CN107493512A - The focus mask method and device of video - Google Patents
The focus mask method and device of video Download PDFInfo
- Publication number
- CN107493512A CN107493512A CN201610409455.8A CN201610409455A CN107493512A CN 107493512 A CN107493512 A CN 107493512A CN 201610409455 A CN201610409455 A CN 201610409455A CN 107493512 A CN107493512 A CN 107493512A
- Authority
- CN
- China
- Prior art keywords
- user
- focus
- video
- region
- clusters
- 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
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
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
-
- 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
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
-
- 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
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/47217—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for controlling playback functions for recorded or on-demand content, e.g. using progress bars, mode or play-point indicators or bookmarks
-
- 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
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/4722—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for requesting additional data associated with the content
- H04N21/4725—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for requesting additional data associated with the content using interactive regions of the image, e.g. hot spots
Abstract
The present invention proposes a kind of the focus mask method and device of video.Wherein, the focus mask method includes：Obtain the user behaviors log that user watches video；User behaviors log is analyzed to obtain at least one video hotspot；And video is labeled according at least one video hotspot.The focus mask method of the embodiment of the present invention, time spent when to video manually mark and human cost are saved, and improve the accuracy being labeled to video hotspot.
Description
Technical field
The present invention relates to the focus mask method and device of Internet technical field, more particularly to a kind of video.
Background technology
User often can show some focuses on the video when watching Online Video on the progress bar of player
Label.At present, these focus labels in video are all based on what handmarking obtained, for example, video editing personnel are taking
After video, whole videos is first watched, then the Hot Contents in video are subjected to handmarking.However, pedestrian is entered to video
The mode of work mark needs to expend substantial amounts of manpower and time, and artificial and time cost is all very high, and to the heat of video labeling
Point content is not often that the effect of focus mark is unsatisfactory interested to user.
The content of the invention
It is contemplated that at least solves one of technical problem in correlation technique to a certain extent.
Therefore, first purpose of the present invention is the focus mask method for proposing a kind of video, focus mark side should be regarded
Method saves time spent when to video manually mark and human cost, and improves and enter rower to video hotspot
The accuracy of note.
Second object of the present invention is the focus annotation equipment for proposing a kind of video.
For the above-mentioned purpose, first aspect present invention embodiment proposes a kind of focus mask method of video, including：Obtain
Take the user behaviors log of family viewing video；The user behaviors log is analyzed to obtain at least one video hotspot；And root
The video is labeled according at least one video hotspot.
The focus mask method of the embodiment of the present invention, user behaviors log when user watches video is obtained, and to user behaviors log
Analyzed to obtain at least one video hotspot of video, it is automatic so as to be carried out according to the video hotspot that analysis obtains to video
Mark, save time spent when to video manually mark and human cost, and the viewing behavior based on user
Video hotspot is labeled, improves the accuracy being labeled to video hotspot.
In one embodiment of the invention, the user behaviors log includes the user redirecting in video display process
Operation, it is described the user behaviors log to be analyzed to obtain at least one video hotspot, including：Existed according to the skip operation
Multiple user's focuses are determined in playing progress bar；The multiple user's focus is analyzed to obtain in the playing progress bar
At least one region that clusters；And user's focus in each region that clusters is fitted to generate video hotspot.
Further, in one embodiment of the invention, it is described true in playing progress bar according to the skip operation
Fixed multiple user's focuses, including：Obtain the reproduction time of the skip operation rear video；And when the reproduction time is more than in advance
If during time threshold, determine that the skip operation corresponding position in the playing progress bar is user's focus.
Further, in one embodiment of the invention, user's focus in each region that clusters enters
Row is fitted to generate video hotspot, including：The point centered on each user's focus in the region that clusters, is existed with pre-set radius
Border circular areas is generated in the playing progress bar；According in the quantity of user's focus in the border circular areas and the region that clusters
The quantity of user's focus calculates weights corresponding to user's focus of the central point；And by maximum weight in the region that clusters
User's focus be defined as the video hotspot.
Further, in one embodiment of the invention, user's heat by maximum weight in the region that clusters
Point is defined as the video hotspot, including：If the weights of at least two user's focuses are identical in the region that clusters, calculate every
The distance of individual user's focus and the central point in the region that clusters；It is and the distance of the central point with the region that clusters is minimum
User's focus be defined as the video hotspot.
In one embodiment of the invention, user's focus in each region that clusters be fitted with
Before generating video hotspot, in addition to：By the quantity of user's focus in the region that clusters compared with predetermined number threshold value；
And if the quantity of user's focus is less than or equal to the predetermined number threshold value in the region that clusters, not to the region that clusters
In user's focus be fitted.
For the above-mentioned purpose, second aspect of the present invention embodiment proposes a kind of focus annotation equipment of video, including：Obtain
Modulus block, the user behaviors log of video is watched for obtaining user；Analysis module, for being analyzed the user behaviors log to obtain
Take at least one video hotspot；And labeling module, for entering rower to the video according at least one video hotspot
Note.
The focus annotation equipment of the embodiment of the present invention, user behaviors log when user watches video is obtained, and to user behaviors log
Analyzed to obtain at least one video hotspot of video, it is automatic so as to be carried out according to the video hotspot that analysis obtains to video
Mark, save time spent when to video manually mark and human cost, and the viewing behavior based on user
Video hotspot is labeled, improves the accuracy being labeled to video hotspot.
Further, in one embodiment of the invention, the user behaviors log includes the user in video playback mistake
Skip operation in journey, the analysis module include：Determination sub-module, for according to the skip operation in playing progress bar
Determine multiple user's focuses；Submodule is analyzed, for being analyzed the multiple user's focus to obtain the playing progress rate
At least one region that clusters on bar；And generation submodule, for being carried out to user's focus in each region that clusters
It is fitted to generate video hotspot.
Further, in one embodiment of the invention, the determination sub-module is additionally operable to：Obtain the skip operation
The reproduction time of rear video, and when the reproduction time is more than preset time threshold, determine that the skip operation is broadcast described
It is user's focus to put corresponding position on progress bar.
Further, in one embodiment of the invention, the generation submodule is additionally operable to：With in the region that clusters
Each user's focus centered on point, border circular areas is generated in the playing progress bar with pre-set radius, and according to the circle
The quantity of user's focus calculates user's focus of the central point in the quantity of user's focus and the region that clusters in shape region
Corresponding weights, and user's focus of maximum weight in the region that clusters is defined as the video hotspot.
Further, in one embodiment of the invention, the generation submodule is additionally operable to：In the region that clusters
When the weights of at least two user's focuses are identical, the distance of each user's focus and the central point in the region that clusters is calculated, and
The minimum user's focus of the distance of central point with the region that clusters is defined as the video hotspot.
In one embodiment of the invention, the analysis module also includes：Comparison sub-module, for by the area that clusters
The quantity of user's focus is compared with predetermined number threshold value in domain；And submodule is abandoned, in the region that clusters
When the quantity of user's focus is less than or equal to the predetermined number threshold value, user's focus in the region that clusters is not intended
Close.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein：
Fig. 1 is the flow chart of the focus mask method of the video of one embodiment of the invention；
Fig. 2 is the flow chart of the focus mask method of the video of a specific embodiment of the invention；
Fig. 3 is the schematic diagram of the user's focus and the region that clusters in the playing progress bar of the embodiment of the present invention；
Fig. 4 is the flow chart of the focus mask method of the video of another specific embodiment of the invention；
Fig. 5 is the structural representation of the focus annotation equipment of the video of one embodiment of the invention；
Fig. 6 is the structural representation of the focus annotation equipment of the video of a specific embodiment of the invention；And
Fig. 7 is the structural representation of the focus annotation equipment of the video of another specific embodiment of the invention.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and is not considered as limiting the invention.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can be expressed or
Implicitly include one or more this feature.In the description of the invention, " multiple " are meant that two or more,
Unless otherwise specifically defined.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used to realize specific logical function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Fig. 1 is the flow chart of the focus mask method of the video of one embodiment of the invention.
As shown in figure 1, the focus mask method of video includes：
S101, obtain the user behaviors log that user watches video.
Specifically, when user watches video, record user watches the user behaviors log of video, for example, the lattice of user behaviors log
Formula can be with as shown in the table：
| Sequence number | Video ID | ID | Watch original position | Viewing time | Watch end position | Action type |
Wherein, video ID is the unique mark of video, and ID is the unique mark for the user for watching the video.Operate class
Type is the operation behavior that user is watched during video, for example, skip operation, pausing operation, forwarding operation etc..Watch start bit
User is set between being watched after being operated at the beginning of video, viewing end position is that user watches video after being operated
End time, i.e. user carries out the time of next operation behavior, and viewing time is that user is carried out between operation behavior twice
Watch the time span of video., will whenever user carries out once-through operation that is, user is during video is watched
A user behaviors log is produced, records the viewing behavior of user.
S102, user behaviors log is analyzed to obtain at least one video hotspot.
Specifically, the viewing behavior to user in user behaviors log is analyzed, so as to judge that the viewing behavior of user institute is right
Whether the video content at the time point answered is the viewing focus of user, and then gets one or more video in the video
Focus.For example, when user has carried out skip operation, then the viewing location after redirecting be possible to be exactly user viewing focus；When
User has carried out forwarding operation, then current viewing position may not be just the viewing focus of user；When user has carried out pause behaviour
Make, then the viewing location suspended is it could also be possible that the focus of user's viewing, it may be possible to which user is in the video of the time-out position
Hold the search for having carried out correlation, understand the relevant information of video content.Therefore, by analyzing the user behaviors log of user,
One or more video hotspot in video can be predicted.
S103, video is labeled according at least one video hotspot.
Specifically, automatic marking is carried out to video by analyzing obtained video hotspot.
The focus mask method of the embodiment of the present invention, user behaviors log when user watches video is obtained, and to user behaviors log
Analyzed to obtain at least one video hotspot of video, it is automatic so as to be carried out according to the video hotspot that analysis obtains to video
Mark, save time spent when to video manually mark and human cost, and the viewing behavior based on user
Video hotspot is labeled, improves the accuracy being labeled to video hotspot.
Fig. 2 is the flow chart of the focus mask method of the video of a specific embodiment of the invention.
As shown in Fig. 2 the focus mask method of video includes：
S201, the user behaviors log that user watches video is obtained, wherein, user behaviors log includes user in video display process
Skip operation.
S202, multiple user's focuses are determined in playing progress bar according to skip operation.
Specifically, user's focus is user's time point interested when watching video, and usual user can be by redirecting behaviour
Make, to find the time point for oneself liking watching, therefore, by obtaining the user behaviors log of each user, to use in analytical behavior daily record
The skip operation that family is carried out every time, it may be determined that go out multiple user's focuses that user likes viewing in video.
And then user's focus of the video is directed to by counting multiple users, i.e., according in the user behaviors log of each user
Skip operation determine user's focus, so as to count be directed to the video all users user's focus.
In one embodiment of the invention, the reproduction time of skip operation rear video is obtained, when reproduction time is more than in advance
If during time threshold, determine that skip operation corresponding position in playing progress bar is user's focus.Specifically, user is being carried out
After skip operation, user behavior is generally divided into two kinds, and one kind is to carry out skip operation again immediately after skip operation or see
See after very short a period of time and carry out skip operation, another kind is to have viewed after skip operation for a long time, and is redirecting behaviour
This behavior for a long time is have viewed after work and can be understood as real user's focus, and if entering immediately after skip operation
Row skip operation is either watched after very short a period of time and carries out skip operation, and the time point after the skip operation is possible to simultaneously
Non- is real user's focus.Therefore, the reproduction time of skip operation rear video is judged, between reproduction time is more than preset time
Every when, i.e., user does not carry out skip operation again in the prefixed time interval after skip operation, it is determined that after skip operation
Time point is user's focus, that is, user carries out after skip operation that corresponding position is user's focus in playing progress bar.
Thus, user's focus is determined according to the length of the viewing time after the redirecting behavior and redirect of user, can improves and determine
User's focus accuracy.
S203, multiple user's focuses are analyzed to obtain at least one region that clusters in playing progress bar.
Specifically, multiple user's focuses are analyzed by clustering algorithm, to determine one in playing progress bar
Or multiple regions that cluster.For example, as shown in figure 3, after by analyzing multiple user's focuses, in playing progress bar really
Four regions that cluster are made, that is, the region 1 that clusters, the region 2 that clusters, cluster region 3 and the region 4 that clusters.
It should be appreciated that clustering algorithm can use existing algorithm to realize, it is no longer multiple herein in order to avoid redundancy
It is superfluous.
S204, user's focus in each region that clusters is fitted to generate video hotspot.
Specifically, the region that clusters includes the hot spot region of a part of user's focus, the user's heat this to be clustered in region
Point is fitted to a point, as video a video hotspot.That is, the region that clusters can be multiple, clustered each
User's focus in region is fitted to a point respectively, can obtain multiple video hotspots.
In one embodiment of the invention, the point centered on each user's focus in the region that clusters, with pre-set radius
Border circular areas is generated in playing progress bar, and according to user's focus in the quantity of user's focus in border circular areas and the region that clusters
Quantity calculate user's focus of central point corresponding to weights, and user's focus of maximum weight in the region that clusters is defined as
Video hotspot.Specifically, as shown in figure 3, by taking the region 3 that clusters as an example, it is assumed that the number of the user's focus to cluster in region is n,
The first point centered on user's focus A in the region 3 that clusters, make a radius and be r circle, and calculate the use in this circle
The number m of family focus, then user's focus A weights for the number/cluster in region of user's focus in circle user's focus
Number, i.e. m/n.And then each user's focus in the region 3 that clusters is repeated the above steps respectively, calculate take this to cluster respectively
The weights of each user's focus in region 3, and then using user's focus of maximum weight as video hotspot.
That is, for the multiple regions that cluster generated after analysis in playing progress bar, respectively to each area that clusters
User's focus in domain is fitted, so as to obtain multiple video hotspots of video, the i.e. quantity of video hotspot and the region that clusters
Quantity it is identical.For example, as shown in figure 3, respectively in the region 1 that clusters, the region 2 that clusters, cluster region 3 and the region 4 that clusters
User's focus be fitted after generate video four video hotspots.
In one embodiment of the invention, if the weights of at least two user's focuses are identical in the region that clusters, calculate
The distance of each user's focus and the central point in the region that clusters, and the minimum user of the distance of the central point with the region that clusters is hot
Point is defined as video hotspot.For example, if the weights for calculating in the region that clusters 3 two user's focuses are identical, first determine
Clustered the central point in region, then calculates the distance of central point of each user's focus to the region that clusters, and distance is clustered in region
Heart point user's focus closer to the distance is as video hotspot.
S205, video is labeled according at least one video hotspot.
Specifically, automatic marking is carried out to video by analyzing obtained video hotspot.
The focus mask method of the embodiment of the present invention, multiple user's focuses are determined according to the skip operation of user, and counted
The distribution situation of user's focus of all users, calculates corresponding weight, so as to extract the video hotspot of video, so as to basis
Video hotspot carries out automatic marking to video, saves time spent when to video manually mark and human cost,
And the viewing behavior based on user is labeled to video hotspot, improves the accuracy being labeled to video hotspot.
Fig. 4 is the flow chart of the focus mask method of the video of another specific embodiment of the invention.
As shown in figure 4, the focus mask method of video includes：
S401, the user behaviors log that user watches video is obtained, wherein, user behaviors log includes user in video display process
Skip operation.
S402, multiple user's focuses are determined in playing progress bar according to skip operation.
Specifically, user's focus is user's time point interested when watching video, and usual user can be by redirecting behaviour
Make, to find the time point for oneself liking watching, therefore, by obtaining the user behaviors log of each user, to use in analytical behavior daily record
The skip operation that family is carried out every time, it may be determined that go out multiple user's focuses that user likes viewing in video.
And then user's focus of the video is directed to by counting multiple users, i.e., according in the user behaviors log of each user
Skip operation determine user's focus, so as to count be directed to the video all users user's focus.
In one embodiment of the invention, the reproduction time of skip operation rear video is obtained, when reproduction time is more than in advance
If during time threshold, determine that skip operation corresponding position in playing progress bar is user's focus.Specifically, user is being carried out
After skip operation, user's row is generally divided into two kinds, and one kind is to carry out skip operation again immediately after skip operation or see
See after very short a period of time and carry out skip operation, another kind is to have viewed after skip operation for a long time, and is redirecting behaviour
This behavior for a long time is have viewed after work and can be understood as real user's focus, and if entering immediately after skip operation
Row skip operation is either watched after very short a period of time and carries out skip operation, and the time point after the skip operation is possible to simultaneously
Non- is real user's focus.Therefore, the reproduction time of skip operation rear video is judged, between reproduction time is more than preset time
Every when, i.e., user does not carry out skip operation again in the prefixed time interval after skip operation, it is determined that after skip operation
Time point is user's focus, that is, user carries out after skip operation that corresponding position is user's focus in playing progress bar.
Thus, user's focus is determined according to the length of the viewing time after the redirecting behavior and redirect of user, can improves and determine
User's focus accuracy.
S403, multiple user's focuses are analyzed to obtain at least one region that clusters in playing progress bar.
Specifically, multiple user's focuses are analyzed by clustering algorithm, to determine one in playing progress bar
Or multiple regions that cluster.For example, as shown in figure 3, after by analyzing multiple user's focuses, in playing progress bar really
Four regions that cluster are made, that is, the region 1 that clusters, the region 2 that clusters, cluster region 3 and the region 4 that clusters.
It should be appreciated that clustering algorithm can use existing algorithm to realize, it is no longer multiple herein in order to avoid redundancy
It is superfluous.
S404, by the quantity of user's focus in the region that clusters compared with predetermined number threshold value.
Wherein, predetermined number threshold value N is determined according to actual experiment, and as user used carries out redirecting behaviour to video
The change real-time change for the total number of hops made, for example, predetermined number threshold value N is equal to the 10% of total number of hops.
S405, if the quantity of user's focus is less than or equal to predetermined number threshold value in the region that clusters, not in the region that clusters
User's focus be fitted, discarding clusters region.
Specifically, for the region that clusters, it is assumed that have n user's focus in the region that clusters, if n≤N, illustrate
The user's focus to cluster in region is fewer, without representativeness, or noise, therefore, does not go on and this is clustered
User's focus in region is fitted, that is, gives up the region that clusters.
S406, if the quantity of user's focus is more than predetermined number threshold value in the region that clusters, in each region that clusters
User's focus is fitted to generate video hotspot.
Specifically, if n ＞ N, user's focus in region that this is clustered is fitted to a point, as the one of video
Video hotspot.That is, the region that clusters can be multiple, user's focus in each region that clusters is fitted to one respectively
Point, multiple video hotspots can be obtained.
In one embodiment of the invention, the point centered on each user's focus in the region that clusters, with pre-set radius
Border circular areas is generated in playing progress bar, and according to user's focus in the quantity of user's focus in border circular areas and the region that clusters
Quantity calculate user's focus of central point corresponding to weights, and user's focus of maximum weight in the region that clusters is defined as
Video hotspot.Specifically, as shown in figure 3, by taking the region 3 that clusters as an example, it is assumed that the number of the user's focus to cluster in region is n,
The first point centered on user's focus A in the region 3 that clusters, make a radius and be r circle, and calculate the use in this circle
The number m of family focus, then user's focus A weights for the number/cluster in region of user's focus in circle user's focus
Number, i.e. m/n.And then each user's focus in the region 3 that clusters is repeated the above steps respectively, calculate take this to cluster respectively
The weights of each user's focus in region 3, and then using user's focus of maximum weight as video hotspot.
That is, for the multiple regions that cluster generated after analysis in playing progress bar, respectively to each area that clusters
User's focus in domain is fitted, so as to obtain multiple video hotspots of video, the i.e. quantity of video hotspot and the region that clusters
Quantity it is identical.For example, as shown in figure 3, respectively in the region 1 that clusters, the region 2 that clusters, cluster region 3 and the region 4 that clusters
User's focus be fitted after generate video four video hotspots.
In one embodiment of the invention, if the weights of at least two user's focuses are identical in the region that clusters, calculate
The distance of each user's focus and the central point in the region that clusters, and the minimum user of the distance of the central point with the region that clusters is hot
Point is defined as video hotspot.For example, if the weights for calculating in the region that clusters 3 two user's focuses are identical, first determine
Clustered the central point in region, then calculates the distance of central point of each user's focus to the region that clusters, and distance is clustered in region
Heart point user's focus closer to the distance is as video hotspot.
S407, video is labeled according at least one video hotspot.
Specifically, automatic marking is carried out to video by analyzing obtained video hotspot.
The focus mask method of the embodiment of the present invention, by the quantity of user's focus in each region that clusters and predetermined number threshold
Value is compared, and is given up so as to which the quantity of user's focus in the region that clusters to be less than or equal to the region that clusters of predetermined number threshold value,
Further increase the accuracy of the video hotspot of generation.
In order to realize above-described embodiment, the present invention also proposes a kind of focus annotation equipment of video.
Fig. 5 is the structural representation of the focus annotation equipment of the video of one embodiment of the invention.
As shown in figure 5, focus annotation equipment includes：Acquisition module 100, analysis module 200 and labeling module 300.
Specifically, acquisition module 100 is used to obtain the user behaviors log that user watches video.
Analysis module 200 is used to analyze user behaviors log to obtain at least one video hotspot.
Labeling module 300 is used to be labeled video according at least one video hotspot.
It should be noted that the explanation of the embodiment of the foregoing focus mask method to video is also applied for the implementation
The focus annotation equipment of the video of example, its realization principle is similar, and here is omitted.
The focus annotation equipment of the embodiment of the present invention, user behaviors log when user watches video is obtained, and to user behaviors log
Analyzed to obtain at least one video hotspot of video, it is automatic so as to be carried out according to the video hotspot that analysis obtains to video
Mark, save time spent when to video manually mark and human cost, and the viewing behavior based on user
Video hotspot is labeled, improves the accuracy being labeled to video hotspot.
Fig. 6 is the structural representation of the focus annotation equipment of the video of a specific embodiment of the invention.
As shown in fig. 6, focus annotation equipment includes：Acquisition module 100, analysis module 200 and labeling module 300, wherein,
Analysis module 200 includes：Determination sub-module 210, analysis submodule 220 and generation submodule 230.
Determination sub-module 210 is used to determine multiple user's focuses in playing progress bar according to skip operation.Wherein, at this
In one embodiment of invention, determination sub-module 210 is additionally operable to obtain the reproduction time of skip operation rear video, and when playing
Between when being more than preset time threshold, determine that skip operation corresponding position in playing progress bar is user's focus.
Analysis submodule 220 is at least one poly- in playing progress bar to obtain for being analyzed multiple user's focuses
Cluster region.
Generation submodule 230 is used to be fitted to generate video hotspot user's focus in each region that clusters.Its
In, in one embodiment of the invention, generation submodule 230 is additionally operable to centered on each user's focus in the region that clusters
Point, border circular areas is generated in playing progress bar with pre-set radius, and according to the quantity of user's focus in border circular areas and clustered
The quantity of user's focus calculates weights corresponding to user's focus of central point in region, and by maximum weight in the region that clusters
User's focus is defined as video hotspot.
In one embodiment of the invention, at least two users in the region that clusters are additionally operable in generation submodule 230
When the weights of focus are identical, calculate each user's focus and cluster region central point distance, and by with the region that clusters
The minimum user's focus of the distance of heart point is defined as video hotspot.
It should be noted that the explanation of the embodiment of the foregoing focus mask method to video is also applied for the implementation
The focus annotation equipment of the video of example, its realization principle is similar, and here is omitted.
The focus annotation equipment of the embodiment of the present invention, multiple user's focuses are determined according to the skip operation of user, and counted
The distribution situation of user's focus of all users, calculates corresponding weight, so as to extract the video hotspot of video, so as to basis
Video hotspot carries out automatic marking to video, saves time spent when to video manually mark and human cost,
And the viewing behavior based on user is labeled to video hotspot, improves the accuracy being labeled to video hotspot.
Fig. 7 is the structural representation of the focus annotation equipment of the video of another specific embodiment of the invention.
As shown in fig. 7, focus annotation equipment includes：Acquisition module 100, analysis module 200 and labeling module 300, wherein,
Analysis module 200 includes：Determination sub-module 210, analysis submodule 220, generate submodule 230, comparison sub-module 240 and abandon
Submodule 250.
Comparison sub-module 240 is used for the quantity of user's focus in the region that clusters compared with predetermined number threshold value.
Abandon submodule 250 to be used for when the quantity of user's focus is less than or equal to predetermined number threshold value in the region that clusters, no
User's focus in the region that clusters is fitted.
It should be noted that the explanation of the embodiment of the foregoing focus mask method to video is also applied for the implementation
The focus annotation equipment of the video of example, its realization principle is similar, and here is omitted.
The focus annotation equipment of the embodiment of the present invention, by the quantity of user's focus in each region that clusters and predetermined number threshold
Value is compared, and is given up so as to which the quantity of user's focus in the region that clusters to be less than or equal to the region that clusters of predetermined number threshold value,
Further increase the accuracy of the video hotspot of generation.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, have suitable combinational logic gate circuit application specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office
Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, the skill of this area
Art personnel can be tied the different embodiments or example and the feature of different embodiments or example described in this specification
Close and combine.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changed, replacing and modification.
Claims (12)
1. the focus mask method of a kind of video, it is characterised in that comprise the following steps：
Obtain the user behaviors log that user watches video；
The user behaviors log is analyzed to obtain at least one video hotspot；And
The video is labeled according at least one video hotspot.
2. focus mask method as claimed in claim 1, it is characterised in that the user behaviors log includes the user in video
Skip operation in playing process, it is described the user behaviors log to be analyzed to obtain at least one video hotspot, including：
Multiple user's focuses are determined in playing progress bar according to the skip operation；
The multiple user's focus is analyzed to obtain at least one region that clusters in the playing progress bar；And
User's focus in each region that clusters is fitted to generate video hotspot.
3. focus mask method as claimed in claim 2, it is characterised in that it is described according to the skip operation in playing progress rate
Multiple user's focuses are determined on bar, including：
Obtain the reproduction time of the skip operation rear video；And
When the reproduction time is more than preset time threshold, determine that the skip operation is corresponding in the playing progress bar
Position is user's focus.
4. focus mask method as claimed in claim 2, it is characterised in that the user in each region that clusters
Focus is fitted to generate video hotspot, including：
The point centered on each user's focus in the region that clusters, circle is generated in the playing progress bar with pre-set radius
Shape region；
According in the quantity of user's focus in the border circular areas and the region that clusters user's focus quantity calculate it is described in
Weights corresponding to user's focus of heart point；And
User's focus of maximum weight in the region that clusters is defined as the video hotspot.
5. focus mask method as claimed in claim 4, it is characterised in that described by maximum weight in the region that clusters
User's focus is defined as the video hotspot, including：
If the weights of at least two user's focuses are identical in the region that clusters, each user's focus and the area that clusters are calculated
The distance of the central point in domain；And
The minimum user's focus of the distance of central point with the region that clusters is defined as the video hotspot.
6. focus mask method as claimed in claim 2, it is characterised in that in the use in each region that clusters
Family focus is fitted with before generating video hotspot, in addition to：
By the quantity of user's focus in the region that clusters compared with predetermined number threshold value；And
If the quantity of user's focus is less than or equal to the predetermined number threshold value in the region that clusters, not to the region that clusters
In user's focus be fitted.
A kind of 7. focus annotation equipment of video, it is characterised in that including：
Acquisition module, the user behaviors log of video is watched for obtaining user；
Analysis module, for being analyzed the user behaviors log to obtain at least one video hotspot；And
Labeling module, for being labeled according at least one video hotspot to the video.
8. focus annotation equipment as claimed in claim 7, it is characterised in that the user behaviors log includes the user in video
Skip operation in playing process, the analysis module include：
Determination sub-module, for determining multiple user's focuses in playing progress bar according to the skip operation；
Submodule is analyzed, it is at least one in the playing progress bar to obtain for being analyzed the multiple user's focus
Cluster region；And
Submodule is generated, for being fitted user's focus in each region that clusters to generate video hotspot.
9. focus annotation equipment as claimed in claim 8, it is characterised in that the determination sub-module is additionally operable to：
The reproduction time of the skip operation rear video is obtained, and when the reproduction time is more than preset time threshold, it is determined that
The skip operation corresponding position in the playing progress bar is user's focus.
10. focus annotation equipment as claimed in claim 8, it is characterised in that the generation submodule is additionally operable to：
The point centered on each user's focus in the region that clusters, circle is generated in the playing progress bar with pre-set radius
Shape region, and institute is calculated according to the quantity of user's focus in the quantity of user's focus in the border circular areas and the region that clusters
State weights corresponding to user's focus of central point, and user's focus of maximum weight in the region that clusters is defined as described
Video hotspot.
11. focus annotation equipment as claimed in claim 10, it is characterised in that the generation submodule is additionally operable to：
When the weights of at least two user's focuses are identical in the region that clusters, each user's focus and the area that clusters are calculated
The distance of the central point in domain, and the minimum user's focus of the distance of the central point with the region that clusters is defined as the video
Focus.
12. focus annotation equipment as claimed in claim 8, it is characterised in that the analysis module also includes：
Comparison sub-module, for by the quantity of user's focus in the region that clusters compared with predetermined number threshold value；And
Submodule is abandoned, when the quantity for user's focus in the region that clusters is less than or equal to the predetermined number threshold value,
User's focus in the region that clusters is not fitted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610409455.8A CN107493512B (en) | 2016-06-12 | 2016-06-12 | Video hotspot marking method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610409455.8A CN107493512B (en) | 2016-06-12 | 2016-06-12 | Video hotspot marking method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107493512A true CN107493512A (en) | 2017-12-19 |
| CN107493512B CN107493512B (en) | 2020-11-13 |
Family
ID=60642316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610409455.8A Active CN107493512B (en) | 2016-06-12 | 2016-06-12 | Video hotspot marking method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107493512B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN108632670A (en) * | 2018-03-15 | 2018-10-09 | 北京奇艺世纪科技有限公司 | A kind of video satisfaction determines method and device |
| CN113727201A (en) * | 2021-08-30 | 2021-11-30 | 北京字节跳动网络技术有限公司 | Data processing method and device, computer equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120155834A1 (en) * | 2010-12-21 | 2012-06-21 | General Instrument Corporation | Bookmarks in Recorded Video |
| US20140215514A1 (en) * | 2012-06-05 | 2014-07-31 | Tvstorm Co., Ltd. | Apparatus of rendering user interface for playing broadcast programs and the method thereof |
| CN104700090A (en) * | 2015-03-25 | 2015-06-10 | 武汉大学 | Method and system for measuring eye movement fixation points based on density |
| CN104717571A (en) * | 2013-12-13 | 2015-06-17 | 中国移动通信集团公司 | Key playing time point determination method, video playing method and related device |
| CN104796777A (en) * | 2015-04-26 | 2015-07-22 | 成都创行信息科技有限公司 | Hot video information pushing method |
| CN104918067A (en) * | 2014-03-12 | 2015-09-16 | 乐视网信息技术（北京）股份有限公司 | Method and system for performing curve processing on video hot degree |
| CN105426548A (en) * | 2015-12-29 | 2016-03-23 | 海信集团有限公司 | Video recommendation method and device based on multiple users |
-
2016
- 2016-06-12 CN CN201610409455.8A patent/CN107493512B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120155834A1 (en) * | 2010-12-21 | 2012-06-21 | General Instrument Corporation | Bookmarks in Recorded Video |
| US20140215514A1 (en) * | 2012-06-05 | 2014-07-31 | Tvstorm Co., Ltd. | Apparatus of rendering user interface for playing broadcast programs and the method thereof |
| CN104717571A (en) * | 2013-12-13 | 2015-06-17 | 中国移动通信集团公司 | Key playing time point determination method, video playing method and related device |
| CN104918067A (en) * | 2014-03-12 | 2015-09-16 | 乐视网信息技术（北京）股份有限公司 | Method and system for performing curve processing on video hot degree |
| CN104700090A (en) * | 2015-03-25 | 2015-06-10 | 武汉大学 | Method and system for measuring eye movement fixation points based on density |
| CN104796777A (en) * | 2015-04-26 | 2015-07-22 | 成都创行信息科技有限公司 | Hot video information pushing method |
| CN105426548A (en) * | 2015-12-29 | 2016-03-23 | 海信集团有限公司 | Video recommendation method and device based on multiple users |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN108632670A (en) * | 2018-03-15 | 2018-10-09 | 北京奇艺世纪科技有限公司 | A kind of video satisfaction determines method and device |
| CN108632670B (en) * | 2018-03-15 | 2021-03-26 | 北京奇艺世纪科技有限公司 | Video satisfaction determining method and device |
| CN113727201A (en) * | 2021-08-30 | 2021-11-30 | 北京字节跳动网络技术有限公司 | Data processing method and device, computer equipment and storage medium |
| CN113727201B (en) * | 2021-08-30 | 2022-08-02 | 北京字节跳动网络技术有限公司 | Data processing method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107493512B (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110248258B (en) | Recommendation method and device for video clips, storage medium and computer equipment | |
| US20210287012A1 (en) | Detection of demarcating segments in video | |
| US11727148B2 (en) | Methods and apparatus to assign demographic information to panelists | |
| US9918128B2 (en) | Content categorization using facial expression recognition, with improved detection of moments of interest | |
| CN109241427A (en) | Information-pushing method, device, computer equipment and storage medium | |
| CN104123325B (en) | The recommendation method and recommendation server of multimedia file | |
| CN106507143A (en) | Video recommendation method and device | |
| CN107493512A (en) | The focus mask method and device of video | |
| CN104270654B (en) | Internet video plays monitoring method and device | |
| CN109587578A (en) | The processing method and processing device of video clip | |
| CN110515816A (en) | A kind of analysis method and analysis system of user behavior | |
| CN106408467A (en) | Legal service system based on internet technologies | |
| CN108388388A (en) | Interaction content display methods and device | |
| CN111026969B (en) | Content recommendation method and device, storage medium and server | |
| CN104915864B (en) | The method and device that the dispensing effect of impression information is evaluated and tested | |
| CN104320674B (en) | The monitoring method and device of Internet video fragment | |
| KR20210038990A (en) | Media identification using watermarks and signatures | |
| CN102007764B (en) | Method of storing and displaying broadcast contents and apparatus therefor | |
| CN109359108B (en) | Report extraction method and device, storage medium and electronic equipment | |
| CN104410873A (en) | Method and device of detecting number of television channel users | |
| CN109729428B (en) | Television channel video audience statistical method and device | |
| CN105979287B (en) | Program keyword extraction and statistics method and device | |
| CN114385936A (en) | Method, device, equipment and storage medium for updating media content collection list | |
| CN104410874A (en) | A method, a device, and a system for detecting video viscosity information | |
| CN107688951A (en) | Information-pushing method and device |
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 |