity algorithms | |
| CN106528633A (en) | Method for improving social attention of video based on keyword recommendation | |
| KR101140318B1 (en) | Keyword Advertising Method and System Based on Meta Information of Multimedia Contents Information like Ccommercial Tags etc. | |
| Abbas | Improved context-aware youtube recommender system with user feedback analysis | |
| CN113407729B (en) | Judicial-oriented personalized case recommendation method and system | |
| KR20110043568A (en) | Keyword Advertising Method and System Based on Meta Information of Multimedia Contents Information like Ccommercial Tags etc. | |
| US20230244739A1 (en) | Content opportunity scoring and automation | |
| CN116610858A (en) | Information distribution method, device, electronic equipment and storage medium | |
| Roshdy et al. | An efficient content-based video recommendation | |
| Lucchese et al. | Recommender Systems. | |
| Hopfgartner et al. | Capturing multiple interests in news video retrieval by incorporating the ostensive model |
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: 20180607 Address after: 201203 7, 1 Lane 666 lane, Zhang Heng Road, Pudong New Area, Shanghai. Applicant after: SHANGHAI ZHANGMEN 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: Cool Sheng (Tianjin) Technology Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180801 Address after: 300450 Tianjin Binhai New Area Tianjin eco city animation road 126 anime building B1 area two layer 201-243 Applicant after: Cool Sheng (Tianjin) Technology Co., Ltd. Address before: 201203 7, 1 Lane 666 lane, Zhang Heng Road, Pudong New Area, Shanghai. Applicant before: SHANGHAI ZHANGMEN TECHNOLOGY CO., LTD. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20181218 Address after: 201306 N2025 room 24, 2 New Town Road, mud town, Pudong New Area, Shanghai Applicant after: Shanghai Lian Shang network technology Co., Ltd Address before: 300450 Tianjin Binhai New Area Tianjin eco city animation road 126 anime building B1 area two layer 201-243 Applicant before: Cool Sheng (Tianjin) Technology Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |