CN107105349A - A kind of video recommendation method - Google Patents
A kind of video recommendation method Download PDFInfo
- Publication number
- CN107105349A CN107105349A CN201710349660.4A CN201710349660A CN107105349A CN 107105349 A CN107105349 A CN 107105349A CN 201710349660 A CN201710349660 A CN 201710349660A CN 107105349 A CN107105349 A CN 107105349A
- Authority
- CN
- China
- Prior art keywords
- video
- concept
- similarity
- justice
- msub
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 238000011524 similarity measure Methods 0.000 claims description 7
- 238000005194 fractionation Methods 0.000 abstract 1
- 230000000052 comparative effect Effects 0.000 description 2
- 238000000205 computational method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26258—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/482—End-user interface for program selection
- H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a kind of video recommendation method, method includes：When user watches video, the video information of current video is obtained；Some recommendation videos are found out from video server according to video information, current video is with recommending the video similarity of video to be more than threshold value；The broadcast address of the recommendation video found is returned, and is shown to user；Recommend the calculation procedure of the video similarity of video and current video as follows：Current video is obtained with recommending the video information of video, using the video information of current video as the first video information, recommends the video information of video to be used as the second video information；Carry out concept fractionation respectively to the first video information and the second video information and obtain the first concept set and the second concept set；Calculate the concept similarity between the second concept in the first concept and the second concept set in the first concept set；Maximum in each concept similarity that calculating is obtained is used as current video and recommends the video similarity between video.
Description
Technical field
Video information process field of the present invention, more particularly to a kind of video recommendation method.
Technical field
With the improvement of people ' s living standards and mobile Internet development, people whenever and wherever possible can be in fixed computer
Or video playback is carried out on mobile device, this also becomes at present the entertainment way of prevalence the most.
In general, user can select to play video online in the environment of with WiFi, and in the environment without WiFi
Under the conditions of can select to play the video or other local videos downloaded, can so save customer flow, improve and play
Effect.
But existing video playback mode is all to play the video that has had determined, and user is often wish to see and
The related video of current video, though there is the method for recommending video in the prior art, but its degree of accuracy is low, and correlation is not
Foot, it is impossible to reach and be well matched with accuracy.
The content of the invention
The invention provides a kind of video recommendation method.
A kind of video recommendation method that the present invention is provided, method includes：
When user watches video, the video information of current video is obtained；
The video information is sent to video server, if being found out according to the video information from video server
Dry to recommend video, the current video is with recommending the video similarity of video to be more than threshold value；
The broadcast address of the recommendation video found is returned, and is shown to user；
The calculation procedure of the video similarity of the recommendation video and current video is as follows：
Current video is obtained with recommending the video information of video, is believed the video information of current video as the first video
Breath, recommends the video information of video to be used as the second video information；
Concept is carried out to first video information and splits the first concept set for obtaining including several concepts, to described
Second video information carries out concept and splits the second concept set for obtaining including several concepts；
Calculate between the second concept in the first concept and the second concept set in the first concept set
Concept similarity, first concept is any concept in the first concept set, and second concept is described second
Any concept in concept set；
Maximum in each concept similarity that calculating is obtained is used as current video and recommends the video phase between video
Like degree.
Alternatively, the video information includes：One kind in video name, synopsis, protagonist, director, video type
Or it is several.
Alternatively, the current video is local video or Online Video.
Alternatively, the recommendation video is shown in the form of a list.
Alternatively, the quantity for recommending video is less than or equal to 5.
Alternatively, first concept calculated in the first concept set and second in the second concept set
Concept similarity between concept includes：
Calculate first concept the first independent justice is former and the first independent justice of the second concept it is former between it is first similar
Degree；
Calculate first concept the second independent justice is former and the second independent justice of the second concept it is former between it is second similar
Degree, the second independent justice was the every other independent justice original in addition to the described first independent justice is former in semantic formula originally；
The third phase calculated between the relation justice original of first concept and the relation justice original of the second concept is seemingly spent；
Calculate the 4th similarity between the Signifier original of first concept and the Signifier original of the second concept；
According to first similarity, the second similarity, third phase like spending, the first concept described in the 4th Similarity Measure with
Concept similarity between second concept.
Alternatively, between the first independent justice of first independent the justice original and the second concept for calculating first concept is former
The first similarity include：
The first similarity Sim is calculated according to equation below1(V1,V2)：
Wherein, described (d+ α) represents that two justice are former, and d is to join with the path length in adopted former hierarchical system, α for constant
Number.
Alternatively, calculate first concept the second independent justice is former and the second independent justice of the second concept it is former between the
Two similarities include：
1) by all independent justice predecessor meaning pairings of the semantic formula of the first concept and the second concept, par wise irrelevance is calculated
Adopted original similarity；
2) it is classified as one group by a pair of similarity value maximum；
3) it is former to remaining independent justice to perform step 2 two-by-two), until all independent justice are former all to complete packet；
4) second similarity is used as to the Similarity Measure average value of each group.
Alternatively, it is described according to first similarity, the second similarity, third phase like spend, the 4th Similarity Measure institute
The concept similarity stated between the first concept and second concept includes：
Concept similarity Sim (the S are calculated according to equation belowi,Tj)：
In the present invention, when user watches video, obtain
The video information of current video, some recommendation videos are found out according to the video information from video server, described current
Video is with recommending the video similarity of video to be more than threshold value；The broadcast address of the recommendation video found is returned, and is shown to use
Family；The calculation procedure of the video similarity of the recommendation video and current video is as follows：Current video is obtained with recommending video
Video information, using the video information of current video as the first video information, recommends the video information of video to be used as the second video
Information；Concept is carried out to first video information and splits to obtain including the first concept set of several concepts, to described the
Two video informations carry out concept and split the second concept set for obtaining including several concepts；Calculate in the first concept set
The first concept and the second concept set in the second concept between concept similarity, first concept is described the
Any concept in one concept set, second concept is any concept in the second concept set；Calculating is obtained
Each concept similarity in maximum be used as current video and recommend video between video similarity.In the present invention, pass through
The video information of current video is obtained, to find out the recommendation video high with current video similarity, and user is recommended, and adopt
Farthest cover the implication of word with the mode of concept set, so as to improve the accuracy of matching.
Brief description of the drawings
Fig. 1 is video recommendation method schematic flow sheet.
Embodiment
In order that those skilled in the art is better understood from technical scheme, it is below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is described in further detail.
Referring to Fig. 1, video recommendation method flow of the present invention includes：
101st, when user watches video, the video information of current video is obtained；
102nd, the video information is sent to video server, searched according to the video information from video server
Go out some recommendation videos, the current video is with recommending the video similarity of video to be more than threshold value；
103rd, the broadcast address of the recommendation video found is returned, and is shown to user；
The calculation procedure of the video similarity of the recommendation video and current video is as follows：
Current video is obtained with recommending the video information of video, is believed the video information of current video as the first video
Breath, recommends the video information of video to be used as the second video information；
Concept is carried out to first video information and splits the first concept set for obtaining including several concepts, to described
Second video information carries out concept and splits the second concept set for obtaining including several concepts；
Calculate between the second concept in the first concept and the second concept set in the first concept set
Concept similarity, first concept is any concept in the first concept set, and second concept is described second
Any concept in concept set；
Maximum in each concept similarity that calculating is obtained is used as current video and recommends the video phase between video
Like degree.
In a step 101, when user watches video, the video information of current video is obtained.
Wherein, user needs to be in presence when watching video in the present invention, so as to which video information is sent
The broadcast address of recommendation video is pushed to user to video server and by video server.But the currently watched video of user
Can be that local video can also be Online Video, i.e., described current video can be that local video can also be Online Video,
That is, user can be obtained its video information when watching local video or Online Video by video playback apparatus.
Video playback apparatus therein can be mobile terminal, for example mobile phone, flat board, removable computer etc. portable electronic
Equipment or other fixing equipments, such as PC computers.
Video information therein includes：One kind or several in video name, synopsis, protagonist, director, video type
Kind.
Video name therein is the current title of video, for example《The fast and the furious》, synopsis therein is
The featured performer that information is briefly summarized, as current video is acted the leading role of current video, director is the director of current video, video
Type then illustrates the style of current video, for example comedy, terror, love, action, science fiction, swordsman, war, crime, it is terrible,
Story of a play or opera etc..
By obtaining above- mentioned information and sending to video server, so that it is similar to facilitate video server therefrom to find
Video.Because above- mentioned information has covered all information of representing video content substantially.
In a step 102, the video information is sent to video server, according to the video information from Video service
Some recommendation videos are found out in device, the current video is with recommending the video similarity of video to be more than threshold value.
The video information of current video is sent to video server by video playback apparatus first, in video server
The video information and corresponding broadcast address of massive video are stored, video server have received the video letter of current video
After breath, it is compared with the video information of other storages, so as to be recommended according to comparison result, wherein the requirement compared is：
The current video is with recommending the video similarity of video to be more than threshold value.Specifically, refer to the video information of current video with
The video similarity of the video information of video therebetween is recommended to be more than threshold value.Because video information is made up of multiple words,
So by being disassembled to video information, you can compare video information of the video information of current video with recommending video
Video similarity.
In addition, it should be noted that, preferred pair video information of the present invention carried out between classification comparison, such as video name
Compare, be compared between video profile, is compared between video type, is compared if choosing multiple options, then excellent
The option comparative result of choosing at least 2/3 or more than 2/3 meets the requirement of video similarity, you can judge video to be compared as recommendation
Video.The option for example compared is 6, respectively video name, synopsis, protagonist, director, video type, producer, that
There should be the option comparative result of 4 or more than 4 to meet the requirement (being more than threshold value) of video similarity, just can determine that and compared
Compared with video for recommend video.
The calculating process to video similarity is described in detail below.
In Hownet, the conceptual description of notional word is made up of the description formula of following three kinds of forms：
(1) the former description formula of independent justice：Represented by " basic meaning is former " or " (specific word) "；
(2) the former description formula of relation justice：By " relation justice original=basic meaning is former " or " relation justice former=(specific word) " or
" (former=specific word of relation justice) " is represented, wherein the adopted original of relation refer to comprising " EventRole | dynamic character " and
The justice of " EventFeatures | dynamic attribute " this two class is former；
(3) the former description formula in Signifier：Represented by " relational symbol basic meaning is former " or " relational symbol (specific word) ", wherein
Relational symbol include " #, %, $, * ,+, ＆ ,@,、！", its relation each represented is repeated no more.
In actual applications, each concept is made up of multiple adopted originals, and adopted original is most basic, be not easy to the meaning split again
The least unit of justice.For example：" people ", although being an extremely complex concept, it can be the aggregate of many attribute,
It can be seen as a justice former.
It is former that all concepts can be decomposed into various justice.Should also there is a former set of limited justice simultaneously,
Adopted original therein is combined into a unlimited concept set.Word (including single-morpheme word) in Chinese is limited, and it can be with
Be used to the various simple or complicated concepts of expression, and between expression concept and concept, the attribute and category of concept
Relation between property.
Pass through the definition to adopted former and concept, it is possible to two word (such as regarding in the video information of current video
Frequency title, referred to as the first word；Video name in the video information of video to be compared is referred to as the second word) similarity carry out
Calculate, such as the first word X1With the second word X2If, the first word X1There is n concept [S1, S2,…,Sn], the second word
Language X2There is m concept [T1, T2,…,Tm], the first word X1With the second word X2Similarity Sim (X1, X2) it is each concept
The maximum of similarity：
Therefore, the first word X is obtained in order to calculate1With the second word X2Similarity Sim (X1, X2), then need to calculate every
Similarity between two concepts.
The similarity calculated between two concepts is then needed by many aspects come COMPREHENSIVE CALCULATING：
(1) the first independent former description formula of justice：
Because all concepts are all finally attributed to be represented originally with justice, the former Similarity Measure of justice is that concept is similar
The basis of degree., can be simply by language because all adopted primitive roots constitute tree-shaped justice original hierarchical system according to hyponymy
Justice distance calculates similarity.
Use Sim1(V1, V2) this part similarities of two concepts is represented, particularly as being the former similarities of two justice, specifically
Calculation formula is as follows：
Wherein (d+ α) represents that two justice are former, and d is and the path length in adopted former hierarchical system.α is one adjustable
Parameter, can set α value, for example in the Similarity of Words computational methods based on Hownet：α=0.5.
(2) other independent former description formulas of justice：Every other independent justice in semantic formula in addition to the first independent justice is former
Original, uses Sim2(V1, V2) this part similarities of two concepts is represented, specific calculation procedure is as follows：
A, first all independent justice predecessor meanings two expression formulas are matched, and calculate the former similarity of justice two-by-two；
Maximum a pair of b, value are classified as one group；
C, two-by-two similarity execution b former to remaining independently justice are walked.So repeatedly, packet is all completed until all.Appoint
The similarity of He Yiyuan and null value is defined as constant δ, for example：δ=0.2；
D, finally average.
(3) the former description formula of relation justice：All relations justice is former in semantic formula, uses Sim3(V1, V2) represent two generally
The former identical expression formula of relation justice, is divided into one group, calculates similarity, finally average by this part similarity read.
(4) the former description formula in Signifier：All Signifiers are former in semantic formula, use Sim4(V1, V2) represent two generally
Relational symbol identical expression formula, is divided into one group by this part similarity read, and is calculated similarity, is finally averaged.
In summary, shown in the similarity calculating method of two concepts such as formula (3).
In step 103, the broadcast address of the recommendation video found is returned, and is shown to user.
The quantity therein for recommending video can have multiple, and preferably be shown in the form of a list.For example user works as
It is preceding to watch video, then its side is provided with recommendation column, show the recommendation that video server is returned in column is recommended
The broadcast address of video, and the information such as the video name for recommending video can be shown, so that user determines the need for viewing correspondence
Recommendation video.When user clicks on broadcast address, then player will automatically go to corresponding broadcast address and play corresponding
Recommend video.
The quantity for recommending video should not be excessive, can excessively cause user's selection difficult, and is difficult to search, and reduces and pushes away
Efficiency is recommended, the present invention preferably lower than or equal to 5, such user targetedly can recommend video by fast steering, improve and see
See efficiency and experience.
Described above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to before
Embodiment is stated the present invention is described in detail, it will be understood by those within the art that：It still can be to preceding
State the technical scheme described in each embodiment to modify, or equivalent substitution is carried out to which part technical characteristic；And these
Modification is replaced, and the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (9)
1. a kind of video recommendation method, it is characterised in that methods described includes：
When user watches video, the video information of current video is obtained；
The video information is sent to video server, some push away is found out from video server according to the video information
Video is recommended, the current video is with recommending the video similarity of video to be more than threshold value；
The broadcast address of the recommendation video found is returned, and is shown to user；
The calculation procedure of the video similarity of the recommendation video and current video is as follows：
Current video is obtained with recommending the video information of video, using the video information of current video as the first video information, is pushed away
The video information of video is recommended as the second video information；
Concept is carried out to first video information and splits the first concept set for obtaining including several concepts, to described second
Video information carries out concept and splits the second concept set for obtaining including several concepts；
Calculate the concept between the second concept in the first concept and the second concept set in the first concept set
Similarity, first concept is any concept in the first concept set, and second concept is second concept
Any concept in set；
Maximum in each concept similarity that calculating is obtained is used as current video and recommends the video similarity between video.
2. video recommendation method according to claim 1, it is characterised in that the video information includes：Video name, play
One or more in feelings brief introduction, protagonist, director, video type.
3. video recommendation method according to claim 1, it is characterised in that the current video is local video or online
Video.
4. video recommendation method according to claim 1, it is characterised in that the recommendation video is carried out in the form of a list
Display.
5. video recommendation method according to claim 1, it is characterised in that the quantity of the recommendation video is less than or equal to
5.
6. video recommendation method according to claim 1, it is characterised in that in calculating the first concept set
The concept similarity between the second concept in first concept and the second concept set includes：
Calculate first the first similarity independently between justice original and the first independent justice original of the second concept of first concept；
Calculate second the second similarity independently between justice original and the second independent justice original of the second concept of first concept, institute
It was the every other independent justice original in semantic formula in addition to the described first independent justice is former originally to state the second independent justice；
The third phase calculated between the relation justice original of first concept and the relation justice original of the second concept is seemingly spent；
Calculate the 4th similarity between the Signifier original of first concept and the Signifier original of the second concept；
According to first similarity, the second similarity, third phase like spending, the first concept described in the 4th Similarity Measure with it is described
Concept similarity between second concept.
7. video recommendation method according to claim 6, it is characterised in that the first of calculating first concept is only
The first similarity between first independent justice of vertical justice original and the second concept is former includes：
The first similarity Sim is calculated according to equation below1(V1,V2)：
<mrow>
<msub>
<mi>Sim</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>V</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>V</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mi>&alpha;</mi>
<mrow>
<mi>d</mi>
<mo>+</mo>
<mi>&alpha;</mi>
</mrow>
</mfrac>
<mo>;</mo>
</mrow>
Wherein, described (d+ α) represents that two justice are former, d be with the path length in adopted former hierarchical system, α is constant parameter.
8. video recommendation method according to claim 7, it is characterised in that calculate the second independent justice of first concept
The second similarity between the independent justice of the second of former and the second concept is former includes：
1) by all independent justice predecessor meaning pairings of the semantic formula of the first concept and the second concept, par wise irrelevance justice is calculated former
Similarity；
2) it is classified as one group by a pair of similarity value maximum；
3) it is former to remaining independent justice to perform step 2 two-by-two), until all independent justice are former all to complete packet；
4) second similarity is used as to the Similarity Measure average value of each group.
9. video recommendation method according to claim 8, it is characterised in that described according to first similarity, second
The concept similarity bag of similarity, third phase like described in degree, the 4th Similarity Measure between the first concept and second concept
Include：
Concept similarity Sim (the S are calculated according to equation belowi,Tj)：
<mrow>
<mi>S</mi>
<mi>i</mi>
<mi>m</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>S</mi>
<mi>i</mi>
</msub>
<mo>,</mo>
<msub>
<mi>T</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>x</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>4</mn>
</munderover>
<msub>
<mi>&beta;</mi>
<mi>x</mi>
</msub>
<munderover>
<mo>&Pi;</mo>
<mrow>
<mi>y</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>Sim</mi>
<mi>y</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>V</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>V</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mo>.</mo>
</mrow>
2
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710349660.4A CN107105349A (en) | 2017-05-17 | 2017-05-17 | A kind of video recommendation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710349660.4A CN107105349A (en) | 2017-05-17 | 2017-05-17 | A kind of video recommendation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107105349A true CN107105349A (en) | 2017-08-29 |
Family
ID=59669855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710349660.4A Pending CN107105349A (en) | 2017-05-17 | 2017-05-17 | A kind of video recommendation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107105349A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108255970A (en) * | 2017-12-26 | 2018-07-06 | 努比亚技术有限公司 | A kind of video retrieval method, terminal and computer readable storage medium |
| CN108307240A (en) * | 2018-02-12 | 2018-07-20 | 北京百度网讯科技有限公司 | Video recommendation method and device |
| CN109446379A (en) * | 2018-10-31 | 2019-03-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling information |
| 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 |
| 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 |
| CN110519621A (en) * | 2019-09-20 | 2019-11-29 | 北京字节跳动网络技术有限公司 | Video recommendation method, device, electronic equipment and computer-readable medium |
| CN110619063A (en) * | 2019-09-20 | 2019-12-27 | 北京字节跳动网络技术有限公司 | Video pushing method and device based on video searching and electronic equipment |
| CN111782109A (en) * | 2020-07-24 | 2020-10-16 | 咪咕数字传媒有限公司 | Electronic work display method, display device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090319883A1 (en) * | 2008-06-19 | 2009-12-24 | Microsoft Corporation | Automatic Video Annotation through Search and Mining |
| CN101655856A (en) * | 2009-09-15 | 2010-02-24 | 西安交通大学 | Method for obtaining user specific metaknowledge interest |
| CN103150667A (en) * | 2013-03-14 | 2013-06-12 | 北京大学 | Individualization recommending method based on mechanical structure |
| CN103970729A (en) * | 2014-04-29 | 2014-08-06 | 河海大学 | Multi-subject extracting method based on semantic categories |
| CN105760544A (en) * | 2016-03-16 | 2016-07-13 | 合网络技术（北京）有限公司 | Video recommendation method and device |
-
2017
- 2017-05-17 CN CN201710349660.4A patent/CN107105349A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090319883A1 (en) * | 2008-06-19 | 2009-12-24 | Microsoft Corporation | Automatic Video Annotation through Search and Mining |
| CN101655856A (en) * | 2009-09-15 | 2010-02-24 | 西安交通大学 | Method for obtaining user specific metaknowledge interest |
| CN103150667A (en) * | 2013-03-14 | 2013-06-12 | 北京大学 | Individualization recommending method based on mechanical structure |
| CN103970729A (en) * | 2014-04-29 | 2014-08-06 | 河海大学 | Multi-subject extracting method based on semantic categories |
| CN105760544A (en) * | 2016-03-16 | 2016-07-13 | 合网络技术（北京）有限公司 | Video recommendation method and device |
Non-Patent Citations (1)
| Title |
|---|
| 金博等: "基于语义理解的本文相似度算法", 《大连理工大学学报》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN108255970A (en) * | 2017-12-26 | 2018-07-06 | 努比亚技术有限公司 | A kind of video retrieval method, terminal and computer readable storage medium |
| CN108307240A (en) * | 2018-02-12 | 2018-07-20 | 北京百度网讯科技有限公司 | Video recommendation method and device |
| CN108307240B (en) * | 2018-02-12 | 2019-10-22 | 北京百度网讯科技有限公司 | Video recommendation method and device |
| CN109446379A (en) * | 2018-10-31 | 2019-03-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling information |
| 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 |
| CN110519621A (en) * | 2019-09-20 | 2019-11-29 | 北京字节跳动网络技术有限公司 | Video recommendation method, device, electronic equipment and computer-readable medium |
| CN110619063A (en) * | 2019-09-20 | 2019-12-27 | 北京字节跳动网络技术有限公司 | Video pushing method and device based on video searching and electronic equipment |
| US11979643B2 (en) | 2019-09-20 | 2024-05-07 | Beijing Bytedance Network Technology Co., Ltd. | Video pushing method and apparatus based on video search, and electronic device |
| CN111782109A (en) * | 2020-07-24 | 2020-10-16 | 咪咕数字传媒有限公司 | Electronic work display method, display device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107105349A (en) | A kind of video recommendation method | |
| KR102008000B1 (en) | Computing similarity between media programs | |
| US20170169341A1 (en) | Method for intelligent recommendation | |
| US8909626B2 (en) | Determining user preference of items based on user ratings and user features | |
| WO2017181612A1 (en) | Personalized video recommendation method and device | |
| CN104317835B (en) | The new user of video terminal recommends method | |
| Pyo et al. | LDA-based unified topic modeling for similar TV user grouping and TV program recommendation | |
| US8819716B2 (en) | Apparatus, system, method and computer readable recording medium storing the program for related recommendation of TV program contents and web contents | |
| CN104199896B (en) | The video similarity of feature based classification is determined and video recommendation method | |
| US11025583B2 (en) | Recommendation system based on common interests in social networks | |
| CN105653572A (en) | Resource processing method and apparatus | |
| US10387915B2 (en) | Digital magazine recommendations by topic | |
| CN102063433A (en) | Method and device for recommending related items | |
| CN106961636B (en) | Commodity information recommendation method and device and electronic equipment | |
| CN104462573A (en) | Method and device for displaying video retrieval results | |
| WO2009126815A2 (en) | Diversified, self-organizing map system and method | |
| Park et al. | Online video recommendation through tag-cloud aggregation | |
| WO2013184957A1 (en) | Systems and methods of classifying content items | |
| CN112100513A (en) | Knowledge graph-based recommendation method, device, equipment and computer readable medium | |
| CN103745100A (en) | Item-based explicit and implicit feedback mixing collaborative filtering recommendation algorithm | |
| CN104008139A (en) | Method and device for creating video index table and method and device for recommending video | |
| US11430049B2 (en) | Communication via simulated user | |
| CN102959539B (en) | Item recommendation method during a kind of repeat in work and system | |
| CN111310046A (en) | Object recommendation method and device | |
| US20140236969A1 (en) | Apparatus and method for recommending contents based on metadata graph |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1242872 Country of ref document: HK |
|
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170829 |
|
| WD01 | Invention patent application deemed withdrawn after publication |