CN109672936B - Method and device for determining video evaluation set and electronic equipment - Google Patents
Method and device for determining video evaluation set and electronic equipment Download PDFInfo
- Publication number
- CN109672936B CN109672936B CN201811603478.8A CN201811603478A CN109672936B CN 109672936 B CN109672936 B CN 109672936B CN 201811603478 A CN201811603478 A CN 201811603478A CN 109672936 B CN109672936 B CN 109672936B
- Authority
- CN
- China
- Prior art keywords
- video
- unit
- time
- segment
- evaluated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
- H04N21/442—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user 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
- H04N21/45—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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Social Psychology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a method, a device and electronic equipment for determining a video evaluation set, wherein the method comprises the following steps: acquiring video clip capturing records of a video to be evaluated by a video platform user, wherein the video clip capturing records comprise the starting time and the ending time of each captured video clip; calculating the intercepted times of each unit segment in different time periods in the video to be evaluated according to the starting time and the ending time of each intercepted video segment recorded by the video segment interception; selecting unit fragments with the interception times not lower than a preset threshold value to obtain each unit fragment to be polymerized; according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain target video sequences; and determining a set formed by each target video sequence as an evaluation set of the video to be evaluated. The invention realizes the high-efficiency obtaining of the evaluation set of the video.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for determining a video evaluation set, and an electronic device.
Background
The video website can conduct various analyses on the online video, analyze whether the online video is liked by the audience, analyze the liked part of the video by the audience, conduct directional popularization and operation and the like, and improve the user experience of the video website.
To analyze a video, an evaluation set of the video needs to be determined. In the prior art, when an evaluation set of videos is determined, after a annotating person needs to watch the videos manually, scores are scored for video frames, and the scored video frames are used as the evaluation set of each video. However, this method requires the annotator to first watch the entire video, know the entire video as a whole, and then watch the video again, giving a score to each frame in the video, the workload of the annotator is large, and the annotator forgets the mark before and after the mark because the number of frames of the video is too many.
Therefore, the efficiency of determining the evaluation set of the video in a manual labeling mode by a labeling person is low. Therefore, how to realize an efficient evaluation set for obtaining videos still remains a technical problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention aims to provide a method and a device for determining a video evaluation set and electronic equipment, so as to efficiently obtain the video evaluation set. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention discloses a method for determining a video evaluation set, where the method includes:
acquiring video clip capturing records of a video to be evaluated by a video platform user, wherein the video clip capturing records comprise the starting time and the ending time of each captured video clip;
calculating the intercepted times of each unit segment in different time periods in the video to be evaluated according to the starting time and the ending time of each intercepted video segment recorded by the video segment interception;
selecting unit fragments with the interception times not lower than a preset threshold value to obtain each unit fragment to be polymerized;
according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain target video sequences;
and determining a set formed by each target video sequence as an evaluation set of the video to be evaluated.
Optionally, the method further comprises: and acquiring preset unit time, and logically dividing the video to be evaluated into a plurality of unit segments by taking the unit time as a dividing unit.
Optionally, the calculating, according to the start time and the end time of each intercepted video segment recorded by the video segment interception, the number of times of interception of each unit segment in different time periods in the video to be evaluated, includes:
determining each unit segment contained in the starting time and the ending time of each intercepted video segment;
and accumulating the interception times of the intercepted video of the unit fragment aiming at each unit fragment.
Optionally, before the unit segments with the interception frequency not lower than the preset threshold are selected to obtain each unit segment to be aggregated, the method further includes:
and calculating the average value of the interception times of the intercepted video of each unit segment, and taking the average value as the preset threshold value.
Optionally, the aggregating the unit segments to be aggregated according to a preset clustering algorithm in a time sequence to obtain each target video sequence includes:
sequencing the unit fragments to be aggregated according to the time sequence;
and determining each target video sequence formed by each sequenced unit segment to be aggregated according to the core radius and the density of a preset DBSCAN algorithm.
In a second aspect, an embodiment of the present invention discloses a device for determining a video assessment set, where the device includes:
the video clip intercepting record acquiring module is used for acquiring video clip intercepting records of a video platform user aiming at a video to be evaluated, wherein the video clip intercepting records comprise the starting time and the ending time of each intercepted video clip;
the unit segment intercepting frequency determining module is used for calculating the intercepting frequency of each unit segment intercepted in different time periods in the video to be evaluated according to the starting time and the ending time of each intercepted video segment recorded by the video segment intercepting;
the unit segment to be polymerized determining module is used for selecting the unit segments with the interception frequency not lower than a preset threshold value to obtain each unit segment to be polymerized;
the target video sequence determining module is used for aggregating the unit segments to be aggregated according to a preset clustering algorithm and a time sequence to obtain each target video sequence;
and the to-be-evaluated video evaluation set determining module is used for determining a set formed by each target video sequence as the evaluation set of the to-be-evaluated video.
Optionally, the apparatus further comprises:
and the unit segment determining module is specifically configured to acquire a preset unit time, and logically divide the video to be evaluated into a plurality of unit segments by using the unit time as a dividing unit.
Optionally, the unit segment interception number determining module includes:
a unit segment determining submodule, configured to determine, for each of the intercepted video segments, each unit segment included in a start time and an end time of the intercepted video segment;
and the unit fragment interception frequency determining submodule is used for accumulating the interception frequency of the intercepted video of the unit fragment aiming at each unit fragment.
Optionally, the apparatus further comprises:
and the preset threshold value determining module is used for calculating the average value of the interception times of the intercepted video of each unit segment and taking the average value as the preset threshold value.
Optionally, the target video sequence determining module includes:
the unit segment to be aggregated sequencing submodule is used for sequencing each unit segment to be aggregated according to a time sequence;
and the target video sequence determining submodule is used for determining each target video sequence formed by each sequenced unit segment to be aggregated according to the core radius and the density of a preset DBSCAN algorithm.
In a third aspect, an embodiment of the present invention discloses an electronic device, including a processor, a communication interface, a memory and a communication bus, where the processor, the communication interface, and the memory complete mutual communication through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of the above methods for determining a video evaluation set when executing a program stored in the memory.
In another aspect, an embodiment of the present invention discloses a computer-readable storage medium, in which a computer program is stored, and when being executed by a processor, the computer program implements the method steps of any one of the above methods for determining a video evaluation set.
Embodiments of the present invention further provide a computer program product containing instructions for implementing the method steps of any one of the above methods for determining a video evaluation set when the computer program product runs on a computer.
In the method, the device and the electronic equipment for determining the video evaluation set, provided by the embodiment of the invention, a video clip intercepting record of a video platform user for a video to be evaluated is obtained; according to the video clip intercepting record, calculating the intercepting times of each unit clip in the video to be evaluated; selecting unit fragments with the interception times not lower than a preset threshold value to obtain each unit fragment to be polymerized; according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain target video sequences; and determining a set formed by all the target video sequences as an evaluation set of the video to be evaluated. According to the method for obtaining the evaluation set of the video to be evaluated based on the video clip intercepted by the user, the evaluation set of the video to be evaluated can be determined without manual marking, compared with a manual marking mode, the time is saved, and the efficient obtaining of the evaluation set of the video is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
Fig. 1 is a flowchart of a method for determining a video evaluation set according to an embodiment of the present invention;
fig. 2 is a flowchart of an intercepted number determining method for each unit segment intercepted in the determining method for a video evaluation set according to the embodiment of the present invention;
fig. 3 is a diagram showing the number of times of capturing each unit clip is captured in the method for determining a video evaluation set according to the embodiment of the present invention;
fig. 4 is a flowchart of a target video sequence determination method in a video evaluation set determination method according to an embodiment of the present invention;
fig. 5 is a diagram illustrating a method for determining a target video sequence in a method for determining a video evaluation set according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a device for determining a video evaluation set according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
After the video website is operated for a period of time, a lot of data of user's watching, such as playing data, dragging data, barrage data, etc., can be accumulated, the video website can use the data to fit a curve, and the change trend that the video is liked is further obtained by analyzing the curve. Specifically, the video website can analyze the curve rising trend and the reasons of the peak, and analyze the curve falling and the reasons of the valley, so as to make a targeted decision. From the above, to make accurate and effective directional popularization, the trend calculation of the curve needs to be accurate, otherwise, the provided suggestion is invalid, and further, how to evaluate the calculated curve, how to calculate the accuracy of the curve accurately, and if to obtain objective accuracy, an objective evaluation set needs to be obtained.
In the prior art, there is also a manual annotation method for discretizing video frames, so as to relatively reduce the annotation cost of annotation personnel. The specific method is that a annotating person marks out wonderful segments after finishing watching the whole video, the annotating person only needs to mark out some segments with impressive impression in the video, the problem that a specific frame of the video is forgotten can be relieved, the problem that specific numerical values are not given easily can be solved, the specific wonderful numerical values do not need to be given as long as the segments are marked out, the obtained segments do not need to be distinguished from each other to be more wonderful, the segments are equal in position and are all wonderful segments, and the segments can be evaluated only by discretizing a model result.
Although the method greatly reduces the labeling difficulty, the labeling personnel still need to label, the wonderful segment is subjective, the results marked by different labeling personnel are different, and the objectivity of the obtained result cannot be guaranteed.
From the above analysis, it can be known that it is inefficient to determine the evaluation set of the video in a manual annotation manner by an annotating person in the prior art.
In order to solve the technical problem that the efficiency of determining a video evaluation set through manual labeling in the prior art is low, the embodiment of the invention discloses a method and a device for determining the video evaluation set, electronic equipment and a storage medium. The specific process is as follows:
in a first aspect, an embodiment of the present invention discloses a method for determining a video evaluation set, as shown in fig. 1. Fig. 1 is a flowchart of a method for determining a video evaluation set according to an embodiment of the present invention, where the method includes:
s101, video clip capturing records of a video platform user for a video to be evaluated are obtained, wherein the video clip capturing records comprise the starting time and the ending time of each captured video clip.
The execution main body of the embodiment of the invention can be a back-end server of the video platform. In the step, a video clip capturing record of a video platform user for a video to be evaluated is obtained, and the video clip capturing records at least the starting time and the ending time of each captured video clip.
The method comprises the following steps: and acquiring a video clip intercepting record aiming at the video to be evaluated in a database or a log for storing video platform data, wherein the video clip intercepting record at least comprises the starting time and the ending time of each intercepted video clip.
And S102, calculating the intercepted times of each unit segment in different time periods in the video to be evaluated according to the starting time and the ending time of each intercepted video segment recorded by the video segment interception.
In this step, the video to be evaluated may be divided into a plurality of unit segments, and one or more unit segments of the video to be evaluated are included in the start time and the end time of each intercepted video segment. And then, according to the starting time and the ending time of each intercepted video segment, the intercepted times of each unit segment in different time periods in the video to be evaluated are calculated. The interception times can reflect the user's preference degree to the unit segment, i.e. the interception times can represent the fineness of the video frame of the unit segment.
In this step, the number of times of capturing each unit segment at different time intervals in the video to be evaluated is calculated as follows: the method comprises the steps of dividing a video to be evaluated into a plurality of unit segments, dividing each intercepted video segment into a plurality of unit segments, and further counting the number of the intercepted video segments of each unit segment in different time periods of the video to be evaluated to obtain the intercepted times of each unit segment in different time periods in the video to be evaluated.
In addition, in the embodiment of the present invention, the start time and the end time of each intercepted video segment may be placed on the same coordinate axis, the minimum start time and the maximum end time are taken as a target time period, the time period is divided into a plurality of unit segments, and then the number of the intercepted video segments of each unit segment in different time periods may be counted, so as to obtain the intercepted times of each unit segment in different time periods in the video to be evaluated.
Optionally, in step S102, a preset unit time may be obtained first, and the video to be evaluated is logically divided into a plurality of unit segments by using the unit time as a dividing unit.
For example, if the preset unit time is seconds and milliseconds, the unit time may be seconds and milliseconds. In this step, the video to be evaluated may be logically divided into a plurality of unit segments. For example, the episode a to be evaluated is 60 minutes, and may be divided into a plurality of unit sections by taking seconds as a unit section.
In the step, the video to be evaluated can be divided into a plurality of unit segments by taking seconds as the unit segments. And accumulating the interception times of the intercepted video clip corresponding to the unit clip aiming at each unit clip, and finally obtaining the interception times of the intercepted video of each unit clip in the video to be evaluated.
S103, selecting the unit segments with the interception frequency not lower than a preset threshold value to obtain each unit segment to be polymerized.
In order to estimate the video chroma in this step, a video evaluation set with a high chroma needs to be obtained, so in this step, in order to reduce the amount of calculation, a preset threshold value can be set by an implementer, and then a unit segment with the interception frequency not lower than the preset threshold value is screened.
In this step, the unit segments with the interception frequency not lower than the preset threshold can be directly selected to obtain each unit segment to be polymerized. Or, in all the unit segments, deleting the unit segments with the interception frequency lower than the preset threshold value to obtain each unit segment to be aggregated.
Optionally, before the step S103, a unit segment with a video frame frequency not lower than a preset threshold is selected, and before the unit segment to be aggregated is obtained, the method further includes:
and calculating the average value of the intercepted times of each unit segment, and taking the average value as the preset threshold value.
In this step, in order to set a suitable preset threshold, an average of the number of times each unit segment is intercepted may be calculated, and the average is used as the preset threshold.
And S104, according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain each target video sequence.
In this step, each unit segment to be aggregated obtained in S103 is aggregated according to a time sequence by a preset clustering algorithm, so as to obtain each aggregated target video sequence.
The preset clustering algorithm may be a DBSCAN algorithm. Specific clustering algorithms are detailed in the following examples.
And S105, determining a set formed by the target video sequences as an evaluation set of the video to be evaluated.
In the method for determining the video evaluation set provided by the embodiment of the invention, video clip interception records of a video to be evaluated by a video platform user are obtained; according to the video clip intercepting record, calculating the intercepting times of each unit clip in the video to be evaluated; selecting unit fragments with the interception times not lower than a preset threshold value to obtain each unit fragment to be polymerized; according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain target video sequences; and determining a set formed by all the target video sequences as an evaluation set of the video to be evaluated. According to the method for obtaining the evaluation set of the video to be evaluated based on the video clip intercepted by the user, the evaluation set of the video to be evaluated can be determined without manual marking, compared with a manual marking mode, the time is saved, and the efficient obtaining of the evaluation set of the video is realized.
Optionally, in an embodiment of the method for determining a video evaluation set according to the present invention, in the step S102, the number of times of capturing each unit segment in different time periods in the video to be evaluated is calculated according to the start time and the end time of each captured video segment recorded in the video segment capturing, as shown in fig. 2. Fig. 2 is a flowchart of a method for determining the number of times each unit segment is intercepted in a method for determining a video evaluation set according to an embodiment of the present invention, where the method includes:
s201, for each of the clipped video clips, each unit clip included in the start time and the end time of the clipped video clip is determined.
And finding out the video clip intercepting record for a video to be evaluated, wherein the video clip intercepting record comprises each intercepted video clip, and each intercepted clip has a start-stop moment corresponding to the video playing bar. In this step, each unit segment included in the start time and the end time of each captured video segment is determined. For example, a unit segment is a video segment of one second.
And S202, accumulating the interception times of the intercepted video of the unit section aiming at each unit section.
And counting the interception times of the intercepted video of the unit segment aiming at each unit segment to obtain the intercepted times of each unit segment in different time periods in the video to be evaluated. For example, fig. 3 is a diagram showing the number of times each unit clip is intercepted in a method for determining a video evaluation set according to an embodiment of the present invention. In fig. 3, the abscissa represents a video frame and the ordinate represents the number of times of truncation. Each bar represents the interception times of the intercepted video of the unit segment, and the interception times can reflect the video wonderful degree of the unit segment. That is, the more times the unit segment is cut, the more brilliant the video of the unit segment is.
And obtaining the highlight value sequence of each unit segment in different time periods in the video to be evaluated through the obtained interception times of each unit segment intercepted by the video. E.g., {2:10,3:12,4:9,8:10}, expressed as a 2 second highlight of 10, a 3 second highlight of 12, and so on.
Therefore, according to the embodiment of the invention, the video clip interception times of each unit clip of the video to be evaluated can be obtained based on the video clip interception record of the video to be evaluated by the user, and the video chroma of each unit clip is reflected by the interception times, so that the problem of low efficiency of manually marking and determining the video frame chroma is solved.
Optionally, in an embodiment of the method for determining a video evaluation set according to the present invention, in the step S104, the unit segments to be aggregated are aggregated according to a preset clustering algorithm in a time sequence, so as to obtain the target video sequences, as shown in fig. 4. Fig. 4 is a flowchart of a method for determining a target video sequence in a method for determining a video evaluation set according to an embodiment of the present invention, including:
s401, sequencing the unit fragments to be aggregated according to the time sequence.
S402, determining continuous target video sequences formed by the sequenced unit segments to be aggregated according to the core radius and the density in the preset DBSCAN algorithm.
The DBSCAN algorithm derives a maximum density connected sample set from the density reachable relation, and one or more core objects may be in the DBSCAN cluster. If there is only one core object, then the other non-core object samples in the cluster are all within witnessed reach of this core; if there are multiple core objects, there must be one other core object in the neighborhood of any one core object in the cluster, otherwise the two core objects cannot be reached in density. The DBSCAN cluster is composed of the set of all samples in the neighborhood of the core objects.
In the embodiment of the invention, the sequenced unit segments to be aggregated are clustered by utilizing the characteristics of the DBSCAN algorithm, and the unit segments to be aggregated are clustered according to the core object and the core radius to obtain one or more continuous target video sequences with the density reaching.
Specifically, as shown in fig. 5, fig. 5 is a diagram illustrating a method for determining a target video sequence in a method for determining a video evaluation set according to an embodiment of the present invention.
The abscissa of fig. 5 represents a video frame, the ordinate represents the number of times of capturing, and each bar represents the number of times of capturing the unit section by the captured video, which may reflect the video highlights of the unit section. The unit segments with the unit segment interception times lower than a preset threshold value are removed from the columnar bars, the unit segments to be aggregated which are sequenced according to time are obtained, the unit segments to be aggregated are highlight frames, and meanwhile, video frames corresponding to the cleaned unit segments are marked as non-highlight frames.
After non-wonderful frames are removed from the washed wonderful frame sequence, the wonderful frame sequence becomes discontinuous, but due to the continuity of the video, if most of the wonderful frames are wonderful at one position, only some frames in the middle are not wonderful frames, and the frames are considered to be wonderful frames if the distances between the frames are small, and the frames can form a wonderful sequence. The parameters of the DBSCAN algorithm are set to have a core radius of 3 and a density of 0.5, which means that if more than 50% of the highlight frames (here, more than 3 frames) exist in 7 seconds, which is 3 seconds or so, of a certain frame, the continuous segment composed of the 7 frames also have a clustered highlight sequence although non-highlight frames exist. As shown in fig. 5, 1040 in the figure has 2 frames of highlight frames on the left, 1 frame of highlight frame on the right, and is itself a highlight frame, and there are 4 frames of highlight frames in 7 seconds before and after 3 seconds, and this segment may form a highlight sequence, and the obtained continuous highlight sequence is the target video sequence of the embodiment of the present invention.
And finally, determining a set formed by all the target video sequences as an evaluation set of the video to be evaluated in the embodiment of the invention.
Therefore, by the method for determining the video evaluation set, the evaluation set of the video to be evaluated can be determined without manual marking, time is saved compared with a manual marking mode, and the evaluation set of the video can be efficiently obtained. And a more objective evaluation result is obtained based on the user data.
In a second aspect, an embodiment of the present invention discloses a device for determining a video assessment set, as shown in fig. 6.
Fig. 6 is a schematic structural diagram of a device for determining a video evaluation set according to an embodiment of the present invention, where the device includes:
a video clip capture record obtaining module 601, configured to obtain a video clip capture record of a video platform user for a video to be evaluated, where the video clip capture record includes a start time and an end time of each captured video clip;
a unit section capturing frequency determining module 602, configured to calculate capturing frequencies of each unit section captured in different time periods in the video to be evaluated according to the start time and the end time of each captured video section recorded in the video section capturing;
a unit segment to be aggregated determining module 603, configured to select a unit segment whose interception frequency is not lower than a preset threshold, to obtain each unit segment to be aggregated;
a target video sequence determining module 604, configured to aggregate, according to a preset clustering algorithm, the unit segments to be aggregated according to a time sequence, so as to obtain each target video sequence;
an evaluation set determining module 605 of the video to be evaluated is configured to determine a set formed by each of the target video sequences as an evaluation set of the video to be evaluated.
In the device for determining the video evaluation set provided by the embodiment of the invention, video clip interception records of a video platform user aiming at a video to be evaluated are obtained; according to the video clip intercepting record, calculating the intercepting times of each unit clip in the video to be evaluated; selecting unit fragments with the interception times not lower than a preset threshold value to obtain each unit fragment to be polymerized; according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain target video sequences; and determining a set formed by all the target video sequences as an evaluation set of the video to be evaluated. According to the method for obtaining the evaluation set of the video to be evaluated based on the video clip intercepted by the user, the evaluation set of the video to be evaluated can be determined without manual marking, compared with a manual marking mode, the time is saved, and the efficient obtaining of the evaluation set of the video is realized.
Optionally, in an embodiment of the apparatus for determining a video assessment set according to the present invention, the apparatus further includes:
and the unit segment determining module is specifically used for acquiring preset unit time, and logically dividing the video to be evaluated into a plurality of unit segments by taking the unit time as a dividing unit.
Optionally, in an embodiment of the apparatus for determining a video evaluation set according to the present invention, the module 602 for determining the number of times of capturing a unit segment includes:
a unit segment determining submodule for determining, for each of the captured video segments, each unit segment included in the start time and the end time of the captured video segment;
and the unit fragment interception frequency determining submodule is used for accumulating the interception frequency of the intercepted video of the unit fragment aiming at each unit fragment.
Optionally, in an embodiment of the apparatus for determining a video assessment set according to the present invention, the apparatus further includes:
and the preset threshold value determining module is used for calculating the average value of the interception times of the intercepted video of each unit segment and taking the average value as the preset threshold value.
Optionally, in an embodiment of the apparatus for determining a video assessment set according to the present invention, the target video sequence determining module 604 includes:
the unit segment to be aggregated sequencing submodule is used for sequencing each unit segment to be aggregated according to the time sequence;
and the target video sequence determining submodule is used for determining each target video sequence formed by each sequenced unit segment to be aggregated according to the core radius and the density of a preset DBSCAN algorithm.
In a third aspect, an embodiment of the invention discloses an electronic device, as shown in fig. 7. Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, which includes a processor 701, a communication interface 702, a memory 703 and a communication bus 704, where the processor 701, the communication interface 702 and the memory 703 complete communication with each other through the communication bus 704;
a memory 703 for storing a computer program;
the processor 701 is configured to implement the following method steps when executing the program stored in the memory 703:
acquiring video clip capturing records of a video to be evaluated by a video platform user, wherein the video clip capturing records comprise the starting time and the ending time of each captured video clip;
calculating the intercepted times of each unit segment in different time periods in the video to be evaluated according to the starting time and the ending time of each intercepted video segment recorded by the video segment interception;
selecting unit fragments with the interception times not lower than a preset threshold value to obtain each unit fragment to be polymerized;
according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain target video sequences;
and determining a set formed by the target video sequences as an evaluation set of the video to be evaluated.
The communication bus 704 mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 704 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface 702 is used for communication between the above-described electronic apparatus and other apparatuses.
The Memory 703 may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory 703 may also be at least one memory device located remotely from the processor 701.
The Processor 701 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
In the electronic equipment provided by the embodiment of the invention, a video clip intercepting record of a video platform user for a video to be evaluated is acquired; according to the video clip intercepting record, calculating the intercepting times of each unit clip in the video to be evaluated; selecting unit fragments with the interception times not lower than a preset threshold value to obtain each unit fragment to be polymerized; according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain target video sequences; and determining a set formed by all the target video sequences as an evaluation set of the video to be evaluated. According to the method for obtaining the evaluation set of the video to be evaluated based on the video clip intercepted by the user, the evaluation set of the video to be evaluated can be determined without manual marking, compared with a manual marking mode, the time is saved, and the efficient obtaining of the evaluation set of the video is realized.
In another aspect, an embodiment of the present invention discloses a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method of determining the video evaluation set is implemented as any one of the above method steps.
In a computer-readable storage medium provided by an embodiment of the present invention, a video clip capture record of a video platform user for a video to be evaluated is obtained; according to the video clip intercepting record, calculating the intercepting times of each unit clip in the video to be evaluated; selecting unit fragments with the interception times not lower than a preset threshold value to obtain each unit fragment to be polymerized; according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain target video sequences; and determining a set formed by all the target video sequences as an evaluation set of the video to be evaluated. According to the method for obtaining the evaluation set of the video to be evaluated based on the video clip intercepted by the user, the evaluation set of the video to be evaluated can be determined without manual marking, compared with a manual marking mode, the time is saved, and the efficient obtaining of the evaluation set of the video is realized.
Embodiments of the present invention further provide a computer program product containing instructions for implementing any of the above method steps of the above method for determining a video evaluation set when the computer program product runs on a computer.
In a computer program product including instructions provided by an embodiment of the present invention, a video clip capture record of a video platform user for a video to be evaluated is obtained; according to the video clip intercepting record, calculating the intercepting times of each unit clip in the video to be evaluated; selecting unit fragments with the interception times not lower than a preset threshold value to obtain each unit fragment to be polymerized; according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain target video sequences; and determining a set formed by all the target video sequences as an evaluation set of the video to be evaluated. According to the method for obtaining the evaluation set of the video to be evaluated based on the video clip intercepted by the user, the evaluation set of the video to be evaluated can be determined without manual marking, compared with a manual marking mode, the time is saved, and the efficient obtaining of the evaluation set of the video is realized.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions described above in accordance with the embodiments of the invention may be generated, in whole or in part, when the computer program instructions described above are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the same element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device and electronic apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (7)
1. A method for determining a video evaluation set, the method comprising:
acquiring video clip capturing records of a video to be evaluated by a video platform user, wherein the video clip capturing records comprise the starting time and the ending time of each captured video clip;
calculating the intercepted times of each unit segment in different time periods in the video to be evaluated according to the starting time and the ending time of each intercepted video segment recorded by the video segment interception, and specifically comprises the following steps: placing the starting time and the ending time of each intercepted video segment on the same coordinate axis, taking the minimum starting time and the maximum ending time as a target time period, dividing the target time period into a plurality of unit segments, and accumulating the intercepted times of each unit segment in the target time period to obtain the intercepted times of each unit segment in different periods in the video to be evaluated;
selecting unit fragments with the interception times not lower than a preset threshold value to obtain each unit fragment to be polymerized;
according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain target video sequences;
determining a set formed by each target video sequence as an evaluation set of the video to be evaluated;
according to a preset clustering algorithm, aggregating the unit segments to be aggregated according to a time sequence to obtain each target video sequence, including:
sequencing the unit fragments to be aggregated according to the time sequence;
and determining each target video sequence formed by each sequenced unit segment to be aggregated according to the core radius and the density of a preset DBSCAN algorithm.
2. The method of claim 1, further comprising: and acquiring preset unit time, and logically dividing the video to be evaluated into a plurality of unit segments by taking the unit time as a dividing unit.
3. The method according to claim 1, wherein before the unit segments with the interception frequency not lower than the preset threshold are selected to obtain each unit segment to be aggregated, the method further comprises:
and calculating the average value of the interception times of the intercepted video of each unit segment, and taking the average value as the preset threshold value.
4. An apparatus for determining a video assessment set, the apparatus comprising:
the video clip intercepting record acquiring module is used for acquiring video clip intercepting records of a video platform user aiming at a video to be evaluated, wherein the video clip intercepting records comprise the starting time and the ending time of each intercepted video clip;
a unit segment capture frequency determining module, configured to calculate the capture frequency of each unit segment captured in different time periods in the video to be evaluated according to the start time and the end time of each captured video segment recorded by the video segment capture, and specifically includes: placing the starting time and the ending time of each intercepted video segment on the same coordinate axis, taking the minimum starting time and the maximum ending time as a target time period, dividing the target time period into a plurality of unit segments, and accumulating the intercepted times of each unit segment in the target time period to obtain the intercepted times of each unit segment in different periods in the video to be evaluated;
the unit segment to be polymerized determining module is used for selecting the unit segments with the interception frequency not lower than a preset threshold value to obtain each unit segment to be polymerized;
the target video sequence determining module is used for aggregating the unit segments to be aggregated according to a preset clustering algorithm and a time sequence to obtain each target video sequence;
the to-be-evaluated video evaluation set determining module is used for determining a set formed by each target video sequence as an evaluation set of the to-be-evaluated video;
the target video sequence determination module includes:
the unit segment to be aggregated sequencing submodule is used for sequencing each unit segment to be aggregated according to a time sequence;
and the target video sequence determining submodule is used for determining each target video sequence formed by each sequenced unit segment to be aggregated according to the core radius and the density of a preset DBSCAN algorithm.
5. The apparatus of claim 4, further comprising:
and the unit segment determining module is specifically configured to acquire a preset unit time, and logically divide the video to be evaluated into a plurality of unit segments by using the unit time as a dividing unit.
6. The apparatus of claim 4, further comprising:
and the preset threshold value determining module is used for calculating the average value of the interception times of the intercepted video of each unit segment and taking the average value as the preset threshold value.
7. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1 to 3 when executing a program stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811603478.8A CN109672936B (en) | 2018-12-26 | 2018-12-26 | Method and device for determining video evaluation set and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811603478.8A CN109672936B (en) | 2018-12-26 | 2018-12-26 | Method and device for determining video evaluation set and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109672936A CN109672936A (en) | 2019-04-23 |
| CN109672936B true CN109672936B (en) | 2021-10-26 |
Family
ID=66146781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811603478.8A Active CN109672936B (en) | 2018-12-26 | 2018-12-26 | Method and device for determining video evaluation set and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109672936B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110099308B (en) * | 2019-05-15 | 2022-06-10 | 浙江传媒学院 | Method for quickly segmenting and extracting hot interval of audio/video program |
| CN110139158B (en) * | 2019-06-21 | 2021-04-02 | 上海摩象网络科技有限公司 | Video and sub-video generation method and device, and electronic equipment |
| CN110381391B (en) * | 2019-07-11 | 2021-11-09 | 北京字节跳动网络技术有限公司 | Video fast slicing method and device and electronic equipment |
| CN111626123B (en) * | 2020-04-24 | 2024-08-20 | 平安国际智慧城市科技股份有限公司 | Video data processing method, device, computer equipment and storage medium |
| CN114040250B (en) * | 2022-01-10 | 2022-04-01 | 深圳市麦谷科技有限公司 | Video frame capturing method and device, electronic equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101345853A (en) * | 2008-08-07 | 2009-01-14 | 深圳市迅雷网络技术有限公司 | Method and system for acquiring video resource cutting time point |
| JP2012039284A (en) * | 2010-08-05 | 2012-02-23 | Mitsubishi Electric Corp | Moving image compression apparatus, moving image distribution system, moving image compression program, recording medium, and moving image compression method |
| CN104284216A (en) * | 2014-10-23 | 2015-01-14 | Tcl集团股份有限公司 | Method and system for generating video highlight clip |
| CN106503029A (en) * | 2015-09-08 | 2017-03-15 | 纳宝株式会社 | Extract and provide the method for excellent image, system and recording medium in video content |
| 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 |
| CN108924576A (en) * | 2018-07-10 | 2018-11-30 | 武汉斗鱼网络科技有限公司 | A kind of video labeling method, device, equipment and medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102487456B (en) * | 2009-11-30 | 2015-06-17 | 国际商业机器公司 | Method for providing visit rate of online video and device thereof |
| EP2775731A1 (en) * | 2013-03-05 | 2014-09-10 | British Telecommunications public limited company | Provision of video data |
| CN104410920B (en) * | 2014-12-31 | 2015-12-30 | 合一网络技术(北京)有限公司 | The method of wonderful mark is carried out based on video segmentation playback volume |
| CN106170104B (en) * | 2016-07-01 | 2019-03-08 | 广州华多网络科技有限公司 | The determination method, apparatus and server of video highlight segment |
| CN108830212B (en) * | 2018-06-12 | 2022-04-22 | 北京大学深圳研究生院 | Video behavior time axis detection method |
-
2018
- 2018-12-26 CN CN201811603478.8A patent/CN109672936B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101345853A (en) * | 2008-08-07 | 2009-01-14 | 深圳市迅雷网络技术有限公司 | Method and system for acquiring video resource cutting time point |
| JP2012039284A (en) * | 2010-08-05 | 2012-02-23 | Mitsubishi Electric Corp | Moving image compression apparatus, moving image distribution system, moving image compression program, recording medium, and moving image compression method |
| CN104284216A (en) * | 2014-10-23 | 2015-01-14 | Tcl集团股份有限公司 | Method and system for generating video highlight clip |
| CN106503029A (en) * | 2015-09-08 | 2017-03-15 | 纳宝株式会社 | Extract and provide the method for excellent image, system and recording medium in video content |
| 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 |
| CN108924576A (en) * | 2018-07-10 | 2018-11-30 | 武汉斗鱼网络科技有限公司 | A kind of video labeling method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109672936A (en) | 2019-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109672936B (en) | Method and device for determining video evaluation set and electronic equipment | |
| CN109685144B (en) | Method and device for evaluating video model and electronic equipment | |
| WO2017113677A1 (en) | User behavior data processing method and system | |
| CN112364202B (en) | Video recommendation method and device and electronic equipment | |
| CN109241084B (en) | Data query method, terminal equipment and medium | |
| CN110083475B (en) | Abnormal data detection method and device | |
| CN112052394B (en) | Professional content information recommendation method, system, terminal equipment and storage medium | |
| CN111225246B (en) | Video recommendation method and device and electronic equipment | |
| CN105183873A (en) | Malicious clicking behavior detection method and device | |
| WO2017156994A1 (en) | Multimedia resource quality assessment method and apparatus | |
| US10545972B2 (en) | Identification and elimination of non-essential statistics for query optimization | |
| CN110941738A (en) | Recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN109885656B (en) | Microblog forwarding prediction method and device based on quantification heat degree | |
| CN109033188A (en) | A kind of metadata acquisition method, apparatus, server and computer-readable medium | |
| WO2010015145A1 (en) | Method and system for filtering and monitoring program behaviors | |
| CN110909005B (en) | Model feature analysis method, device, equipment and medium | |
| CN110968802B (en) | Analysis method and analysis device for user characteristics and readable storage medium | |
| CN114785616A (en) | Data risk detection method and device, computer equipment and storage medium | |
| CN108900339B (en) | Method and device for measuring service quality and electronic equipment | |
| CN109410198B (en) | Time sequence action detection method, device and equipment | |
| CN114281648A (en) | Data acquisition method and device, electronic equipment and storage medium | |
| CN110996142B (en) | Video recall method and device, electronic equipment and storage medium | |
| CN113728655B (en) | Method for monitoring the use of at least one application executing in an operating system, corresponding device, computer program product and computer-readable carrier medium | |
| CN110097113B (en) | Method, device and system for monitoring working state of display information delivery system | |
| WO2020143641A1 (en) | Screen browsing data processing method and apparatus, medium and electronic 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 |