CN111526385A

CN111526385A - Video processing method and device, electronic equipment and storage medium

Info

Publication number: CN111526385A
Application number: CN202010359314.6A
Authority: CN
Inventors: 杨春炼; 邵明星; 朱朴
Original assignee: Beijing QIYI Century Science and Technology Co Ltd
Current assignee: Beijing QIYI Century Science and Technology Co Ltd
Priority date: 2020-04-29
Filing date: 2020-04-29
Publication date: 2020-08-11
Anticipated expiration: 2040-04-29
Also published as: CN111526385B

Abstract

The embodiment of the invention provides a video processing method, a video processing device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a current playing record of a video to be processed, wherein the current playing record comprises: the current playing time length of the video to be processed; determining the current playing progress of the video to be processed by utilizing the ratio of the current playing time length in the current playing record to the video time length of the video to be processed, which is acquired in advance; judging whether the current playing progress is the same as each historical playing progress or not, and updating the predetermined statistical times of each historical playing progress according to the judgment result to obtain the updated statistical times of each playing progress; and determining the video ending time point of the video to be processed based on the updated statistical times of the playing progresses and the size relationship between the updated statistical times of the playing progresses. The embodiment of the invention can further accurately determine the video ending time point.

Description

Video processing method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of video processing technologies, and in particular, to a video processing method and apparatus, an electronic device, and a storage medium.

Background

In the existing video recommendation method, if a user already watches a to-be-processed video, the to-be-processed video is continuously recommended to the same user, so that the user experience is poor. Therefore, for each video to be processed, marking processing needs to be performed at the end of the video to be processed, whether the user has viewed the video to be processed is judged according to the marked position, and whether the video to be processed needs to be recommended to the user is determined according to the judgment result. The video end time point may generally refer to a position of a corresponding to-be-processed video when a to-be-processed video trailer is reported.

In the prior art, in the process of marking the end of a video to be processed, a preset video end time point is usually marked, and the preset video end time point is usually set according to industry experience, for example, for a movie, 95% of the length of the movie is usually set as the video end time point of the movie, for a variety program, which may include a prize awarding link or other contents at the end, the last but one minute of the length of the variety program is usually set as the video end time point of the variety program. However, different movies have different film lengths, the time of the trailer report appearing in the videos to be processed is different, and for the variety programs including the award-awarding link, the award-awarding link in the trailer has different time lengths, so that the video ending time point of the movie and the video ending time point of the variety programs determined according to the industry experience are not accurate enough, and further the videos to be processed which are watched by the user are recommended or the videos to be processed which are not watched by the user are not recommended, so that the user experience is poor.

Disclosure of Invention

An object of the embodiments of the present invention is to provide a video processing method, an apparatus, an electronic device, and a storage medium, so as to further accurately determine a video end time point. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides a video processing method, where the method includes:

acquiring a current playing record of a video to be processed, wherein the current playing record comprises: the current playing time length of the video to be processed;

determining the current playing progress of the video to be processed by utilizing the ratio of the current playing time length in the current playing record to the video time length of the video to be processed, which is acquired in advance;

judging whether the current playing progress is the same as each historical playing progress or not, and updating the predetermined statistical times of each historical playing progress according to the judgment result to obtain the updated statistical times of each playing progress;

and determining the video ending time point of the video to be processed based on the updated statistical times of the playing progresses and the size relationship between the updated statistical times of the playing progresses.

Optionally, the step of determining a video end time point of the video to be processed based on the updated statistical times of the playing schedules and a size relationship between the updated statistical times of the playing schedules includes:

comparing the updated statistical times of the playing progresses;

and determining a difference value between the playing progress corresponding to the highest statistical frequency and a first preset numerical value as a video ending time point of the video to be processed, wherein the first preset numerical value is a numerical value which is greater than or equal to 0.

comparing the updated statistical times of the playing progresses;

extracting the statistical times corresponding to a plurality of playing durations which are smaller than a target playing duration, wherein the target playing duration is the playing duration corresponding to the highest statistical times;

performing moving average processing on each extracted statistical frequency to obtain a plurality of statistical frequencies subjected to moving average;

obtaining a curve by using the statistical times after the moving averages and the playing time corresponding to the statistical times after the moving averages are processed;

calculating the slope corresponding to each statistical frequency in the curve, and calculating the slope ratio between each slope and the previous slope;

and determining the playing progress corresponding to the slope with the maximum slope ratio as the video end time point.

Optionally, the step of determining a difference between the playing progress corresponding to the highest statistical number and a first preset value as the video end time point of the video to be processed includes:

according to the comparison result, determining the highest statistical frequency in the updated statistical frequencies of the playing progresses;

judging the size between the highest statistical frequency and a first preset threshold value;

if the maximum statistical time is greater than the first preset threshold, determining a difference value between the playing progress corresponding to the maximum statistical time and the first preset numerical value as the video ending time point, and executing the step of obtaining the current playing record of the video to be processed;

and if the highest statistical frequency is less than or equal to the first preset threshold, determining a preset video ending time point as the video ending time point.

Optionally, the step of determining whether the current playing progress is the same as each historical playing progress, and updating the predetermined statistical times of each historical playing progress according to the determination result to obtain the updated statistical times of each playing progress includes:

judging whether a historical playing progress identical to the current playing progress exists in each predetermined historical playing progress;

if the historical playing progress which is the same as the current playing progress exists, increasing a second preset value to the statistical frequency of the historical playing progress which is the same as the current playing progress to obtain a new statistical frequency, and updating the statistical frequency of the historical playing progress to the new statistical frequency;

and if the historical playing progress which is the same as the current playing progress does not exist, setting the counting times of the current playing progress as a preset initial value, and keeping the predetermined counting times of the historical playing progress unchanged.

Optionally, the step of obtaining the current playing record of the video to be processed includes:

acquiring a current playing record of the video to be processed, wherein the current playing record comprises: the playing time length of the played video when the video to be processed exits;

or, obtaining a current playing record of the video to be processed at preset intervals, where the current playing record includes: and acquiring the playing time corresponding to the current playing record moment.

Optionally, after the step of determining, if the highest statistical number is greater than the first preset threshold, a difference between the playing progress corresponding to the highest statistical number and the first preset value as the video end time point, the method further includes:

judging the size between the highest statistical frequency and a second preset threshold value;

and if the highest statistical frequency is greater than the second preset threshold value, stopping executing the step of acquiring the current playing record of the video to be processed.

In a second aspect, an embodiment of the present invention provides a video processing apparatus, where the apparatus includes:

the acquisition module is used for acquiring a current playing record of a video to be processed, wherein the current playing record comprises: the current playing time length of the video to be processed;

a first determining module, configured to determine a current playing progress of the video to be processed by using a ratio between a current playing time length in the current playing record and a video time length of the video to be processed, which is obtained in advance;

the updating module is used for judging whether the current playing progress is the same as each historical playing progress or not, updating the predetermined statistical times of each historical playing progress according to the judgment result and obtaining the updated statistical times of each playing progress;

and the second determining module is used for determining the video ending time point of the video to be processed based on the updated statistical times of the playing progresses and the size relationship between the updated statistical times of the playing progresses.

Optionally, the second determining module includes:

the first comparison submodule is used for comparing the updated statistical times of the playing progresses;

and the first determining submodule is used for determining a difference value between the playing progress corresponding to the highest statistical frequency and a first preset numerical value as a video ending time point of the video to be processed, wherein the first preset numerical value is a numerical value which is greater than or equal to 0.

Optionally, the second determining module includes:

the second comparison submodule is used for comparing the updated statistical times of the playing progresses;

the extraction submodule is used for extracting the statistical times corresponding to a plurality of playing durations which are smaller than the target playing duration, and the target playing duration is the playing duration corresponding to the highest statistical times;

the moving average processing submodule is used for carrying out moving average processing on the extracted statistical times to obtain a plurality of statistical times after moving average;

the curve obtaining submodule is used for obtaining a curve by utilizing the statistical times of the plurality of moving means and the playing time length corresponding to the statistical times of the moving means;

the calculation submodule is used for calculating the slope corresponding to each statistical frequency in the curve and calculating the slope ratio between each slope and the previous slope;

and the second determining submodule is used for determining the playing progress corresponding to the slope with the maximum slope ratio as the video end time point.

Optionally, the first determining sub-module includes:

a first determining unit, configured to determine, according to the comparison result, a highest statistical number among the updated statistical numbers of each playing progress;

the judging unit is used for judging the size between the highest statistical frequency and a first preset threshold value;

a processing unit, configured to determine, if the highest statistical number is greater than the first preset threshold, a difference between a playing progress corresponding to the highest statistical number and the first preset value as the video end time point, and trigger the obtaining module to perform the step of obtaining the current playing record of the video to be processed;

a second determining unit, configured to determine a preset video end time point as the video end time point if the highest statistical number is less than or equal to the first preset threshold.

Optionally, the update module includes:

the judging submodule is used for judging whether a historical playing progress identical to the current playing progress exists in each predetermined historical playing progress;

the first processing submodule is used for increasing the statistical times of the historical playing progress which is the same as the current playing progress by a second preset value to obtain new statistical times and updating the statistical times of the historical playing progress to the new statistical times if the historical playing progress which is the same as the current playing progress exists;

and the second processing submodule is used for setting the counting times of the current playing progress to be a preset initial value and keeping the predetermined counting times of the historical playing progress unchanged if the historical playing progress which is the same as the current playing progress does not exist.

Optionally, the obtaining module is specifically configured to:

Optionally, the apparatus further comprises:

the judging module is used for judging the size between the highest statistical frequency and a second preset threshold value;

and the first triggering module is used for triggering the acquisition module to stop executing the step of acquiring the current playing record of the video to be processed if the highest statistical frequency is greater than the second preset threshold value.

In a third aspect, an embodiment of the present invention further provides 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;

and the processor is used for realizing the steps of any video processing method when executing the program stored in the memory.

In a fourth aspect, the present invention also provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of any of the above-mentioned video processing methods.

In a fifth aspect, embodiments of the present invention further provide a computer program product containing instructions, which when run on a computer, cause the computer to perform the steps of any of the video processing methods described above.

The embodiment of the invention has the following beneficial effects:

according to the video processing method, the video processing device, the electronic equipment and the storage medium, the current playing progress of the video to be processed is determined by acquiring the current playing record of the video to be processed and utilizing the current playing time length in the current playing record and the ratio of the video time length; judging whether the current playing progress is the same as each historical playing progress or not, updating the predetermined statistical times of each playing progress according to the judgment result to obtain the updated statistical times of each playing progress, and determining the video ending time point of the video to be processed based on the updated statistical times of each playing progress and the size relationship between the updated statistical times of each playing progress. According to the embodiment of the invention, the video ending time point can be determined according to the actual situation that the user actually views the video to be processed and the current playing progress of the video to be processed, so that the obtained video ending time point is closer to the actual viewing situation, namely, the accuracy of the video ending time point can be improved, and the user experience can be improved.

Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.

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, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flowchart of a video processing method according to an embodiment of the present invention;

fig. 2 is a schematic flowchart of step S140 in the video processing method according to the embodiment of the present invention;

fig. 3a is a schematic diagram of a statistical result of the playing progress and the statistical times of the movie according to the embodiment of the present invention;

fig. 3b is a schematic diagram of a statistical result of the playing progress and the statistical frequency of the heddle art program according to the embodiment of the present invention;

fig. 3c is another schematic diagram of a statistical result of the playing progress and the statistical frequency of the variety program according to the embodiment of the present invention;

fig. 4 is a schematic flowchart of S142 in the video processing method according to the embodiment of the present invention;

fig. 5 is another schematic flow chart of S142 in the video processing method according to the embodiment of the present invention;

fig. 6 is a schematic flowchart of S130 in the video processing method according to the embodiment of the present invention;

fig. 7 is a schematic flowchart of S120 in the video processing method according to the embodiment of the present invention;

fig. 8 is a schematic structural diagram of a video processing apparatus according to an embodiment of the present invention;

fig. 9 is a schematic structural diagram of a second determining module in the video processing apparatus according to the embodiment of the present invention;

fig. 10 is a schematic structural diagram of a first determining sub-module in the video processing apparatus according to the embodiment of the present invention;

fig. 11 is a schematic structural diagram of a first determining sub-module in the video processing apparatus according to the embodiment of the present invention;

fig. 12 is a schematic structural diagram of an update module in the video processing apparatus according to the embodiment of the present invention;

fig. 13 is a schematic structural diagram of a first determining module in the video processing apparatus according to the embodiment of the present invention;

fig. 14 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

As shown in fig. 1, an embodiment of the present invention provides a video processing method, which may include:

s110, acquiring a current playing record of the video to be processed, wherein the current playing record comprises: the current playing time of the video to be processed.

And S120, determining the current playing progress of the video to be processed by utilizing the ratio of the current playing time length in the current playing record to the video time length of the video to be processed, which is acquired in advance.

S130, judging whether the current playing progress is the same as each historical playing progress, and updating the predetermined statistical times of each historical playing progress according to the judgment result to obtain the updated statistical times of each playing progress.

And S140, determining the video ending time point of the video to be processed based on the updated statistical times of the playing progresses and the size relationship between the updated statistical times of the playing progresses.

The video processing method provided by the embodiment of the invention determines the current playing progress of the video to be processed by obtaining the current playing record of the video to be processed and utilizing the ratio of the current playing duration in the current playing record to the video duration, judges whether the current playing progress is the same as each historical playing progress or not, updates the predetermined statistical times of each playing progress according to the judgment result to obtain the updated statistical times of each playing progress, and determines the video ending time point of the video to be processed based on the updated statistical times of each playing progress and the size relationship between the updated statistical times of each playing progress. According to the embodiment of the invention, the video ending time point can be determined according to the actual situation that the user actually views the video to be processed and the current playing progress of the video to be processed, so that the obtained video ending time point is closer to the actual viewing situation, namely, the accuracy of the video ending time point can be improved, and the user experience can be improved.

Further, in step S110 of the flow of the embodiment shown in fig. 1, the video to be processed may include, but is not limited to: movies, short videos, or continuous videos, etc., where continuous videos may include, but are not limited to: a series, a variety program, or an animation, etc.

When the playing record of the video to be processed is obtained, the playing record corresponding to the video to be processed at each obtaining moment can be obtained in real time, because only one user may watch the video to be processed at the obtaining moment of the current playing record, under the condition, the obtained current playing record can be one, and if a plurality of users watch the video to be processed at the same time at the moment of obtaining the current playing record of the video to be processed, the current playing record can be a plurality of records.

The obtained current playing record may include the current playing time of the video to be processed, that is, the playing time corresponding to the obtaining time of the current playing record is obtained, for example, at the current obtaining time, one hour and twenty minutes when one user watches the video to be processed, and the one hour and twenty minutes are the current playing time of the obtained video to be processed.

In step S120 of the flow in the embodiment shown in fig. 1, the video duration of the video to be processed may be obtained in advance, for example, before obtaining the current playing record of the video to be processed, the video duration may be obtained in a public database, where information such as a video name and a video duration of a video shown in a video APP (Application program) is generally stored in the public database.

Since the video ending time point can be the proportion of the video ending point in the video duration, the current playing duration can be determined as the current playing progress of the video to be processed, and the current playing progress can be represented by percentage.

It should be noted that, in order to avoid the large amount of data at the time point of the end of the video, a plurality of playing schedules that need to be counted may be preset, for example, 20 playing schedules in total may be preset, and after the current playing schedule is obtained, it may be determined whether the current playing schedule is the preset plurality of playing schedules that need to be counted, and if not, the current playing schedule is deleted, that is, the number of times of counting of each predetermined playing schedule is not updated by using the current playing schedule.

In addition, after the video to be processed is published on the video APP, whether the publishing duration of the video to be processed on the video APP is greater than or equal to the video duration of the video to be processed can be judged in advance, and when the publishing duration is greater than or equal to the video duration, the video to be processed is completely published, and then the current playing record of the video to be processed is obtained; when the release duration is shorter than the video duration, it is indicated that the video to be processed is not completely released, and the video ending time point calculated by using the current play record of the video to be processed is not accurate enough, so that the current play record of the video to be processed can not be obtained.

In step S130 of the flow shown in fig. 1, since the current playing record of the video to be processed is obtained in real time, before the current playing record is obtained, the playing records of the obtaining times before the current obtaining time are obtained, and the statistical times of different playing schedules are determined in real time according to the playing records. Therefore, after the current playing progress of the video to be processed is determined, whether the current playing progress is the same as each historical playing progress can be determined, the statistical times of each determined playing progress are updated according to the determination result, and the updated statistical times of each playing progress are obtained.

In step S140 of the flow of the embodiment shown in fig. 1, after the updated statistical times of the playing schedules are obtained, the video end time point of the video to be processed may be determined based on the updated statistical times of the playing schedules and the size relationship between the updated statistical times of the playing schedules. The updated statistical times of the playing schedules represent the times of the playing schedules of the video to be processed from the initial acquiring time of the video to be processed to the current acquiring time, so that the ending time point of the video can be obtained by comparing different statistical times and according to the comparison result of the different statistical times.

The initial acquisition time here may refer to a time of first acquiring a play record of the video to be processed, and the initial acquisition time may be set in advance, for example, the initial acquisition time may be set in advance as a time of publishing the video to be processed, and if the video to be processed is published at twelve o 'clock at midnight, the initial acquisition time may be set at twelve o' clock at midnight; the initial acquisition time may also be set in advance as a time spaced by a preset time after the time at which the to-be-processed video is released, and if the to-be-processed video is released at twelve o 'clock in the midnight, the initial acquisition time may be set as eight o' clock in the next morning.

As an optional implementation manner of the embodiment of the present invention, as shown in fig. 2, step S140 of the flow in the embodiment shown in fig. 1 may include:

and S141, comparing the updated statistical times of the playing progresses.

Referring to fig. 3a, fig. 3b and fig. 3c, the first column is the playing progress, the second column is the statistical times of each playing progress, and after the updated statistical times of each playing progress are obtained, the sizes of the statistical times can be compared. The specific comparison method can be as follows: and traversing the updated statistical times of the playing schedules in sequence, comparing the statistical times of two updated playing schedules, selecting a larger value between the two updated playing schedules, temporarily determining the larger value as a maximum value, then comparing the larger value with the statistical times of a third updated playing schedule, temporarily determining the larger value between the two updated playing schedules as a new maximum value, and so on until determining the maximum value of all the statistical times, and determining the maximum value as the highest statistical time of the statistical times of the updated playing schedules.

And S142, determining the difference between the playing progress corresponding to the highest statistical frequency and a first preset value as the video ending time point of the video to be processed.

Since the highest statistical frequency indicates that the frequency of viewing the playing progress corresponding to the highest statistical frequency by the user is the largest, after the highest statistical frequency is obtained, a difference between the playing progress corresponding to the highest statistical frequency and a first preset value may be determined as a video end time point of the video to be processed, and the first preset value may be a value greater than or equal to 0. As shown in fig. 3a, the playing progress corresponding to the highest statistical number 43332 is 0.93, and a difference between 0.93 and a first preset value may be determined as the video end time point. In addition, if the maximum number of times is multiple, a difference between one of the playing schedules with the largest value and a first preset value in the playing schedules corresponding to the multiple maximum numbers of times may be determined as the video end time point.

The first preset value may be a preset value, for example, 0, or a value greater than 0. When the first preset value is 0, the video ending time point is the playing progress corresponding to the highest statistical number, for example, the playing progress corresponding to the highest statistical number 43332 is 0.93, and the video ending time point is 0.93.

Or setting the first preset value as a value greater than 0, and after the video end time point is obtained, performing an AB test on the video by using the existing video recommendation method, where the specific test process is as follows: selecting two different user groups to watch the video to be processed, clicking to quit playing after the user watches the video to be processed, namely after seeing the report of the trailer, and acquiring current playing records of each user, wherein each current playing record comprises the playing time length when the user quits playing, the finally obtained playing progress is 0.93, and the real ending time point of the video to be processed is 0.92. The inventor finds, through analysis, that there is an error between the video end time point obtained through testing and the real end time point because the user usually clicks to quit playing after seeing the report of the trailer, so that 0.92 can be obtained by subtracting 0.01 from 0.93 in consideration of the reaction time of the user and the network delay, and the 0.92 is determined as the video end time point. Therefore, the first preset value may be set to 0.01. It should be noted that the real video end time point may refer to a time point when a trailer appears in the video.

In the embodiment of the invention, the difference value between the highest statistical frequency and the first preset value is determined as the video ending time point of the video to be processed by considering the reaction time and the network delay of the user when watching the video to be processed, so that the video ending time point determined according to the method is more accurate.

As an optional implementation manner of the embodiment of the present invention, as shown in fig. 4, step S140 of the embodiment flow shown in fig. 1 may include:

and S143, comparing the updated statistical times of the playing progresses.

Referring to step S141 in the embodiment shown in fig. 2, the updated statistics times of the playing schedules are compared, and details of the embodiment of the present invention are not repeated herein.

S144, extracting the statistical times corresponding to the multiple playing time lengths smaller than the target playing time length.

In the embodiment of the present invention, the target playing duration may be the playing duration corresponding to the highest statistical number, and after comparing the updated statistical numbers of the playing schedules in step S143, the highest statistical number may be obtained, so as to obtain the playing schedule corresponding to the highest statistical number, thereby obtaining the target playing duration. Then, the statistical frequency corresponding to each playing time length in the plurality of playing time lengths smaller than the target playing time length can be extracted, that is, the plurality of playing time lengths smaller than the target playing time length are determined, the number of the plurality of playing time lengths can be a preset number, and then the statistical frequency corresponding to each playing time length is obtained by using the playing progress corresponding to each playing time length in the plurality of playing time lengths. For example, the target playback time period is 85 minutes, and the plurality of playback time periods may be one playback time period taken every one second between 84 and 85 minutes, that is, 84 minutes 01 seconds, 84 minutes 02 seconds, … … 84 minutes 59 seconds.

S145, performing moving average processing on each extracted statistical frequency to obtain a plurality of statistical frequencies after moving average.

The specific process of performing moving average processing on each extracted statistical number may be: the plurality of statistical times may be sorted according to the size of the playing time length corresponding to each statistical time, wherein for a first statistical time, an average value between the statistical time and a second statistical time may be used as the statistical time processed by a first moving average, and for a last statistical time, an average value between the statistical time and a last-but-second statistical time may be used as the statistical time processed by a last moving average. For the other statistical times except the first statistical time and the last statistical time, an average value between the statistical times, the statistical times located one bit before the statistical times, and the statistical times located one bit after the statistical times may be used as the statistical times after the moving average value corresponding to the statistical times. For example, for the second statistical number, an average value among the first statistical number, the second statistical number, and the third statistical number may be used as the second moving average statistical number.

And S146, obtaining a curve by utilizing the plurality of statistical times after moving the average value and the playing time length corresponding to the statistical times after moving the average value.

A coordinate system may be created, where the abscissa represents the playing duration, the ordinate represents the counted number of times after moving the mean, a plurality of coordinate points are marked in the coordinate system, the number of the coordinate points is the number of the extracted plurality of playing durations smaller than the target playing duration, the coordinate position of each coordinate point may be the playing duration, and the counted number of times after moving the mean corresponding to the playing duration. And then connecting the plurality of coordinate points by using the smooth curve to obtain a curve.

And S147, calculating the slope corresponding to each statistical frequency in the curve, and calculating the slope ratio between each slope and the previous slope.

The slope corresponding to each coordinate point in the coordinate system can be calculated, that is, the slope corresponding to each statistical frequency in the curve can be calculated. After obtaining the slope corresponding to each statistical number, for the other slopes except the first slope among all slopes, a ratio between the slope and the previous slope may be calculated as a slope ratio.

And S148, determining the playing progress corresponding to the slope with the maximum slope ratio as the video end time point.

The maximum slope ratio indicates that the change of the statistical times corresponding to the slope is larger than the change of the previous statistical times, so that the playing times corresponding to the slope with the maximum slope ratio can be determined as the video end time point. In addition, since the slope ratio is a ratio of each slope to its previous slope, the slope having the largest slope ratio may be the next slope after the slope ratio is calculated, or the previous slope.

As an optional implementation manner of the embodiment of the present invention, as shown in fig. 5, step S142 of the flow in the embodiment shown in fig. 2 may include:

s1421, according to the comparison result, determining the highest statistical frequency among the updated statistical frequencies of the playing schedules.

After comparing the updated statistical times of the playing schedules in the flow S141 of the embodiment shown in fig. 2, the maximum value finally obtained in the comparison result may be determined as the highest statistical time according to the comparison result. By comparison, 43332 is the highest statistical number, as shown in FIG. 3 a.

S1422, determine the size between the highest statistical number and the first preset threshold.

When statistical analysis is performed on some data and the method represented by the data is optimized by using the analysis result, under the condition that the counted data amount is small, the deviation between the final calculation result and the actual result is likely to be large, for example, when the highest statistical frequency is small, that is, the counted data amount (in the embodiment of the present invention, the current playing record) is small, the calculated video ending time point may not be accurate enough according to the playing duration in the playing record acquired at each acquisition time, therefore, a first preset threshold may be preset, and after the highest statistical frequency is obtained, the size between the highest statistical frequency and the first preset threshold is judged, and whether the video ending time point is determined according to the highest statistical frequency is determined according to the judgment result.

The first preset threshold may be determined by performing linear regression analysis on the counted number of times of each playing progress and a real video ending time point, specifically, comparing the playing progress corresponding to the calculated highest number of times of statistics with the real ending time point, and if the playing progress is the real video ending time point, setting the highest number of times of statistics as the first preset threshold. Of course, the first preset threshold value may be determined by other experiments or experience.

S1423, if the highest statistical frequency is greater than the first preset threshold, determining a difference between the playing progress corresponding to the highest statistical frequency and the first preset value as a video end time point, and executing step S110 in the flow of the embodiment shown in fig. 1.

If the highest statistical time is greater than the first preset value, it indicates that the accuracy of the highest statistical time is high, and in order to meet the real-time performance in the video recommendation process, the highest statistical time may be used as a basis for calculating the video ending time point, that is, the video ending time point may be determined by using the difference between the playing progress corresponding to the highest statistical time and the first preset value.

As shown in fig. 3a, for the movie "sad adverse current river", the highest statistical frequency is 43332, and the corresponding playing progress is 0.93, then, when the first preset value is 0, the video ending time point is 0.93. As shown in fig. 3b, for the fantasy food 20181117, the highest statistical number is 2971, and the corresponding playing speed is 0.97, and when the first preset value is 0, the video ending time point is 0.97. As shown in fig. 3c, for the "20181116 of chinese music bulletin board" of the general skill, the highest statistical frequency is 589, and the corresponding playing progress is 0.93, then, when the first preset value is 0, the video end time point is 0.93, and after watching the general skill program, it is found that although 0.93 is not the time point of the film trailer of the general skill program, from 0.93, the substantial content already does not exist in the general skill program, so the user quits playing.

Although the accuracy of the calculated video end time point is high in this case, there may be other situations that result in a calculation error of the video end time point, for example, when a video is published at twelve o 'clock at midnight, and some users may watch the video at twelve o' clock at midnight, but the watching crowd at this stage may quit playing as soon as possible when the video is not ended, that is, when the trailer report of the video to be processed is not seen, so that the playing record of this time period is obtained, and the video end time point calculated according to the playing duration in the playing record may not be accurate enough, so that it is still necessary to continue to obtain the current playing record of the video to be processed and recalculate the video end point.

S1424, if the highest statistical number is less than or equal to the first preset threshold, determining the preset video ending time point as a video ending time point.

If the highest statistical number is less than or equal to the first preset threshold, the preset video end time point may be determined as the video end time point. For example, 0.95 of the movie film length may be determined as the video end time point of the movie, and the second last minute of the anagraph film length may be determined as the video end time point of the anagraph program.

In the embodiment of the invention, by judging the size between the highest statistical time and the first preset threshold, if the highest statistical time is greater than the first preset threshold, the difference between the playing progress corresponding to the highest statistical time and the first preset numerical value is determined as the video ending time point, so that the condition that the accuracy of the video ending time point obtained by calculation is poor within a period of time after the video is published can be avoided, and the calculation accuracy of the video ending time point can be further improved.

In addition, in order to avoid that the accuracy of the calculated video is considered to be low because the playing time difference in each acquired playing record is large in a period of time after the video is published, the time at which the to-be-processed video is published and the preset time interval is taken as the initial acquisition time for acquiring the playing record of the to-be-processed video, for example, when the to-be-processed video is published at twelve o 'clock in midnight, eight o' clock in the morning of the next day can be taken as the initial acquisition time.

As an optional implementation manner of the embodiment of the present invention, as shown in fig. 6, step S130 of the flow in the embodiment shown in fig. 1 may include:

s131, determining whether there is a historical play progress identical to the current play progress from each of the predetermined historical play progresses.

The predetermined playing schedules can be traversed in sequence, whether each playing schedule is the same as the current playing schedule or not is judged, if one playing schedule in the predetermined playing schedules is the same as the current playing schedule, the playing schedule which is the same as the current playing schedule exists in each playing schedule, and if all the playing schedules are different from the current playing schedule, the playing schedule which is the same as the current playing schedule does not exist.

And S132, if the historical playing progress which is the same as the current playing progress exists, increasing the statistical frequency of the historical playing progress which is the same as the current playing progress by a second preset value to obtain a new statistical frequency, and updating the statistical frequency of the historical playing progress to the new statistical frequency.

And if the historical playing progress which is the same as the current playing progress exists, increasing the statistical times of the historical playing progress which is the same as the current playing progress by a second preset value to obtain new statistical times, and updating the statistical times of the playing progress to the new statistical times. The second predetermined value may be 1. Whether the historical playing schedules are the same as the current playing schedule or not can be sequentially judged, and the judgment is stopped when the historical playing schedule which is the same as the current playing schedule exists.

And keeping the statistical times of the historical playing progress different from the current playing progress in the predetermined playing progresses unchanged.

S133, if there is no historical playing progress that is the same as the current playing progress, setting the statistical number of the current playing progress to a preset initial value, and keeping the predetermined statistical number of each historical playing progress unchanged.

If there is no historical playing progress which is the same as the current playing progress, it indicates that the current playing progress appears for the first time in the whole counting process, so the counting number of the current playing progress can be set as an initial number, the initial number can be 1, and the predetermined counting number of each historical playing progress is kept unchanged. The process of updating the predetermined statistical number of the historical playing schedules is simplified by adopting the flow steps S131 to S133.

As an optional implementation manner of the embodiment of the present invention, step S110 of the flow in the embodiment shown in fig. 1 may include:

acquiring a current playing record of a video to be processed, wherein the current playing record comprises: and the playing time length of the played video when the video to be processed exits.

When the user watches the video to be processed, the playing is usually quitted when the user watches the video to be processed, so that the current playing record of the user when the user quits playing the video to be processed can be obtained, and therefore, the current playing record comprises: and the playing time length of the played video when the video to be processed exits. For example, when the user exits play when viewing one hour and twenty minutes, then one hour and twenty minutes are included in the current play record. It should be noted that, the current playing record of the video to be processed may be obtained through the message queue.

Or, acquiring a current playing record of the video to be processed at preset intervals, wherein the current playing record comprises: and acquiring the playing time corresponding to the current playing record moment.

The interval time may be preset, and may be set empirically, for example, the interval time may be set to 5s, that is, every 5s, a current playing record of the video to be processed is obtained, where the current playing record includes: the playing duration corresponding to the current playing record time is obtained, for example, the current playing record is obtained at the 5 th time in the video to be processed, the playing duration in the current playing record is 5s, then the current playing record is obtained at the 10 th time in the video, the playing duration in the current playing record is 10s, and the like.

By adopting the method provided by the embodiment of the invention to obtain the current playing record of the video to be processed, the video APP operator can conveniently analyze whether the user continuously watches the video to be processed according to the data.

It should be noted that the current play record may further include an identifier of the to-be-processed video, where the identifier may include a video name of the to-be-processed video, and when the to-be-processed video is a continuous video, the identifier may include a video name and an episode number. When the play record comprises the video name and the episode number, after the current play record is obtained, the video ending time point of the video to be processed corresponding to the video name and the episode number can be calculated according to the play duration in the current play record with the same video name and episode number, so that the accuracy of the video ending time point of the video to be processed with different episode numbers can be further improved.

As an optional implementation manner of the embodiment of the present invention, as shown in fig. 7, after step S1423 of the flow in the embodiment shown in fig. 5, the video processing method provided in the embodiment of the present invention may further include:

s1425, determine the size between the highest statistical number and a second preset threshold.

The second preset threshold value can be determined according to experiments or experiences, the second preset threshold value can be set to be a larger value, and when the highest statistical frequency is within a value range smaller than the second preset threshold value, the corresponding playing progress is stable, so that whether the playing record of the video to be processed needs to be continuously obtained or not can be judged by judging the size between the highest statistical frequency and the second preset threshold value.

S1426, if the highest statistical number is greater than the second preset threshold, the step S110 of the embodiment shown in fig. 1 is stopped.

If the highest statistical number is greater than the second preset threshold, it indicates that the playing progress corresponding to the highest statistical number is relatively stable, the playing record of the video to be processed is continuously obtained, and the video ending time point determined based on the playing duration in the playing record is the same as the video ending time point corresponding to the highest statistical number greater than the second preset threshold, so that the playing record of the video to be processed does not need to be obtained, and then the execution of step S110 in the flow of the embodiment shown in fig. 1 is stopped.

If the highest statistical number is less than or equal to the second preset threshold, the step S110 of the embodiment shown in fig. 1 is continuously executed.

Corresponding to the above method embodiment, the embodiment of the present invention also provides a corresponding device embodiment.

An embodiment of the present invention provides a specific embodiment of a video processing apparatus, which corresponds to the flow shown in fig. 1, with reference to fig. 8, fig. 8 is a schematic structural diagram of a video processing apparatus according to an embodiment of the present invention, and the video processing apparatus may include:

an obtaining module 210, configured to obtain a current playing record of a video to be processed, where the current playing record includes: the current playing time of the video to be processed.

The first determining module 220 is configured to determine a current playing progress of the video to be processed by using a ratio between a current playing time length in the current playing record and a video time length of the video to be processed, which is obtained in advance.

The updating module 230 is configured to determine whether the current playing schedule is the same as each historical playing schedule, and update the predetermined statistical times of each historical playing schedule according to the determination result to obtain the updated statistical times of each playing schedule.

The second determining module 240 is configured to determine a video end time point of the video to be processed based on the updated statistical times of the playing schedules and a size relationship between the updated statistical times of the playing schedules.

The video processing device provided by the embodiment of the invention determines the current playing progress of the video to be processed by acquiring the current playing record of the video to be processed and utilizing the ratio of the current playing duration in the current playing record to the video duration, judges whether the current playing progress is the same as each historical playing progress or not, updates the predetermined statistical times of each playing progress according to the judgment result to obtain the updated statistical times of each playing progress, and determines the video ending time point of the video to be processed based on the updated statistical times of each playing progress and the size relationship between the updated statistical times of each playing progress. According to the embodiment of the invention, the video ending time point can be determined according to the actual situation that the user actually views the video to be processed and the current playing progress of the video to be processed, so that the obtained video ending time point is closer to the actual viewing situation, namely, the accuracy of the video ending time point can be improved, and the user experience can be improved.

As an alternative embodiment of the present invention, as shown in fig. 9, the second determining module 240 may include:

the first comparing sub-module 241 is configured to compare the updated statistics times of the playing schedules.

The first determining submodule 242 is configured to determine, as a video end time point of the video to be processed, a difference between the playing progress corresponding to the highest statistical number and a first preset value, where the first preset value is a value greater than or equal to 0.

As an alternative embodiment of the present invention, as shown in fig. 10, the second determining module 240 may include:

a second comparison submodule 243, configured to compare the updated statistics times of the playing schedules;

an extracting submodule 244, configured to extract a statistical number of times corresponding to a plurality of playing durations that are smaller than a target playing duration, where the target playing duration is a playing duration corresponding to a highest statistical number of times;

a moving average processing submodule 245, configured to perform moving average processing on the extracted statistical times to obtain a plurality of statistical times after moving average;

a curve obtaining submodule 246, configured to obtain a curve by using the plurality of statistical times after moving the average and the playing time length corresponding to the statistical times after moving the average;

the calculation submodule 247 is configured to calculate slopes corresponding to the statistical times in the curve, and calculate a slope ratio between each slope and a previous slope;

the second determining submodule 248 is configured to determine the playing progress corresponding to the slope with the largest slope ratio as the video end time point.

As an alternative embodiment of the present invention, as shown in fig. 11, the first determining sub-module 242 may include:

a first determining unit 2421, configured to determine the highest statistical number among the updated statistical numbers of the respective playing schedules according to the comparison result.

A judging unit 2422, configured to judge a size between the highest statistical number and a first preset threshold.

The processing unit 2423 is configured to determine, if the highest statistical number is greater than a first preset threshold, a difference between the playing progress corresponding to the highest statistical number and a first preset value as a video end time point, and trigger the obtaining module to perform the step of obtaining the current playing record of the video to be processed.

A second determining unit 2424 for determining a preset video end time point as a video end time point if the highest number of statistics is less than or equal to the first preset threshold.

As an alternative embodiment of the present invention, as shown in fig. 12, the update module 230 may include:

the judging submodule 231 is configured to judge whether there is a historical playing progress that is the same as the current playing progress from the predetermined historical playing progresses.

The first processing sub-module 232 is configured to, if there is a historical playing progress that is the same as the current playing progress, increase the statistical number of the historical playing progress that is the same as the current playing progress by a second preset value to obtain a new statistical number, and update the statistical number of the historical playing progress to the new statistical number.

The second processing sub-module 233 is configured to set the statistical number of the current play progress to a preset initial value and keep the predetermined statistical number of each historical play progress unchanged if there is no historical play progress that is the same as the current play progress.

As an optional implementation manner of the present invention, the obtaining module 210 is specifically configured to:

acquiring a current playing record of a video to be processed, wherein the current playing record comprises: and the playing time length when the video to be processed exits.

As an optional implementation manner of the present invention, as shown in fig. 13, the apparatus provided in the embodiment of the present invention may further include:

a determining module 2425, configured to determine a size between the highest statistical number and a second preset threshold.

A first triggering module 2426, configured to, if the highest statistical number is greater than a second preset threshold, stop executing the step of acquiring the current playing record of the video to be processed by the trigger acquiring module 210.

A second triggering module 2427, configured to trigger the obtaining module 210 to perform the step of obtaining the current playing record of the to-be-processed video if the highest statistical number is smaller than or equal to a second preset threshold.

An embodiment of the present invention further provides an electronic device, as shown in fig. 14, including a processor 301, a communication interface 302, a memory 303, and a communication bus 304, where the processor 301, the communication interface 302, and the memory 303 complete mutual communication through the communication bus 304.

A memory 303 for storing a computer program.

The processor 301, when executing the program stored in the memory 303, implements the following steps:

acquiring a current playing record of a video to be processed, wherein the current playing record comprises: the current playing time of the video to be processed.

And determining the current playing progress of the video to be processed by utilizing the ratio of the current playing time length in the current playing record to the video time length of the video to be processed, which is acquired in advance.

And judging whether the current playing progress is the same as each historical playing progress or not, and updating the predetermined statistical times of each historical playing progress according to the judgment result to obtain the updated statistical times of each playing progress.

According to the electronic device provided by the embodiment of the invention, the current playing progress of the video to be processed is determined by obtaining the current playing record of the video to be processed and utilizing the ratio of the current playing duration in the current playing record to the video duration, whether the current playing progress is the same as each historical playing progress is judged, the predetermined statistical times of each playing progress are updated according to the judgment result, the updated statistical times of each playing progress are obtained, and the video ending time point of the video to be processed is determined based on the updated statistical times of each playing progress and the size relationship between the updated statistical times of each playing progress. According to the embodiment of the invention, the video ending time point can be determined according to the actual situation that the user actually views the video to be processed and the current playing progress of the video to be processed, so that the obtained video ending time point is closer to the actual viewing situation, namely, the accuracy of the video ending time point can be improved, and the user experience can be improved.

The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 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 is used for communication between the electronic equipment and other equipment.

The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component.

In yet another embodiment of the present invention, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of any of the above-mentioned video processing methods.

In a further embodiment provided by the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the steps of any of the video processing methods of the above embodiments.

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. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. 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 incorporates 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 identical elements in a process, method, article, or apparatus that comprises the 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 apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

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

1. A method of video processing, the method comprising:

2. The method according to claim 1, wherein the step of determining the video end time point of the video to be processed based on the updated statistical times of the playing schedules and the size relationship between the updated statistical times of the playing schedules comprises:

comparing the updated statistical times of the playing progresses;

3. The method according to claim 1, wherein the step of determining the video end time point of the video to be processed based on the updated statistical times of the playing schedules and the size relationship between the updated statistical times of the playing schedules comprises:

comparing the updated statistical times of the playing progresses;

4. The method according to claim 2, wherein the step of determining the difference between the playing progress corresponding to the highest statistical number and a first preset value as the video end time point of the video to be processed comprises:

5. The method according to any one of claims 1 to 4, wherein the step of determining whether the current playing progress is the same as each historical playing progress, and updating the predetermined statistical times of each historical playing progress according to the determination result to obtain the updated statistical times of each playing progress comprises:

6. The method according to any one of claims 1 to 4, wherein the step of obtaining the current playing record of the video to be processed comprises:

7. The method according to claim 4, wherein after the step of determining the difference between the playing progress corresponding to the highest statistical number and the first preset value as the video end time point if the highest statistical number is greater than the first preset threshold, the method further comprises:

8. A video processing apparatus, characterized in that the apparatus comprises:

9. 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 7 when executing a program stored in the memory.

10. A computer storage medium, characterized in that a computer program is stored in the computer readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of the claims 1-7.