CN107197368A - Determine method and system of the user to multimedia content degree of concern - Google Patents
Determine method and system of the user to multimedia content degree of concern Download PDFInfo
- Publication number
- CN107197368A CN107197368A CN201710311715.2A CN201710311715A CN107197368A CN 107197368 A CN107197368 A CN 107197368A CN 201710311715 A CN201710311715 A CN 201710311715A CN 107197368 A CN107197368 A CN 107197368A
- Authority
- CN
- China
- Prior art keywords
- barrage
- period
- time
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000011156 evaluation Methods 0.000 claims description 37
- 239000012634 fragment Substances 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 6
- 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
- 238000001914 filtration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 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 determination user to the method for multimedia content degree of concern, for the determination of barrage video-frequency playing content, it at least includes：The reproduction time of target video is divided into multiple period s, and each period s real-time barrages occurred are grouped；The figure of merit of the real-time barrage of correspondence each period s record packet, and weight analysis is carried out according to the figure of merit of real-time barrage, obtain the importance value θ of the video segment of correspondence period s；According to the importance value θ of the video segment, the video content of user's concern is determined.This method has the advantages that accuracy is high, real-time.
Description
Technical field
The present invention relates to video processing technique, more particularly to a kind of determination user is to multimedia content degree of concern
Method and system, the degree of concern for barrage video content is determined.
Background technology
Video content has become the pith of internet traffic, and the history that video content is watched by analyzing user is remembered
Record, obtains the hobby of user, can improve Consumer's Experience, and targetedly provides in media content or advertisement, raising perhaps
The interests of advertising provider.It is existing typically to obtain preference of the user to video content by data such as video click rate, flows, this
Analysis is planted to the preference for whole video content, the analysis for the importance of video interior segments also lacks automated analysis
Method.
For the technical problem, patent CN103503467B discloses a kind of method for determining user's attentinal contents and set
It is standby, by recording operating point and corresponding time point of the user when watching video, determined according to operating point corresponding time point
The starting point and end point of video segment, and the operating point carried out according to the determination video segment determines the video segment
Importance value, so that it is determined that user concern video content；Specific operating point is broadcastings, pause, F.F., rewind, slowly
Enter, move back, scale slowly.This method realizes the significance level of the mark video segment content of automation, but user is when being operated
Operating point be intended to not single, except using slow-motion, rewind to video preference, preference is not using F.F. etc., it is also possible to exist
Viewing midway is left, other people are situations such as add viewing, and operating point is not being judged in the range of importance value caused by this kind of situation,
It influences the accuracy rate of video segment importance value.
On the other hand, existing barrage watches the exchange evaluation meanses of user as conventional Internet video, with 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 beholder real-time network is regarded
The fancy grade of frequency fragment is extremely effectively and accurate to the judgment criteria of Internet video content attention rate as user.
The content of the invention
It is an object of the invention to overcome defect of the prior art, design is a kind of to determine 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, is determined from information is judged
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 is high, real-time.
To achieve the above object, the technical solution adopted in the present invention is that a kind of determination user is closed to multimedia content
The method of note degree, methods described is used for the determination of barrage video-frequency playing content, and it at least includes：
The reproduction time of target video is divided into multiple period s, and each period s real-time barrages occurred are entered
Row packet；
The figure of merit of the real-time barrage of correspondence each period s record packet, and entered according to the figure of merit of real-time barrage
Row weight analysis, obtains the importance value θ of the video segment of correspondence period s；
According to the importance value θ of the video segment, the video content of user's concern is determined；
The figure of merit of the real-time barrage includes barrage quantity ε and delivers the number of users η of barrage；Correspondence period s
Video segment 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.
Present invention also offers a kind of system for determining user to content of multimedia degree of concern, the system is at least wrapped
Include：
Fragment and barrage grouped element are played, for the reproduction time of target video to be divided into multiple period s, and will
The real-time barrage that each period s occurs is grouped；
Fragment barrage recording unit is paid close attention to, for the figure of merit of the real-time barrage of correspondence each period s record packets, institute
Stating the figure of merit of real-time barrage includes barrage quantity ε and delivers the number of users η of barrage；
Fragment barrage statistics and analytic unit are paid close attention to, the figure of merit for counting real-time barrage obtains correspondence period s
Video segment importance value θ, and according to importance value θ determine user pay close attention to video content.
From upper technical scheme, the present invention judges user to this by the statistical analysis to target video barrage information
The degree of concern of video segment, carries out automation mark, and obtain the importance number of video segment by directly perceived, accurate barrage information
Value, is that can determine that the video content that user pays close attention to according to importance value；This method is novel, accuracy is high and real-time, obtains
The concern information gone out is more diversified.
Brief description of the drawings
Fig. 1 is present invention determine that user is to the schematic flow sheet of the embodiment of content of multimedia degree of concern method one；
Fig. 2 is present invention determine that user is to the structural representation of the embodiment of content of multimedia degree of concern system one；
Fig. 3 is present invention determine that user is to the schematic flow sheet of content of multimedia degree of concern method second embodiment；
Fig. 4 is present invention determine that user is to the structural representation of content of multimedia degree of concern system second embodiment.
Embodiment
With reference to the accompanying drawings and examples, the embodiment to the present invention is further described.Following examples are only
For clearly illustrating technical scheme, and it can not be limited the scope of the invention with this.
Fig. 1 is present invention determine that user illustrates to the flow of the embodiment of method one of multimedia content degree of concern
Figure, this method includes：
Step 11：The reproduction 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：The figure of merit and content of the real-time barrage of correspondence each period s record packet, and according to real-time barrage
Figure of merit carry out weight analysis, obtain correspondence period s video segment importance value θ；
Wherein, the figure of merit of the real-time barrage includes barrage quantity ε and delivers the number of users η of barrage；When to correspondence
Between section s video segment 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 segment, the video content of user's concern is determined.
The video content segments that multiple users pay close attention to can directly be determined by the above method；First determined relative to documents
Unique user is counted to the video content that multiple users pay close attention to again, and the method for determining the importance number of video content is more high
Imitate, 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 fragment and barrage grouped element, concern fragment barrage recording unit and concern fragment barrage statistics and analyze
Unit.
Wherein, playing fragment and barrage grouped element is used to the reproduction time of target video being divided into multiple period s,
And be grouped each period s real-time barrages occurred.Paying close attention to fragment barrage recording unit is used for correspondence each period s
The figure of merit and content of the real-time barrage of record packet, the figure of merit of the real-time barrage include barrage quantity ε and delivered
The number of users η of barrage.Concern fragment barrage statistics and analytic unit are used for the figure of merit for counting real-time barrage, when obtaining to correspondence
Between section s video segment importance value θ, and according to importance value θ determine user pay close attention to video content.
Flow of the user to the method second embodiment of multimedia content degree of concern is determined in the embodiment of the present invention
Schematic diagram is as indicated at 3.
Step 31, the reproduction time of target video is divided into multiple period s, and the phase that each period s is occurred
It is grouped to postponing real-time barrage；
Because in practical operation, video viewers often watch and delivering for barrage are just carried out after some picture really
(i.e. picture has been broadcast), needs to occupy word input time to the evaluation barrage of the picture, typically the real-time barrage of meeting respective picture
Have certain delay, it is therefore desirable to which the initial time of delivering to real-time barrage is adjusted.Specifically, the real-time bullet of relative delay
Curtain method of adjustment be：Certain time period s initial time is t1, the termination time is t2；It is divided into the reality of period s groups
When barrage group deliver time initial time for t1+ 1 second~t1+ 5 seconds, the termination time was t2+ 1 second~t2+ 5 seconds.
For example, period s initial time is 00:30, the time that terminates is 02:00, then the real-time bullet of period s groups
The initial time of delivering of curtain group is 00:31~00:35, it is 02 to deliver the termination time:01~02:05.Delay 1 shown in the present invention
~5s is only preferred scheme, and specific time delay can input font to delivering operation in practical operation according to multiple users
Between take length average after judged.
Step 32, the figure of merit and content for corresponding to the real-time barrage of each period s record packets；
Step 33, the evaluation content to record are filtered；
Real-time barrage information to acquisition carries out the automatic identification that same barrage user repeats barrage content, is identified as repeating
During barrage content, barrage quantity is only designated as 1.Specific automatic identifying method：It is multiple that same user delivers in certain period s
Barrage is compared, and compares text overlays rate and reaches more than 80%, is considered as the barrage content of repetition.
For example, where in two barrage contents that same user delivers " scape Wei not be obtainedIt is super to praise！！！" " where take
Obtain scapePraise very much！！！", the text overlays rate of two barrage contents reaches more than 80%, and its barrage quantity is only designated as into 1, and
It is not 2.
Step 34, the figure of merit progress weight analysis by effective real-time barrage after filtering, obtain correspondence period s
The importance value θ of video segment；
Wherein, the figure of merit of the real-time barrage includes barrage quantity ε and delivers the number of users η of barrage；When to correspondence
Between section s video segment 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, and 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 segment, and then determine in the video of user's concern
Hold.
The determination user that Fig. 3 also show the present invention refers to another evaluation in multimedia content degree of concern method
Target determines method.Each period s real-time barrage of packet is recorded on the basis of method second embodiment, in step 32
Evaluation content has also been recorded while evaluating quantity, and evaluation content can also be entered in addition to for filtering information by following methods
The determination of attitude is disliked in the degree of concern of row fragment video and happiness.This method is according to shared by different evaluation content direction after step 32
Proportion, with determine correspondence period s video segment in focus particularly on content and the evaluation to attentinal contents, it is specific as follows.
Step 43, the evaluation content of the real-time barrage of each period s records are pre-processed；
Wherein, above-mentioned preprocess method includes：
(1) barrage content is cleaned, removes noise data；
Specifically, there may be in barrage information, some can not react viewing user's happiness evil attitude or system thinks useless
Noise data, such as numeral, network address and some spcial characters, these data do not have any use to system text analyzing,
Therefore remove.
(2) participle is carried out to the barrage Chinese text after cleaning, and the everyday words in participle or stop words are deleted；
, can be with Chinese word segmentation instrument of increasing income, such as based on java languages when the Chinese text after to cleaning carries out participle
Say lightweight Chinese word segmentation kit IKAnalazer, Paoding of exploitation etc.；Some everyday words of presence after participle and stop
Word, if " " "Yes" " but " etc. is, it is necessary to be deleted.
(3) number of times of each participle appearance is counted, while carrying out attribute point to wherein commendatory term, neutral words and derogatory term
Class, and store.
While the number of times occurred in each participle after by processing is counted, by each participle according to Chinese meaning of a word number
Carry out automatic identification according to the classification in storehouse, carried out being divided into three generic attributes according to the ownership of its commendation, derogatory sense or neutrality, and by its
Store into barrage content data base.
Counted after step 44, processing according to evaluation content direction, the proportion size shared by statistics different evaluation content；
The statistics in evaluation content direction is carried out with reference to participle attribute and number of times；Specifically, the participle of commendation attribute is divided into
Direction is liked to video segment, the participle of derogatory sense attribute is divided into direction is detested to video segment, the participle of neutral attribute is drawn
For to the noninductive direction of video segment.
Step 45, according to the proportion size determine correspondence period s video focus particularly on content and to attentinal contents
Evaluate.
After statistics, the participle proportion in three directions is compared, the concern video is used as using heavy direction
The evaluation attitude of segment contents.On the other hand, also it can determine that viewing user regards to this according to the most participle of statistics occurrence number
It is most that someone name of the content particularly paid close attention in frequency fragment, such as video segment weighs up existing number of times, it is known that the personage uses for viewing
The high object of family concern rate.
The determination user that Fig. 3 also show the present invention determines the excellent of result to multimedia content degree of concern method pair
Change.Meticulous due to may divide group when dividing group, the period is smaller, and the group of whole video excessively causes to evaluate
As a result excessively disperse, not enough intuitively.On the basis of the second embodiment of the inventive method, following steps are also included after step 35
Suddenly.
Step 36-1, according to the difference between each time adjacent segments s importance value θ, 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 set up new period sa；The period sa=sn+sm, period saImportance number
Value θaFor importance value θnWith importance value θmAverage.
For example, period snImportance value θnFor 14.08, its expanded range value θn± 2, i.e. expanded range value is
12.08-16.08.As period snPeriod s beforemImportance value θmFor 13.02 when, judge that it belongs to period sn's
Importance value θnExpanded range value in, how to merge condition, will merge two periods, the period s after merginga's
Initial time is in preceding period smInitial time, its terminate 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 afterwardsm+2Importance value
θm+2In period snImportance value θnExpanded range value in, then set up new period sa；The period sa=sn
+sm+1+sm+2, period saImportance value be θn、θm+1And θm+2Average.
In another embodiment, also comprise the steps after step 35.
Step 36-2, as period snImportance value θnWith time adjacent segments smImportance value θmBetween difference
Value is more than predetermined sharp prominent value range, then the larger period video content of importance value is labeled as swashing prominent attentinal contents.
For example, it is 6 that initialization system, which swashs prominent value range,.Period snImportance value θnFor 14.08, time adjacent segments sm
Importance value θmFor 4.15, difference 9.93 between the two be more than it is predetermined swash prominent value range, will period snFragment
Content-label, and can be to swashing the concern direction of its content of prominent attentinal contents independent studies to swash prominent attentinal contents.
Fig. 4 also show a kind of system for determining user to content of multimedia degree of concern of the present invention, and the system includes
Play fragment and barrage grouped element, concern fragment barrage recording unit, concern fragment barrage statistics and analytic unit, concern piece
Section barrage filter element, period comparing unit and barrage resource content evaluation unit.
Wherein, playing fragment and barrage grouped element is used to the reproduction time of target video being divided into multiple period s,
And be grouped each period s real-time barrages occurred；In specific group technology, the broadcasting fragment and barrage packet
Unit is additionally operable to certain period s initial times t1Backward postpone 1~5 second time point as period s real-time barrage
The initial time delivered, time t is terminated by certain period s2The time point for postponing 1~5 second backward is used as the real-time of period s
The termination time that barrage is delivered.
Paying close attention to fragment barrage recording unit is used for the figure of merit of the real-time barrage of correspondence each period s record packet and interior
Hold, the figure of merit of the real-time barrage includes barrage quantity ε and delivers the number of users η of barrage.
Concern fragment barrage statistics and analytic unit are used for the figure of merit for counting real-time barrage, obtain correspondence period s
Video segment importance value θ, and according to importance value θ determine user pay close attention to video content.
Paying close attention to fragment barrage filter element is used to carry out the real-time barrage information of acquisition same barrage user repetition barrage
The automatic identification of content, when being identified as repeating barrage content, barrage quantity is only designated as 1；
The difference that period comparing unit is used between the importance value θ according to 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, for by the evaluation of each period s real-time barrages recorded
Content is pre-processed, and is counted after processing according to evaluation content direction, the proportion size shared by statistics different evaluation content,
And determine that the video of correspondence period s focuses particularly on content and the evaluation to attentinal contents according to the proportion size.
Described above is only the 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, some 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. determine method of the user to multimedia content degree of concern, it is characterised in that methods described is used for barrage video
The determination of content is played, it at least includes：
The reproduction time of target video is divided into multiple period s, and each period s real-time barrages occurred are divided
Group；
The figure of merit and content of the real-time barrage of correspondence each period s record packet, and according to the figure of merit of real-time barrage
Weight analysis is carried out, the importance value θ of the video segment of correspondence period s is obtained；
According to the importance value θ of the video segment, the video content of user's concern is determined；
The figure of merit of the real-time barrage includes barrage quantity ε and delivers the number of users η of barrage；Correspond to regarding for period s
Importance value θ=ε ω of frequency fragment1+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. method of the user to content of multimedia degree of concern is determined as claimed in claim 1, it is characterised in that record correspondence
After the figure of merit and content of each period s real-time barrage, evaluation content is filtered：To the real-time barrage letter of acquisition
Breath carries out the automatic identification that same barrage user repeats barrage content, and when being identified as repeating barrage content, barrage quantity is only designated as
1。
3. method of the user to content of multimedia degree of concern is determined as claimed in claim 1, it is characterised in that the barrage
Content is additionally operable to：The evaluation content of each period s real-time barrages recorded is pre-processed, according to evaluation content after processing
Direction is counted, the proportion size shared by statistics different evaluation content, and determines correspondence period s according to the proportion size
Focus particularly on content and the evaluation to attentinal contents.
4. method of the user to content of multimedia degree of concern is determined as claimed in claim 3, it is characterised in that the pre- place
Reason method includes：
Barrage content is cleaned, noise data is removed；
Participle is carried out to the barrage Chinese text after cleaning, and the everyday words in participle or stop words are deleted；
The number of times of each participle appearance is counted, while carrying out attributive classification to wherein commendatory term, neutral words and derogatory term, and is deposited
Storage.
5. method of the user to content of multimedia degree of concern is determined as claimed in claim 1, it is characterised in that described by respectively
The real-time barrage that individual period s occurs be grouped in real-time barrage for relative delay real-time barrage：
The real-time barrage of the relative delay is specially：Certain time period s initial time is t1, the termination time is t2；It is divided into
The time initial time of delivering of the real-time barrage group of period s groups is t1+ 1 second~t1+ 5 seconds, the termination time was t2+ 1 second~
t2+ 5 seconds.
6. method of the user to content of multimedia degree of concern is determined as claimed in claim 1, it is characterised in that obtained important
After property numerical value θ, methods described also includes：As period snBefore or after period smImportance value θmIn the period
snImportance value θnExpanded range value in, then set up new period sa；The period sa=sn+sm, period sa
Importance value θaFor importance value θnWith importance value θmAverage；
Or, as period snPeriod s beforem+1Importance value θm+1Period s afterwardsm+2Importance value
θm+2In period snImportance value θnExpanded range value in, then set up new period sa；The period sa=sn
+sm+1+sm+2, period saImportance value be θn、θm+1And θm+2Average.
7. method of the user to content of multimedia degree of concern is determined as claimed in claim 1, it is characterised in that obtained important
After property numerical value θ, methods described also includes：As period snImportance value θnWith time adjacent segments smImportance value θm
Between difference be more than it is predetermined swash prominent value range, then the larger video content of importance value is labeled as swashing prominent attentinal contents.
8. a kind of system for determining user to content of multimedia degree of concern, it is characterised in that the system at least includes
Play fragment and barrage grouped element, for the reproduction time of target video to be divided into multiple period s, and by each
The real-time barrage that period s occurs is grouped；
Fragment barrage recording unit is paid close attention to, for the figure of merit and content of the real-time barrage of correspondence each period s record packets,
The figure of merit of the real-time barrage includes barrage quantity ε and delivers the number of users η of barrage；
Fragment barrage statistics and analytic unit are paid close attention to, the figure of merit for counting real-time barrage obtains regarding for correspondence period s
The importance value θ of frequency fragment, and the video content that user pays close attention to is determined according to importance value θ.
9. system as claimed in claim 8, it is characterised in that the broadcasting fragment and barrage grouped element were additionally operable to some time
Between section s initial times t1The initial time that the time point of delay 1~5 second delivers as period s real-time barrage backward, will
Certain period s terminates time t2During the termination that the time point of delay 1~5 second delivers as period s real-time barrage backward
Between；
The system also includes：
Fragment barrage filter element is paid close attention to, carrying out same barrage user for the real-time barrage information to acquisition repeats barrage content
Automatic identification, be identified as repeat barrage content when, barrage quantity is only designated 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, it is characterised in that the system also includes barrage resource content evaluation unit, for inciting somebody to action
The evaluation content of the real-time barrage of each period s records is pre-processed, and is counted after processing according to evaluation content direction,
The proportion size shared by different evaluation content is counted, and determines that the video of correspondence period s is focused particularly on according to the proportion size
Content and the 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 true CN107197368A (en) | 2017-09-22 |
| CN107197368B 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) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107948206A (en) * | 2018-01-02 | 2018-04-20 | 联想(北京)有限公司 | A kind of multi-medium data download/or the method and system uploaded |
| CN108307230A (en) * | 2018-02-07 | 2018-07-20 | 北京奇艺世纪科技有限公司 | A kind of extracting method and device of video highlight segment |
| CN108694236A (en) * | 2018-05-11 | 2018-10-23 | 优视科技有限公司 | Video data handling procedure, device and electronic equipment |
| CN109275047A (en) * | 2018-09-13 | 2019-01-25 | 周昕 | Video information processing method and device, electronic equipment, storage medium |
| CN109308487A (en) * | 2018-08-06 | 2019-02-05 | 同济大学 | A kind of advertising mechanism based on the analysis of barrage data |
| 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 |
| CN110427897A (en) * | 2019-08-07 | 2019-11-08 | 北京奇艺世纪科技有限公司 | Analysis method, device and the server of video highlight degree |
| CN110740374A (en) * | 2019-10-31 | 2020-01-31 | 广州市网星信息技术有限公司 | multimedia data processing method, 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 |
| CN111526374A (en) * | 2019-02-01 | 2020-08-11 | 广州虎牙信息科技有限公司 | Live broadcast-based bullet screen processing method, stream pulling method and device |
| CN112752133A (en) * | 2020-03-20 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Video playing method and device, electronic equipment and storage medium |
| CN113055741A (en) * | 2020-12-31 | 2021-06-29 | 科大讯飞股份有限公司 | Video abstract generation method, electronic equipment and computer readable storage medium |
Citations (7)
| 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 |
| US20160164988A1 (en) * | 2013-03-15 | 2016-06-09 | Facebook, Inc. | Enabling photoset recommendations |
| 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 |
-
2017
- 2017-05-05 CN CN201710311715.2A patent/CN107197368B/en active Active
Patent Citations (7)
| 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 |
| US20160164988A1 (en) * | 2013-03-15 | 2016-06-09 | Facebook, Inc. | Enabling photoset recommendations |
| 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 |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107948206A (en) * | 2018-01-02 | 2018-04-20 | 联想(北京)有限公司 | A kind of multi-medium data download/or the method and system uploaded |
| CN108307230A (en) * | 2018-02-07 | 2018-07-20 | 北京奇艺世纪科技有限公司 | A kind of extracting method and device of video highlight segment |
| CN108694236A (en) * | 2018-05-11 | 2018-10-23 | 优视科技有限公司 | Video data handling procedure, 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 |
| CN109308487A (en) * | 2018-08-06 | 2019-02-05 | 同济大学 | A kind of advertising mechanism based on the analysis of barrage data |
| CN109275047B (en) * | 2018-09-13 | 2021-06-29 | 周昕 | Video information processing method and device, electronic equipment and storage medium |
| CN109275047A (en) * | 2018-09-13 | 2019-01-25 | 周昕 | Video information processing method and device, electronic equipment, storage medium |
| CN111526374A (en) * | 2019-02-01 | 2020-08-11 | 广州虎牙信息科技有限公司 | Live broadcast-based bullet screen processing method, stream pulling method and device |
| 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 |
| CN110427897A (en) * | 2019-08-07 | 2019-11-08 | 北京奇艺世纪科技有限公司 | Analysis method, device and the server of video highlight degree |
| 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 |
| CN110740374A (en) * | 2019-10-31 | 2020-01-31 | 广州市网星信息技术有限公司 | multimedia data processing method, 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 |
| CN112752133A (en) * | 2020-03-20 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Video playing method and device, electronic equipment and storage medium |
| 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 |
| CN113055741A (en) * | 2020-12-31 | 2021-06-29 | 科大讯飞股份有限公司 | Video abstract generation method, electronic equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107197368B (en) | 2019-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107197368B (en) | Determine user to the method and system of multimedia content degree of concern | |
| CN107038213B (en) | Video recommendation method and device | |
| JP6054448B2 (en) | Targeted video advertising | |
| JP5546632B2 (en) | Method and mechanism for analyzing multimedia content | |
| CN103686237B (en) | Recommend the method and system of video resource | |
| JP4329436B2 (en) | Content viewing support system, content viewing support method, and computer program | |
| CN103533393B (en) | The family's analysis noted down based on home audience and program commending method | |
| US20170034577A1 (en) | Assessing digital content across a communications network | |
| US20150347903A1 (en) | Method and apparatus for performing sentiment analysis based on user reactions to displayable content | |
| CN107148781A (en) | Produce the customization bloom sequence for describing one or more events | |
| CN105868259A (en) | Video recommendation method and device based on face identification | |
| KR20090086395A (en) | Content rating systems and methods | |
| CN103501434A (en) | Method and device for analyzing quality of video | |
| CN107018408A (en) | The Quality of experience appraisal procedure of mobile terminal HTTP video flowings | |
| CN109040795B (en) | Video recommendation method and system | |
| US8712831B2 (en) | Method and system for quantifying viewer awareness of advertising images in a video source | |
| CN104081386A (en) | Content evaluation/playback device | |
| CN104216883A (en) | Video recommendation reason generating system and method | |
| CN109151488A (en) | According to the method and system of user behavior real-time recommendation direct broadcasting room | |
| CN103002329B (en) | Device and method for predicting reach-frequency table data of network video advertisements | |
| US8036932B2 (en) | Method and system for valuing advertising content | |
| CN106604068A (en) | Method and system for updating media program | |
| CN106941623B (en) | Method and device for evaluating video course quality based on big data | |
| CN109033443A (en) | Recommended determines method, apparatus, storage medium and computer equipment | |
| JP2006011896A (en) | Recommendation system, program recommendation system, and service |
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 |