CN107197368B - Determine user to the method and system of multimedia content degree of concern - Google Patents
Determine user to the method and system of multimedia content degree of concern Download PDFInfo
- Publication number
- CN107197368B CN107197368B CN201710311715.2A CN201710311715A CN107197368B CN 107197368 B CN107197368 B CN 107197368B CN 201710311715 A CN201710311715 A CN 201710311715A CN 107197368 B CN107197368 B CN 107197368B
- Authority
- CN
- China
- Prior art keywords
- barrage
- time
- period
- content
- real
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000011156 evaluation Methods 0.000 claims description 38
- 230000005484 gravity Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 3
- 230000007935 neutral effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000007619 statistical method 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
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- 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
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
-
- 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
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
-
- 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
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The present invention relates to a kind of determining users to the method for multimedia content degree of concern, determination for barrage video-frequency playing content, it is included at least: the play time of target video being divided into multiple period s, and each period s real-time barrage occurred is grouped;Corresponding each period s record is grouped the figure of merit of real-time barrage, and carries out weight analysis according to the figure of merit of real-time barrage, obtains the importance value θ of the video clip of corresponding period s;According to the importance value θ of the video clip, the video content of user's concern is determined.This method has the advantages that accuracy height, strong real-time.
Description
Technical field
The present invention relates to video processing techniques more particularly to a kind of determining user to multimedia content degree of concern
Method and system is determined for the degree of concern of barrage video content.
Background technique
Video content has become the pith of internet traffic, is remembered by the history that analysis user watches video content
Record, obtains the hobby of user, user experience can be improved, and targetedly provides media content or advertisement, in raising perhaps
The interests of advertising provider.It is existing it is general obtain user to the preference of video content by data such as video click rate, flows, this
Kind analysis also lacks automated analysis for the analysis of the importance of video interior segments to the preference for being directed to entire video content
Method.
For the technical problem, patent CN103503467B discloses a kind of method of determining user's attentinal contents and sets
It is standby, by operating point and corresponding time point of the record user when watching video, determined according to operating point corresponding time point
The starting point and end point of video clip, and the video clip is determined according to the operating point that the determination video clip is carried out
Importance value, so that it is determined that user concern video content;Specific operating point is broadcastings, pause, F.F., rewind, slowly
Into, slowly move back, scale.This method realizes the significance level of the mark video clip content of automation, but when user operates
Operating point be intended to not single, in addition to using slow-motion, rewind to video preference, preference is not using F.F. etc., it is also possible to exist
Situations such as midway is left, viewing is added in other people is watched, operating point caused by this kind of situation is not judging within the scope of importance value,
Its accuracy rate for influencing video clip importance value.
On the other hand, exchange evaluation means of the existing barrage as conventional network video viewing user, have experience
Property high, real-time and the characteristics of have a strong temperament;Applicant thinks that barrage is very intuitive and accurate and has reacted viewer to real-time network view
The fancy grade of frequency segment is extremely effectively and accurate as judgment criteria of the user to network video content attention rate.
Summary of the invention
The purpose of the present invention is to overcome the defects in the prior art, designs a kind of determining user to multimedia inner cylinder
The method of degree of concern carries out the judge of degree of concern mainly for the contents fragment of barrage video, determines from judging in information
The importance value of video interior segments, and then the video content of user's concern can be determined according to importance value;This method
Have the advantages that accuracy height, strong real-time.
To achieve the above object, the technical scheme adopted by the invention is that a kind of determining user closes multimedia content
The method of note degree, the method are used for the determination of barrage video-frequency playing content, include at least:
The real-time barrage that the play time of target video is divided into multiple period s, and each period s is occurred into
Row grouping;
Corresponding each period s record is grouped the figure of merit of real-time barrage, and according to the figure of merit of real-time barrage into
Row weight analysis obtains the importance value θ of the video clip of corresponding period s;
According to the importance value θ of the video clip, the video content of user's concern is determined;
The figure of merit of the real-time barrage includes the barrage quantity ε and number of users η for delivering barrage;Corresponding period s
Video clip importance value θ=ε ω1+ηω2, the ω1For weight coefficient of the barrage quantity in evaluation system, institute
State ω2To deliver weight coefficient of the number of users of barrage in evaluation system.
The present invention also provides a kind of determining users to the system of multimedia content degree of concern, and the system is at least wrapped
It includes:
Segment and barrage grouped element are played, for the play time of target video to be divided into multiple period s, and will
The real-time barrage that each period s occurs is grouped;
Segment barrage recording unit is paid close attention to, the figure of merit for being grouped real-time barrage for corresponding to each period s record, institute
The figure of merit for stating real-time barrage includes the barrage quantity ε and number of users η for delivering barrage;
Segment barrage statistics and analytical unit are paid close attention to, for counting the figure of merit of real-time barrage, obtains corresponding period s
Video clip importance value θ, and according to importance value θ determine user concern video content.
By upper technical solution it is found that the present invention determines user to this by the statistical analysis to target video barrage information
Intuitive, accurate barrage information is carried out automation mark, and obtains the importance number of video clip by the degree of concern of video clip
Value is the video content that can determine user's concern according to importance value;This method is novel, accuracy is high and strong real-time, obtains
Concern information out is more diversified.
Detailed description of the invention
Fig. 1 is present invention determine that user is to the flow diagram of one embodiment of multimedia content degree of concern method;
Fig. 2 is present invention determine that user is to the structural schematic diagram of one embodiment of multimedia content degree of concern system;
Fig. 3 is present invention determine that user is to the flow diagram of multimedia content degree of concern method second embodiment;
Fig. 4 is present invention determine that user is to the structural schematic diagram of multimedia content degree of concern system second embodiment.
Specific embodiment
With reference to the accompanying drawings and examples, further description of the specific embodiments of the present invention.Following embodiment is only
For clearly illustrating technical solution of the present invention, and not intended to limit the protection scope of the present invention.
Fig. 1 is present invention determine that user illustrates the process of one embodiment of method of multimedia content degree of concern
Figure, this method comprises:
Step 11: the play time of target video is divided into multiple period s, and the reality that each period s is occurred
When barrage be grouped;
Step 12: corresponding each period s record is grouped the figure of merit and content of real-time barrage, and according to real-time barrage
Figure of merit carry out weight analysis, obtain the importance value θ of the video clip of corresponding period s;
Wherein, the figure of merit of the real-time barrage includes the barrage quantity ε and number of users η for delivering barrage;When to correspondence
Between section s video clip importance value θ=ε ω1+ηω2, the ω1The weight system for being barrage quantity in evaluation system
Number, the ω2To deliver weight coefficient of the number of users of barrage in evaluation system;
Step 13: according to the importance value θ of the video clip, determining the video content of user's concern.
The video content segments of multiple user's concerns can be directly determined by the above method;It is first determined relative to documents
Single user again counts the video content of multiple users concern, and the method for determining the importance number of video content is more high
It imitates, directly.
Fig. 2 is the structural representation of determination user in the embodiment of the present invention to the system of multimedia content degree of concern
Figure, including play segment and barrage grouped element, concern segment barrage recording unit and concern segment barrage statistics and analysis
Unit.
Wherein, it plays segment and barrage grouped element is used to the play time of target video being divided into multiple period s,
And each period s real-time barrage occurred is grouped.Concern segment barrage recording unit is for corresponding to each period s
Record is grouped the figure of merit and content of real-time barrage, and the figure of merit of the real-time barrage includes barrage quantity ε and delivers
The number of users η of barrage.Concern segment barrage statistics and analytical unit are used to count the figure of merit of real-time barrage, obtain to it is corresponding when
Between section s video clip importance value θ, and according to importance value θ determine user concern video content.
Determine user to the process of the method second embodiment of multimedia content degree of concern in the embodiment of the present invention
Schematic diagram is as indicated at 3.
The play time of target video is divided into multiple period s, and the phase that each period s is occurred by step 31
It is grouped to real-time barrage is postponed;
Since in actual operation, video viewers often watch really and just carry out delivering for barrage after some picture
(i.e. picture has been broadcast) needs to occupy text input time to the evaluation barrage of the picture, generally the real-time barrage of meeting respective picture
Have certain delay, it is therefore desirable to be adjusted to the initial time of delivering of real-time barrage.Specifically, the real-time bullet of relative delay
The method of adjustment of curtain are as follows: the initial time of certain time period s is t1, the termination time is t2;It is divided into the period other reality of s group
When barrage group deliver time initial time be t1+ 1 second~t1+ 5 seconds, the termination time was t2+ 1 second~t2+ 5 seconds.
For example, the initial time of period s is 00:30, the termination time is 02:00, then the real-time bullet of period s group
The initial time of delivering of curtain group is 00:31~00:35, delivers and terminates the time as 02:01~02:05.Postpone 1 shown in the present invention
~5s is only preferred embodiment, and specific delay time can input font to delivering operation according to multiple users in actual operation
Between judged after time-consuming length mean value.
Step 32, corresponding each period s record are grouped the figure of merit and content of real-time barrage;
Step 33 is filtered the evaluation content of record;
The automatic identification that same barrage user repeats barrage content is carried out to the real-time barrage information of acquisition, is identified as repeating
When barrage content, barrage quantity is only denoted as 1.Specific automatic identifying method: same user delivers multiple in certain period s
Barrage is compared, and compares text overlays rate and reaches 80% or more, is considered as duplicate barrage content.
For example, in two barrage contents that same user delivers not " where obtain scape? it is super to praise!!!" " where take
Obtain scape? it praises very much!!!", the text overlays rate of two barrage contents reaches 80% or more, its barrage quantity is only denoted as 1, and
It is not 2.
The figure of merit of filtered effectively real-time barrage is carried out weight analysis by step 34, obtains corresponding period s's
The importance value θ of video clip;
Wherein, the figure of merit of the real-time barrage includes the barrage quantity ε and number of users η for delivering barrage;When to correspondence
Between section s video clip importance value θ=ε ω1+ηω2, the ω1The weight system for being barrage quantity in evaluation system
Number, the ω2To deliver weight coefficient of the number of users of barrage in evaluation system.Its specific weight coefficient is in practical application
In set as the case may be, the present invention is not specifically limited, preferably delivers the weight coefficient ω of the number of users of barrage2Greatly
In the weight coefficient ω of barrage quantity1。
Step 35, the size according to the importance value θ of above-mentioned video clip, and then determine in the video of user's concern
Hold.
Fig. 3 also shows determination user of the invention and refers to another evaluation in multimedia content degree of concern method
Target determines method.On the basis of method second embodiment, the real-time barrage of grouping of each period s is recorded in step 32
Also record has an evaluation content while evaluating quantity, and evaluation content is except in addition to filtering information, can also by following methods into
The determination of attitude is disliked in the degree of concern of row segment video and happiness.This method is according to shared by different evaluation content direction after step 32
Specific gravity, focus particularly on content in the video clip to determine corresponding period s and to the evaluation of attentinal contents, it is specific as follows.
The evaluation content for the real-time barrage that step 43, each period s are recorded is pre-processed;
Wherein, above-mentioned preprocess method includes:
(1) barrage content is cleaned, removes noise data;
Specifically, in barrage information there may be it is some can not react viewing user and like to dislike attitude or system think useless
Noise data, such as number, network address and some spcial characters, these data to system text analyzing there is no what use,
Therefore it removes.
(2) the barrage Chinese text after cleaning is segmented, and by participle everyday words or stop words delete;
, can be with open source Chinese word segmentation tool when being segmented to the Chinese text after cleaning, for example it is based on java language
Say lightweight Chinese word segmentation kit IKAnalazer, Paoding etc. of exploitation;Existing some everyday words after participle and stop
Word, as " " "Yes" " however ", it needs to be deleted.
(3) number that each participle occurs is counted, while attribute point is carried out to wherein commendatory term, neutral words and derogatory term
Class, and store.
By treated it is each participle occur number counted while, by it is each participle according to Chinese meaning of a word number
Carry out automatic identification according to the classification in library, be divided into three generic attributes according to the ownership of its commendation, derogatory sense or neutrality, and by its
It stores into barrage content data base.
It is counted after step 44, processing according to evaluation content direction, counts specific gravity size shared by different evaluation content;
The statistics in evaluation content direction is carried out in conjunction with participle attribute and number;Specifically, the participle of commendation attribute is divided into
Direction is liked to video clip, the participle of derogatory sense attribute is divided into, direction is detested to video clip, the participle of neutral attribute is drawn
For the direction noninductive to video clip.
Step 45 determines that the video of corresponding period s focuses particularly on content and to attentinal contents according to the specific gravity size
Evaluation.
After statistics, the participle proportion in three directions is compared, using heavy direction as the concern video
The evaluation attitude of segment contents.On the other hand, also viewing user can be determined to the view according to the most participle of statistics frequency of occurrence
The content especially paid close attention in frequency segment, as to weigh up existing number most for video clip someone name, it is known that the personage is that viewing is used
The high object of family concern rate.
Fig. 3 also shows determination user of the invention to multimedia content degree of concern method to the excellent of definitive result
Change.Meticulous due to that may divide group when dividing group, the period is smaller, and the group of entire video excessively causes to evaluate
As a result excessively disperse, not enough intuitively.It further include following steps after step 35 on the basis of the second embodiment of the method for the present invention
Suddenly.
Step 36-1, according to the difference between the importance value θ of each time adjacent segments s, and sentenced according to size of the difference
It is disconnected whether to meet merging condition;If reaching merging condition, merge.
Specifically, as period snBefore or after period smImportance value θmIn period snImportance
Numerical value θnExpanded range value in, then establish new period sa;The period sa=sn+sm, period saImportance number
Value θaFor importance value θnWith importance value θmMean value.
For example, period snImportance value θnIt is 14.08, expanded range value θn± 2, i.e. expanded range value is
12.08-16.08.As period snPeriod s beforemImportance value θmWhen being 13.02, determine that it belongs to period sn's
Importance value θnExpanded range value in, how to merge condition, i.e., merge two periods, the period s after merginga's
Initial time is in preceding period smInitial time, terminate the time be in rear period snThe termination time.And importance number
Value θa=13.55.
As period snPeriod s beforem+1Importance value θm+1Period s laterm+2Importance value
θm+2In period snImportance value θnExpanded range value in, then establish new period sa;The period sa=sn
+sm+1+sm+2, period saImportance value be θn、θm+1And θm+2Mean value.
It further include following step after step 35 in another embodiment.
Step 36-2, as period snImportance value θnWith time adjacent segments smImportance value θmBetween difference
Value is greater than scheduled sharp prominent value range, then the biggish period video content of importance value is labeled as swashing prominent attentinal contents.
For example, setting system swashs prominent value range as 6.Period snImportance value θnIt is 14.08, time adjacent segments sm
Importance value θmIt is 4.15, difference 9.93 between the two is greater than scheduled sharp prominent value range, i.e., by period snSegment
Content-label is sharp prominent attentinal contents, and can be to the concern direction for swashing prominent its content of attentinal contents independent studies.
Fig. 4 also shows a kind of determining user of the present invention to the system of multimedia content degree of concern, the system comprises
Play segment and barrage grouped element, concern segment barrage recording unit, concern segment barrage statistics and analytical unit, concern piece
Section barrage filter element, period comparing unit and barrage resource content evaluation unit.
Wherein, it plays segment and barrage grouped element is used to the play time of target video being divided into multiple period s,
And each period s real-time barrage occurred is grouped;In specific group technology, the broadcasting segment and barrage grouping
Unit is also used to certain period s initial time t1Postpone real-time barrage of 1~5 second time point as period s backward
Certain period s is terminated time t by the initial time delivered2Postpone 1~5 second time point backward as the real-time of period s
The termination time that barrage is delivered.
Concern segment barrage recording unit is used to correspond to each period s record and is grouped the figure of merit of real-time barrage and interior
Hold, the figure of merit of the real-time barrage includes the barrage quantity ε and number of users η for delivering barrage.
Concern segment barrage statistics and analytical unit are used to count the figure of merit of real-time barrage, obtain corresponding period s
Video clip importance value θ, and according to importance value θ determine user concern video content.
Segment barrage filter element is paid close attention to be used to carry out same barrage user to the real-time barrage information of acquisition to repeat barrage
The automatic identification of content, when being identified as repeating barrage content, barrage quantity is only denoted as 1;
Period comparing unit is used for according to the difference between the importance value θ of each time adjacent segments s, and according to difference
Value size judges whether to meet merging condition, if reaching merging condition, directly merges.
The system also includes barrage resource content evaluation unit, the evaluations of the real-time barrage for recording each period s
Content is pre-processed, and is counted after processing according to evaluation content direction, and specific gravity size shared by different evaluation content is counted,
And determine that the video of corresponding period s focuses particularly on content and to the evaluation of attentinal contents according to the specific gravity size.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvements and modifications can also be made, these improvements and modifications
Also it should be regarded as protection scope of the present invention.
Claims (10)
1. determining user to the method for multimedia content degree of concern, which is characterized in that the method is used for barrage video
The determination of broadcasting content, includes at least:
The play time of target video is divided into multiple period s, and each period s real-time barrage occurred is divided
Group;
Corresponding each period s record is grouped the figure of merit and content of real-time barrage, and according to the figure of merit of real-time barrage
Weight analysis is carried out, the importance value θ of the video clip of corresponding period s is obtained;
According to the importance value θ of the video clip, the video content of user's concern is determined;
The figure of merit of the real-time barrage includes the barrage quantity ε and number of users η for delivering barrage;The view of corresponding period s
Importance value θ=ε ω of frequency segment1+ηω2, the ω1For weight coefficient of the barrage quantity in evaluation system, the ω2
To deliver weight coefficient of the number of users of barrage in evaluation system.
2. determining user to the method for multimedia content degree of concern as described in claim 1, which is characterized in that record
After the figure of merit and content of the real-time barrage of corresponding each period s, evaluation content is filtered: to the real-time bullet of acquisition
Curtain information carries out the automatic identification that same barrage user repeats barrage content, and when being identified as repeating barrage content, barrage quantity is only
It is denoted as 1.
3. determining user to the method for multimedia content degree of concern as described in claim 1, which is characterized in that described
Barrage content is also used to: the evaluation content of the real-time barrage of each period s record being pre-processed, according to evaluation after processing
Content direction is counted, and counts specific gravity size shared by different evaluation content, and determine the corresponding time according to the specific gravity size
Section s's focuses particularly on content and the evaluation to attentinal contents.
4. determining user to the method for multimedia content degree of concern as claimed in claim 3, which is characterized in that described
Preprocess method includes:
Barrage content is cleaned, noise data is removed;
Barrage Chinese text after cleaning is segmented, and by participle everyday words or stop words delete;
The number that each participle occurs is counted, while attributive classification is carried out to wherein commendatory term, neutral words and derogatory term, and deposit
Storage.
5. determining user to the method for multimedia content degree of concern as described in claim 1, which is characterized in that described
By each period s occur real-time barrage be grouped in real-time barrage be relative delay real-time barrage:
The real-time barrage of the relative delay specifically: the initial time of certain time period s is t1, the termination time is t2;It is divided into
The time initial time of delivering of the other real-time barrage group of period s group is t1+ 1 second~t1+ 5 seconds, the termination time was t2+ 1 second~
t2+ 5 seconds.
6. determining user to the method for multimedia content degree of concern as described in claim 1, which is characterized in that obtain
After importance value θ, the method also includes: as period snBefore or after period smImportance value θmWhen
Between section snImportance value θnExpanded range value in, then establish new period sa;The period sa=sn+sm, the time
Section saImportance value θaFor importance value θnWith importance value θmMean value;
Alternatively, as period snPeriod s beforem+1Importance value θm+1Period s laterm+2Importance value
θm+2In period snImportance value θnExpanded range value in, then establish new period sa;The period sa=sn
+sm+1+sm+2, period saImportance value be θn、θm+1And θm+2Mean value.
7. determining user to the method for multimedia content degree of concern as described in claim 1, which is characterized in that obtain
After importance value θ, the method also includes: as period snImportance value θnWith time adjacent segments smImportance number
Value θmBetween difference be greater than it is scheduled swash prominent value range, then the biggish video content of importance value is labeled as swashing in tip out note
Hold.
8. a kind of determining user is to the system of multimedia content degree of concern, which is characterized in that the system includes at least
Segment and barrage grouped element are played, for the play time of target video to be divided into multiple period s, and will be each
The real-time barrage that period s occurs is grouped;
Segment barrage recording unit is paid close attention to, the figure of merit and content for being grouped real-time barrage for corresponding to each period s record,
The figure of merit of the real-time barrage includes the barrage quantity ε and number of users η for delivering barrage;
Segment barrage statistics and analytical unit are paid close attention to, for counting the figure of merit of real-time barrage, obtains the view of corresponding period s
The importance value θ of frequency segment, and the video content that user pays close attention to is determined according to importance value θ.
9. system as claimed in claim 8, which is characterized in that the broadcasting segment and barrage grouped element were also used to some time
Between section s initial time t1The initial time that the time point of delay 1~5 second delivers as the real-time barrage of period s backward, will
Certain period s terminates time t2When the termination that the time point of delay 1~5 second delivers as the real-time barrage of period s backward
Between;
The system also includes:
Segment barrage filter element is paid close attention to, repeats barrage content for carrying out same barrage user to the real-time barrage information of acquisition
Automatic identification, be identified as repeat barrage content when, barrage quantity is only denoted as 1;
Period comparing unit, for the difference between the importance value θ according to each time adjacent segments s, and according to difference
Size judges whether to meet merging condition, if reaching merging condition, directly merges.
10. system as claimed in claim 8, which is characterized in that the system also includes barrage resource content evaluation unit, being used for will
The evaluation content of the real-time barrage of each period s record is pre-processed, and is counted after processing according to evaluation content direction,
Specific gravity size shared by different evaluation content is counted, and determines that the video of corresponding period s focuses particularly on according to the specific gravity size
Content and evaluation to attentinal contents.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710311715.2A CN107197368B (en) | 2017-05-05 | 2017-05-05 | Determine user to the method and system of multimedia content degree of concern |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710311715.2A CN107197368B (en) | 2017-05-05 | 2017-05-05 | Determine user to the method and system of multimedia content degree of concern |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107197368A CN107197368A (en) | 2017-09-22 |
CN107197368B true CN107197368B (en) | 2019-10-18 |
Family
ID=59873119
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710311715.2A Active CN107197368B (en) | 2017-05-05 | 2017-05-05 | Determine user to the method and system of multimedia content degree of concern |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107197368B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107948206B (en) * | 2018-01-02 | 2020-11-20 | 联想(北京)有限公司 | Method and system for downloading and/or uploading multimedia data |
CN108307230B (en) * | 2018-02-07 | 2021-01-22 | 北京奇艺世纪科技有限公司 | Method and device for extracting video highlight |
CN108694236B (en) * | 2018-05-11 | 2021-02-02 | 阿里巴巴(中国)有限公司 | Video data processing method and device and electronic equipment |
CN109308487B (en) * | 2018-08-06 | 2021-03-30 | 同济大学 | Advertisement putting method based on bullet screen data analysis |
CN109275047B (en) * | 2018-09-13 | 2021-06-29 | 周昕 | Video information processing method and device, electronic equipment and storage medium |
CN111526374B (en) * | 2019-02-01 | 2022-05-10 | 广州虎牙信息科技有限公司 | Live broadcast-based bullet screen processing method, stream pulling method and device |
CN110267111A (en) * | 2019-05-24 | 2019-09-20 | 平安科技(深圳)有限公司 | Video barrage analysis method, device and storage medium, computer equipment |
CN110427897B (en) * | 2019-08-07 | 2022-03-08 | 北京奇艺世纪科技有限公司 | Video precision analysis method and device and server |
CN110740374B (en) * | 2019-10-31 | 2022-03-11 | 广州市网星信息技术有限公司 | Multimedia data processing method and device, computer equipment and storage medium |
CN111163357A (en) * | 2020-01-06 | 2020-05-15 | 上海众言网络科技有限公司 | Method and device for evaluating video content |
CN112752133B (en) * | 2020-03-20 | 2024-05-10 | 深圳市雅阅科技有限公司 | Video playing method and device, electronic equipment and storage medium |
CN113055741B (en) * | 2020-12-31 | 2023-05-30 | 科大讯飞股份有限公司 | Video abstract generation method, electronic equipment and computer readable storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739416A (en) * | 2008-11-04 | 2010-06-16 | 未序网络科技(上海)有限公司 | Method for sequencing multi-index comprehensive weight video |
WO2013097245A1 (en) * | 2011-12-31 | 2013-07-04 | 华为技术有限公司 | Method and device for determining focus content of user |
CN105095508A (en) * | 2015-08-31 | 2015-11-25 | 北京奇艺世纪科技有限公司 | Multimedia content recommendation method and multimedia content recommendation apparatus |
CN105847993A (en) * | 2016-04-19 | 2016-08-10 | 乐视控股(北京)有限公司 | Method and device for sharing video clip |
CN106060672A (en) * | 2016-06-06 | 2016-10-26 | 乐视控股(北京)有限公司 | Method and device for processing video information |
CN106251172A (en) * | 2016-07-20 | 2016-12-21 | 武汉斗鱼网络科技有限公司 | A kind of user based on Information Entropy is worth score calculation method and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9282138B2 (en) * | 2013-03-15 | 2016-03-08 | Facebook, Inc. | Enabling photoset recommendations |
-
2017
- 2017-05-05 CN CN201710311715.2A patent/CN107197368B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739416A (en) * | 2008-11-04 | 2010-06-16 | 未序网络科技(上海)有限公司 | Method for sequencing multi-index comprehensive weight video |
WO2013097245A1 (en) * | 2011-12-31 | 2013-07-04 | 华为技术有限公司 | Method and device for determining focus content of user |
CN105095508A (en) * | 2015-08-31 | 2015-11-25 | 北京奇艺世纪科技有限公司 | Multimedia content recommendation method and multimedia content recommendation apparatus |
CN105847993A (en) * | 2016-04-19 | 2016-08-10 | 乐视控股(北京)有限公司 | Method and device for sharing video clip |
CN106060672A (en) * | 2016-06-06 | 2016-10-26 | 乐视控股(北京)有限公司 | Method and device for processing video information |
CN106251172A (en) * | 2016-07-20 | 2016-12-21 | 武汉斗鱼网络科技有限公司 | A kind of user based on Information Entropy is worth score calculation method and system |
Also Published As
Publication number | Publication date |
---|---|
CN107197368A (en) | 2017-09-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107197368B (en) | Determine user to the method and system of multimedia content degree of concern | |
CN109189951B (en) | Multimedia resource recommendation method, equipment and storage medium | |
US9736503B1 (en) | Optimizing timing of display of a mid-roll video advertisement based on viewer retention data | |
CN105142028B (en) | The content of TV program search of triple play oriented is with recommending method | |
JP6054448B2 (en) | Targeted video advertising | |
Cha et al. | Analyzing the video popularity characteristics of large-scale user generated content systems | |
US8995823B2 (en) | Method and system for content relevance score determination | |
CN105183897B (en) | A kind of method and system of video search sequence | |
CN103686237B (en) | Recommend the method and system of video resource | |
CN108259939B (en) | New video push control method and device and server | |
US20170034577A1 (en) | Assessing digital content across a communications network | |
US20080189733A1 (en) | Content rating systems and methods | |
CN103747343B (en) | The method and apparatus that resource is recommended at times | |
CN106331779A (en) | Method and system for pushing anchor based on user preferences during video playing process | |
JP2010066837A (en) | Information processing apparatus and method, program, and recording medium | |
CN104219575A (en) | Related video recommending method and system | |
JP2005033600A (en) | Content viewing support system and content viewing support method, and computer program | |
CN103533393A (en) | Family analyzing and program recommending method based on family watching records | |
US8712831B2 (en) | Method and system for quantifying viewer awareness of advertising images in a video source | |
CN101833552A (en) | Method for marking and recommending streaming media | |
Aggrawal et al. | View-count based modeling for YouTube videos and weighted criteria–based ranking | |
CN104216883A (en) | Video recommendation reason generating system and method | |
CN107018408A (en) | The Quality of experience appraisal procedure of mobile terminal HTTP video flowings | |
CN103442270B (en) | A kind of method and device for the viewing-data for gathering user | |
CN103002329B (en) | Device and method for predicting reach-frequency table data of network video advertisements |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |