CN110392253B

CN110392253B - Video quality evaluation method, device, equipment and storage medium

Info

Publication number: CN110392253B
Application number: CN201910557314.4A
Authority: CN
Inventors: 范佳; 赵冲翔; 孙斌; 叶田田; 周莹
Original assignee: Beijing QIYI Century Science and Technology Co Ltd
Current assignee: Beijing QIYI Century Science and Technology Co Ltd
Priority date: 2019-06-25
Filing date: 2019-06-25
Publication date: 2021-07-16
Anticipated expiration: 2039-06-25
Also published as: CN110392253A

Abstract

The application provides a video quality evaluation method and device, terminal equipment and a storage medium. In the application, when the accumulated playing quality of the video is determined, in addition to the score corresponding to the playing frequency index of the video, the score corresponding to the number index of the playing people of the video and the score corresponding to the playing quality index of the video are also used at the same time, the number index of the playing people of the video can at least reflect the total number of users playing the video in the historical process and the like, and the playing quality index of the video can at least reflect the total playing duration of the video in the historical process, the number of times that the video is completely played and the like. Therefore, the accumulated playing quality of the video can be more accurately determined by combining multiple dimensions such as the playing times of the video, the number of users playing the video, the playing completion rate/amount of the video and the like, and the real playing situation of the video in the historical process and the real feedback situation of the majority of users to the video can be more accurately reflected.

Description

Video quality evaluation method, device, equipment and storage medium

Technical Field

The present application relates to the field of internet technologies, and in particular, to a method and an apparatus for evaluating quality of a video, a terminal device, and a storage medium.

Background

With the rapid development of internet technology, videos on a network are growing explosively, and a video platform generally needs to determine the market coverage scale of each video for profit, and then determines whether to push the video or to put the video on or off the shelf according to the market coverage scale.

At present, the accumulated playing times of the video played in a preset time period from the online to the current time are often counted and used as the accumulated playing quality of the video.

However, the inventors found that: the accumulative playing quality of the video is determined only according to the index of the accumulative playing times, the index dimension is single, and the accumulative playing quality of the video is determined to be inaccurate.

Disclosure of Invention

In order to solve the above technical problem, embodiments of the present application show a method and an apparatus for evaluating quality of a video, a terminal device, and a storage medium.

In a first aspect, an embodiment of the present application shows a method for evaluating quality of a video, where the method includes:

acquiring a score corresponding to a playing time index of a video, acquiring a score corresponding to a player number index of the video and acquiring a score corresponding to a playing quality index of the video;

and determining the accumulated playing quality of the video according to the score corresponding to the playing time index, the score corresponding to the player number index and the score corresponding to the playing quality index.

In an optional implementation manner, the obtaining a score corresponding to the play time index of the video includes:

determining a video type of the video;

searching at least one playing time index suitable for the video type in a plurality of preset playing time indexes;

and obtaining a score corresponding to each searched playing time index of the video.

In an optional implementation manner, the preset play time indexes include: the total accumulated playing times in the history process and the accumulated playing times in the preset time period.

In an optional implementation manner, the searching for at least one play time index applicable to the video type from among the plurality of preset play time indexes includes:

in a first corresponding relation between a video type and a playing time index set, searching for the playing time index set corresponding to the video type, wherein each playing time index set in the first corresponding relation comprises at least one of a plurality of preset playing time indexes.

In an optional implementation manner, the obtaining a score corresponding to each found play time index of the video includes:

acquiring a video clip included in the video;

and respectively obtaining the score corresponding to each found playing time index of each video clip.

In an optional implementation manner, the obtaining a score corresponding to the index of the number of people playing the video includes:

determining a video type of the video;

searching at least one index of the number of players suitable for the video type in a plurality of preset indexes of the number of players;

and obtaining a score corresponding to each found player number index of the video.

In an optional implementation manner, the preset number of players indexes include: the accumulated total number of the played people in the history process and the accumulated number of the played people in the preset time period.

In an optional implementation manner, the searching for at least one index of the number of playing people applicable to the video type in the plurality of preset indexes of the number of playing people includes:

and searching a number of playing people index set corresponding to the video type in a second corresponding relation between the video type and the number of playing people index set, wherein each number of playing people index set in the second corresponding relation comprises at least one of the preset number of playing people indexes.

In an optional implementation manner, the obtaining a score corresponding to each found number of players of the video includes:

acquiring a video clip included in the video;

and respectively obtaining the score corresponding to each found player number index of each video clip.

In an optional implementation manner, the obtaining a score corresponding to the play quality indicator of the video includes:

determining a video type of the video;

searching at least one playing quality index suitable for the video type in a plurality of preset playing quality indexes;

and obtaining a score corresponding to each searched playing quality index of the video.

In an optional implementation manner, the plurality of preset playback quality indicators include: the total playing time in the history process, the times of being completely played in the history process and the total playing time in the preset time period.

In an optional implementation manner, the searching for at least one play quality indicator applicable to the video type from among the plurality of preset play quality indicators includes:

and searching a playing quality index set corresponding to the video type in a third corresponding relation between the video type and the playing quality index set, wherein each playing quality index set in the third corresponding relation comprises at least one of the preset playing quality indexes.

In an optional implementation manner, obtaining a score corresponding to each found play quality indicator of the video includes:

acquiring a video clip included in the video;

and respectively obtaining the score corresponding to each searched playing quality index of each video clip.

In an alternative implementation, the video clip includes a feature, a cut, and a pre-cut of the video.

In an optional implementation manner, the determining the cumulative playing quality of the video according to the score corresponding to the playing time index, the score corresponding to the number of players, and the score corresponding to the playing quality index includes:

acquiring a first weight coefficient corresponding to the playing time index of the video, acquiring a second weight coefficient corresponding to the playing number index of the video and acquiring a third weight coefficient corresponding to the playing quality index of the video;

calculating the accumulative playing quality of the video according to the following formula;

M＝A*α+ (B*β+C*γ)；

a is the score corresponding to the index of the playing times, B is the score corresponding to the index of the number of players, C is the score corresponding to the index of the playing quality, alpha is a first weight coefficient, beta is a second weight coefficient, and gamma is a third weight coefficient.

In an optional implementation manner, the obtaining a first weight coefficient corresponding to the play time index of the video includes:

determining a video type of the video;

and determining a first weight coefficient corresponding to the playing time index of the video according to the video type.

In an optional implementation manner, the determining, according to the video type, a first weight coefficient corresponding to the play time index of the video includes:

and searching a weight coefficient corresponding to the playing time index in a fourth corresponding relation corresponding to the video type, and using the weight coefficient as the first weight coefficient, wherein the fourth corresponding relation is used for storing a corresponding table item between the playing time index and the weight coefficient.

acquiring a video clip included in the video;

and searching a weight coefficient corresponding to the video segment of the video and the playing time index in a fifth corresponding relation corresponding to the video type, and taking the weight coefficient as the first weight coefficient, wherein the fifth corresponding relation is used for storing corresponding table items among the video segment, the playing time index and the weight coefficient.

In an optional implementation manner, the obtaining a second weight coefficient corresponding to the number of people playing the video includes:

determining a video type of the video;

and determining a second weight coefficient corresponding to the number of the players of the video according to the video type.

In an optional implementation manner, the determining, according to the video type, a second weight coefficient corresponding to the number of people playing the video according to the index of the number of people playing the video includes:

and searching a weight coefficient corresponding to the number of the players in a sixth corresponding relation corresponding to the video type, and taking the weight coefficient as the second weight coefficient, wherein the sixth corresponding relation is used for storing corresponding items between the number of the players and the weight coefficient.

acquiring a video clip included in the video;

and searching a weight coefficient corresponding to the video clip of the video and the number of players in a seventh corresponding relation corresponding to the video type, and taking the weight coefficient as the second weight coefficient, wherein the seventh corresponding relation is used for storing corresponding items among the video clip, the number of players and the weight coefficient.

In an optional implementation manner, the obtaining a third weight coefficient corresponding to the play quality indicator of the video includes:

determining a video type of the video;

and determining a third weight coefficient corresponding to the playing quality index of the video according to the video type.

In an optional implementation manner, the determining, according to the video type, a third weight coefficient corresponding to the play quality indicator of the video includes:

and searching a weight coefficient corresponding to the playing quality index in an eighth corresponding relation corresponding to the video type, and using the weight coefficient as the third weight coefficient, wherein the eighth corresponding relation is used for storing a corresponding table item between the playing quality index and the weight coefficient.

acquiring a video clip included in the video;

and searching a weight coefficient corresponding to the video segment of the video and the playing quality index in a ninth corresponding relation corresponding to the video type, and using the weight coefficient as the third weight coefficient, wherein the ninth corresponding relation is used for storing corresponding table items among the video segment, the playing quality index and the weight coefficient.

In a second aspect, an embodiment of the present application shows an apparatus for evaluating quality of a video, where the apparatus includes:

the first acquisition module is used for acquiring a score corresponding to the playing time index of the video;

the second acquisition module is used for acquiring a score corresponding to the number index of the players of the video;

the third acquisition module is used for acquiring a score corresponding to the playing quality index of the video;

and the determining module is used for determining the accumulated playing quality of the video according to the score corresponding to the playing time index, the score corresponding to the player number index and the score corresponding to the playing quality index.

In an optional implementation manner, the first obtaining module includes:

a first determination unit for determining a video type of the video;

the first searching unit is used for searching at least one playing time index suitable for the video type in a plurality of preset playing time indexes;

and the first acquisition unit is used for acquiring a score corresponding to each searched playing time index of the video.

In an optional implementation manner, the first search unit is specifically configured to: in a first corresponding relation between a video type and a playing time index set, searching for the playing time index set corresponding to the video type, wherein each playing time index set in the first corresponding relation comprises at least one of a plurality of preset playing time indexes.

In an optional implementation manner, the first obtaining unit includes:

a first obtaining subunit, configured to obtain a video segment included in the video;

and the second obtaining subunit is used for respectively obtaining the score corresponding to each found playing time index of each video clip.

In an optional implementation manner, the second obtaining module includes:

a second determination unit for determining a video type of the video;

the second searching unit is used for searching at least one player number index suitable for the video type in a plurality of preset player number indexes;

and the second acquisition unit is used for acquiring the score corresponding to each found player number index of the video.

In an optional implementation manner, the second search unit is specifically configured to: and searching a number of playing people index set corresponding to the video type in a second corresponding relation between the video type and the number of playing people index set, wherein each number of playing people index set in the second corresponding relation comprises at least one of the preset number of playing people indexes.

In an optional implementation manner, the second obtaining unit includes:

a third obtaining subunit, configured to obtain a video segment included in the video;

and the fourth obtaining subunit is used for respectively obtaining the score corresponding to each found player number index of each video clip.

In an optional implementation manner, the third obtaining module includes:

a third determining unit for determining a video type of the video;

a third searching unit, configured to search at least one playing quality indicator applicable to the video type from among a plurality of preset playing quality indicators;

and the third acquisition unit is used for acquiring a score corresponding to each found playing quality index of the video.

In an optional implementation manner, the third searching unit is specifically configured to: and searching a playing quality index set corresponding to the video type in a third corresponding relation between the video type and the playing quality index set, wherein each playing quality index set in the third corresponding relation comprises at least one of the preset playing quality indexes.

In an optional implementation manner, the third obtaining unit includes:

a fifth acquiring subunit, configured to acquire a video segment included in the video;

and the sixth obtaining subunit is configured to obtain a score corresponding to each found play quality indicator of each video segment.

In an optional implementation manner, the determining module includes:

a fourth obtaining unit, configured to obtain a first weight coefficient corresponding to the play time index of the video;

the fifth acquiring unit is used for acquiring a second weight coefficient corresponding to the number index of the playing people of the video;

a sixth obtaining unit, configured to obtain a third weight coefficient corresponding to the play quality indicator of the video;

the calculating unit is used for calculating the accumulative playing quality of the video according to the following formula;

M＝A*α+ (B*β+C*γ)；

In an optional implementation manner, the fourth obtaining unit includes:

a first determining subunit, configured to determine a video type of the video;

and the second determining subunit is configured to determine, according to the video type, a first weight coefficient corresponding to the play time index of the video.

In an optional implementation manner, the second determining subunit is specifically configured to: and searching a weight coefficient corresponding to the playing time index in a fourth corresponding relation corresponding to the video type, and using the weight coefficient as the first weight coefficient, wherein the fourth corresponding relation is used for storing a corresponding table item between the playing time index and the weight coefficient.

In an optional implementation manner, the second determining subunit is specifically configured to: acquiring a video clip included in the video; and searching a weight coefficient corresponding to the video segment of the video and the playing time index in a fifth corresponding relation corresponding to the video type, and taking the weight coefficient as the first weight coefficient, wherein the fifth corresponding relation is used for storing corresponding table items among the video segment, the playing time index and the weight coefficient.

In an optional implementation manner, the fifth obtaining unit includes:

a third determining subunit, configured to determine a video type of the video;

and the fourth determining subunit is used for determining a second weight coefficient corresponding to the number of the players of the video according to the video type.

In an optional implementation manner, the fourth determining subunit is specifically configured to: and searching a weight coefficient corresponding to the number of the players in a sixth corresponding relation corresponding to the video type, and taking the weight coefficient as the second weight coefficient, wherein the sixth corresponding relation is used for storing corresponding items between the number of the players and the weight coefficient.

In an optional implementation manner, the fourth determining subunit is specifically configured to: acquiring a video clip included in the video; and searching a weight coefficient corresponding to the video clip of the video and the number of players in a seventh corresponding relation corresponding to the video type, and taking the weight coefficient as the second weight coefficient, wherein the seventh corresponding relation is used for storing corresponding items among the video clip, the number of players and the weight coefficient.

In an optional implementation manner, the sixth obtaining unit includes:

a fifth determining subunit, configured to determine a video type of the video;

a sixth determining subunit, configured to determine, according to the video type, a third weight coefficient corresponding to the play quality indicator of the video.

In an optional implementation manner, the sixth determining subunit is specifically configured to: and searching a weight coefficient corresponding to the playing quality index in an eighth corresponding relation corresponding to the video type, and using the weight coefficient as the third weight coefficient, wherein the eighth corresponding relation is used for storing a corresponding table item between the playing quality index and the weight coefficient.

In an optional implementation manner, the sixth determining subunit is specifically configured to: acquiring a video clip included in the video; and searching a weight coefficient corresponding to the video segment of the video and the playing quality index in a ninth corresponding relation corresponding to the video type, and using the weight coefficient as the third weight coefficient, wherein the ninth corresponding relation is used for storing corresponding table items among the video segment, the playing quality index and the weight coefficient.

In a third aspect, an embodiment of the present application shows a terminal device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the method of quality assessment of video as set forth in any of the above.

In a fourth aspect, this application embodiment shows a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the quality assessment method for video described in any one of the above.

Compared with the prior art, the embodiment of the application has the following advantages:

in the prior art, the accumulated playing quality of a video is determined only according to an index of the accumulated playing times, the index dimension is single, and the single index of the accumulated playing times is easy to cheat, for example, the number of times of illegal playing is swiped, so that the objectivity of the determined accumulated playing quality is low, and further the accumulated playing times of the video cannot represent real feedback of a large number of users to the accumulated playing quality, that is, the high accumulated playing times of the video cannot indicate that the accumulated playing quality of the video is high, and therefore the determination of the accumulated playing quality of the video is inaccurate.

In the application, when the accumulated playing quality of the video is determined, in addition to the score corresponding to the playing frequency index of the video, the score corresponding to the number index of the playing people of the video and the score corresponding to the playing quality index of the video are also used at the same time, the number index of the playing people of the video can at least represent the total number of users playing the video in the historical process and the like, and the playing quality index of the video can at least represent the total playing duration of the video in the historical process, the number of times that the video is completely played and the like.

Therefore, compared with the prior art that the accumulative playing quality of the video is determined by only using the single index of the accumulative playing times, the method and the device can more accurately determine the accumulative playing quality of the video by combining multiple dimensions such as the playing times of the video, the number of users playing the video, the playing completion rate/amount of the video and the like, and further more accurately reflect the real playing situation of the video in the history process and the real feedback situation of the majority of users to the video.

For a video, the quality of the video is related to the factors of the video itself, for example, if the video is played more times in the history process, the video is more popular, and thus the quality of the video is higher; if the video is played less times in the history, it is indicated that the video is less popular, and thus the quality of the video tends to be lower.

However, although the number of times that the video is played is many sometimes, in many cases, after the user clicks to play the video, the user feels that the video is not good and is quitted to be played in a short time, in this case, the video is not popular, and therefore, the quality of the video needs to be determined simultaneously by combining the total playing time length in the history process, the number of times that the video is completely played in the history process and the total playing time length in a preset time period, for example, if the total playing time length of the video in the history process is more, the video is more popular, and the quality of the video is higher; if the total time length of the video played in the history process is less, the video is not popular, and the quality of the video is low. The same is true for the number of times of being played in full in the history and the total length of time of playing in the preset time period.

In addition, in the present application, it is common for a user to select whether to play a video, and therefore, the quality of a video is often related to the user in addition to the factors of the video itself, for example, if the more users playing the video in the history process, the more popular the video is with the broad users, that is, the more users recognize the video, and thus the higher the quality of the video. If the number of users playing the video in the history process is less, the video is not popular with the majority of users, that is, the video is only approved by a small number of users, so that the quality of the video is often lower.

Therefore, in the application, the quality of the video can be more accurately determined by combining the score corresponding to the playing time index of the video, the score corresponding to the number index of the playing people of the video and the score corresponding to the playing quality index of the video.

Drawings

FIG. 1 is a flow chart of steps of an embodiment of a method for quality assessment of video according to the present application;

fig. 2 is a flowchart illustrating steps of an embodiment of a method for obtaining a score corresponding to a play time index of a video according to the present application;

FIG. 3 is a flowchart illustrating steps of an embodiment of a method for obtaining a score corresponding to a player index of a video according to the present application;

fig. 4 is a flowchart illustrating steps of an embodiment of a method for obtaining a score corresponding to a video playing quality indicator according to the present application;

FIG. 5 is a flow chart of steps of an embodiment of a method for quality assessment of video according to the present application;

FIG. 6 is a flow chart of steps of an embodiment of a method of obtaining weighting coefficients according to the present application;

FIG. 7 is a flow chart of steps of an embodiment of a method of obtaining weighting coefficients according to the present application;

FIG. 8 is a flow chart of steps of an embodiment of a method of obtaining weighting coefficients according to the present application;

fig. 9 is a block diagram of a video quality evaluation apparatus according to an embodiment of the present application.

Fig. 10 is a block diagram of a video quality evaluation apparatus according to an embodiment of the present application.

Detailed Description

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.

Referring to fig. 1, a flowchart illustrating steps of an embodiment of a video quality assessment method according to the present application is shown, where the method may specifically include the following steps:

in step S101, obtaining a score corresponding to a play time index of a video, obtaining a score corresponding to a play people index of the video, and obtaining a score corresponding to a play quality index of the video;

in the present application, the video includes a short video and a normal video, and the like, the short video includes a video having a duration of 10 seconds, 15 seconds, or 1 minute in the social network, and the normal video includes a movie, a tv show, a variety, and the like.

The play time index in the present application may include the accumulated play time of the video in the history process, and the like.

The number of players in the application may include the number of accumulated players of the video in the history process, and the number of accumulated players includes the total number of users playing the video.

The playing quality index in the application can include the total playing time of the video in the history process, the number of times that the video is completely played and the like, the video being completely played means that the video is continuously played from the 0 th second to the last second of the video, and no midway quitting exists in the playing process.

In step S102, the cumulative playing quality of the video is determined according to the score corresponding to the playing time index, the score corresponding to the number of players, and the score corresponding to the playing quality index.

In another embodiment of the present application, referring to fig. 2, obtaining a score corresponding to a play time index of a video includes:

in step S201, the video type of the video is determined;

the video types in the present application include animation, television play, movie, art, entertainment, and documentary, etc.

In this application, each video is provided with a respective video type. The video type of the video can be determined in a variety of ways.

Which is illustrated in a manner that is not intended to limit the scope of protection of the present application.

For example, each video has a video identification, and the video identifications of different videos are different. Some characters in the video identifier may be used as flags of video types, for example, the video identifier includes 10 characters, and characters of 4 th and 5 th bits are used as flags of video types, for example, 01 represents a movie, 02 represents a tv show, 03 represents a variety, and so on.

Thus, in this step, the video identifier of the video may be obtained, and then the video type of the video is obtained according to the video identifier, for example, the video type of the video is determined according to the flag bit of the video type in the video identifier.

In step S202, at least one play time index applicable to the video type is searched for from a plurality of preset play time indexes;

in the present application, the plurality of preset play times indexes include: the total accumulated playing times in the history process, the accumulated playing times in the preset time period and the like.

The time is divided into a plurality of continuous preset time periods, for example, each day is a preset time period, or each week is a preset time period, and the like. The preset time period in the accumulated playing times in the aforementioned preset time period includes: a preset time period before the current time and closest to the current time or at least two adjacent preset time periods.

For example, each day is a preset time period, and assuming that the current time is 1 point of 4 and 15 months in 2019, the preset time period in the accumulated playing times in the preset time period may include: 14/4/2019, or 11/4/2019 to 14/4/2019, etc.

The later preset time period may not coincide with the earlier preset time period, and the later preset time period may be adjacent to the earlier preset time period, or may not be adjacent to the earlier preset time period.

For example, assuming that the current time is 1 point of 15/4/2019, the later preset time period may be 14/4/2019, and the earlier preset time period may be 13/4/2019. Alternatively, the later preset time period may be 10 days in 4 months and 14 days in 4 months in 2019, and the earlier preset time period may be 5 days in 4 months and 9 days in 4 months in 2019.

In the application, for any video type, at least one play time index applicable to the video type can be set in advance according to actual conditions, the set at least one play time index applicable to the video type is formed into a play time index set, the video type and the formed play time index set are formed into corresponding entries and stored in a first corresponding relation between the video type and the play time index set, and the operations are executed for each other video type. Each play time index set in the first corresponding relation comprises at least one of a plurality of preset play time indexes.

Therefore, in this step, a play time index set corresponding to the video type may be searched in the first corresponding relationship between the video type and the play time index set, where the play time index in the play time index set is at least one play time index applicable to the video type.

In step S203, a score corresponding to each found play time index of the video is obtained.

In the application, a video clip included in a video may be acquired; video clips include feature, cut, and pre-cut of a video. The front of the film comprises advertisements and the like before the front film or the flower is played. And then respectively obtaining the score corresponding to each found playing time index of each video clip.

In the history process, each time a video segment is played once, the score corresponding to the play time index of the video segment is updated. For example, a score corresponding to the accumulated playing times within a preset time period.

Thus, in the present application, for any one video segment included in the video, the score corresponding to each found play time index of the video segment may be obtained, and for each other video segment included in the video, the above operation is also performed.

In the present application, there are various types of videos objectively, when determining the cumulative play quality of a video, the play frequency index of the video may be used, however, in a plurality of preset play frequency indexes, the play frequency indexes applicable to different video types are often different, and the present application may determine at least one play frequency index applicable to the video according to the video type of the video, so that, on the basis of the embodiment shown in fig. 1, the cumulative play quality of the video determined by using the at least one play frequency index applicable to the video may be more accurate and more reasonable.

In another embodiment of the present application, referring to fig. 3, obtaining a score corresponding to the index of the number of people playing the video includes:

in step S301, the video type of the video is determined;

the step S201 can be referred to specifically, and is not described in detail here.

In step S302, at least one index of the number of people playing applicable to the video type is searched for from a plurality of preset indexes of the number of people playing;

in this application, a plurality of predetermined broadcast number indicators include: the accumulated total number of the players in the history process, the accumulated number of the players in the preset time period and the like.

The time is divided into a plurality of continuous preset time periods, for example, each day is a preset time period, or each week is a preset time period, and the like. The preset time period of the accumulated number of players in the aforementioned preset time period includes: a preset time period before the current time and closest to the current time or at least two adjacent preset time periods.

For example, each day is a preset time period, and assuming that the current time is 1 point in 4 and 15 months in 2019, the preset time period in the accumulated number of players in the preset time period may include: 14/4/2019, or 11/4/2019 to 14/4/2019, etc.

In the application, for any video type, at least one player number index applicable to the video type can be set in advance according to actual conditions, then the set at least one player number index applicable to the video type is formed into a player number index set, then the video type and the formed player number index set are formed into corresponding items and stored in a second corresponding relation between the video type and the player number index set, and the operations are executed for each other video type. Each player number index set in the first corresponding relation comprises at least one of a plurality of preset player number indexes.

Therefore, in this step, the number of people playing in the set of people playing in the video type may be found from the second corresponding relationship between the video type and the number of people playing in the set of people playing in the video type.

In step S303, a score corresponding to each found number of players of the video is obtained.

In the application, a video clip included in a video may be acquired; video clips include feature, cut, and pre-cut of a video. The front of the film comprises advertisements and the like before the front film or the flower is played. And then respectively obtaining the score corresponding to each found player number index of each video clip.

In the history process, when a video clip is played once, the score corresponding to the number-of-players index of the video clip is updated. For example, a score corresponding to the cumulative number of players playing within a preset time period.

Thus, in the present application, for any one video segment included in the video, the score corresponding to each found player number index of the video segment may be obtained, and for each other video segment included in the video, the above operation is also performed.

In this application, there are various types of videos objectively, when the video accumulative total broadcast quality is confirmed, the number of players index of the video can be used, however, in a plurality of preset number of players indexes, the number of players index that is applicable to different video types is often different, this application can confirm at least one number of players index that is applicable to this video according to the video type of this video, so, on the basis of the embodiment shown in fig. 1, the video accumulative total broadcast quality that this video that uses at least one number of players index that is applicable to this video to determine can be more accurate and more reasonable.

In another embodiment of the present application, referring to fig. 4, the obtaining a score corresponding to the play quality indicator of the video includes:

in step S401, the video type of the video is determined;

In step S402, at least one play quality indicator applicable to the video type is searched for from a plurality of preset play quality indicators;

in the present application, the plurality of preset playback quality indicators include: the total playing time in the history process, the times of being completely played in the history process, the total playing time in a preset time period and the like.

The time is divided into a plurality of continuous preset time periods, for example, each day is a preset time period, or each week is a preset time period, and the like. The aforementioned preset time period in the accumulated playing quality in the preset time period includes: a preset time period before the current time and closest to the current time or at least two adjacent preset time periods.

For example, each day is a preset time period, and assuming that the current time is 1 point of 4 and 15 months in 2019, the preset time period in the accumulated playing quality in the preset time period may include: 14/4/2019, or 11/4/2019 to 14/4/2019, etc.

In the application, for any video type, at least one play quality index applicable to the video type according to actual conditions may be set in advance, the set at least one play quality index applicable to the video type is then combined into a play quality index set, the video type and the combined play quality index set are then combined into a corresponding entry and stored in a third corresponding relationship between the video type and the play quality index set, and the above operations are performed for each of the other video types as well. Each play quality index set in the first corresponding relation comprises at least one of a plurality of preset play quality indexes.

Therefore, in this step, a play quality index set corresponding to the video type may be searched in a third corresponding relationship between the video type and the play quality index set, where the play quality index in the play quality index set is at least one play quality index applicable to the video type.

In step S403, a score corresponding to each found playing quality index of the video is obtained.

In the application, a video clip included in a video may be acquired; video clips include feature, cut, and pre-cut of a video. The front of the film comprises advertisements and the like before the front film or the flower is played. And then respectively obtaining the score corresponding to each found playing quality index of each video clip.

In the history process, each time a video segment is played, the score corresponding to the playing quality index of the video segment is updated. For example, a score corresponding to the accumulated playing quality within a preset time period, and the like.

Thus, in the present application, for any one video segment included in the video, the score corresponding to each found play quality index of the video segment may be obtained, and for each other video segment included in the video, the above operation is also performed.

In the present application, there are various types of videos objectively, when determining the cumulative play quality of a video, the play quality index of the video may be used, however, in a plurality of preset play quality indexes, the play quality indexes applicable to different video types are often different, and the present application may determine at least one play quality index applicable to the video according to the video type of the video, so on the basis of the embodiment shown in fig. 1, the cumulative play quality of the video determined by using the at least one play quality index applicable to the video may be more accurate and more reasonable.

In another embodiment of the present application, referring to fig. 5, step S102 includes:

in step S501, a first weight coefficient corresponding to the index of the number of times of playing the video, a second weight coefficient corresponding to the index of the number of people playing the video, and a third weight coefficient corresponding to the index of the quality of playing the video are obtained;

the steps can be specifically referred to the following examples, which are not described in detail herein.

In step S502, the cumulative playing quality of the video is calculated according to the following formula:

M＝A*α+ (B*β+C*γ)；

a is the score corresponding to the index of the playing times of the video, B is the score corresponding to the index of the number of players playing the video, C is the score corresponding to the index of the playing quality playing the video, alpha is a first weight coefficient, beta is a second weight coefficient and gamma is a third weight coefficient.

In the present application, when the cumulative playing quality of the video is determined based on the score corresponding to the index of the number of times the video is played, the score corresponding to the index of the number of people who played the video, and the score corresponding to the index of the playing quality of the video, the contribution of each score to the cumulative playing quality of the video is different, and therefore, the method can respectively determine the contribution of the playing time index of the video, the number index of the players of the video and the playing quality index of the video to the accumulated playing quality of the video by combining with the actual situation, and then setting a weight coefficient corresponding to the playing time index of the video, a weight coefficient corresponding to the playing number index of the video and a weight coefficient corresponding to the playing quality index of the video according to the contribution of the playing time index of the video, the playing number index of the video and the playing quality index of the video to the accumulated playing quality of the video.

On the basis of the embodiment shown in fig. 1, the cumulative playing quality of the video is determined according to the weight coefficient corresponding to the playing time index of the video, the weight coefficient corresponding to the playing people number index of the video and the weight coefficient corresponding to the playing quality index of the video, in combination with the score corresponding to the playing time index of the video, the score corresponding to the playing people number index of the video and the score corresponding to the playing quality index of the video, so that the determined cumulative playing quality of the video can be more accurate and reasonable.

If the number of the playing time indexes of the video is multiple and each playing time index corresponds to a first weight coefficient, when the value "a x α" is calculated in the formula, the values corresponding to the multiple playing time indexes can be weighted and summed according to the corresponding weight coefficients, so as to obtain the value "a x α".

If the number of the players of the video is multiple or the number of the play quality indicators is multiple, the calculation is also performed in the above manner, and details are not described herein.

In another embodiment of the present application, referring to fig. 6, obtaining a first weight coefficient corresponding to a play time index of the video includes:

in step S601, the video type of the video is determined;

the step can be specifically described in step S201, and is not described in detail here.

In step S602, a first weighting factor corresponding to the play count index of the video is determined according to the video type.

In an embodiment of the present application, when determining the cumulative playing quality of a video, the playing time index of the video is used, however, different playing time indexes in a plurality of preset playing time indexes contribute differently to the cumulative playing quality of the video.

Therefore, the contribution of different playing time indexes to the video accumulated playing quality can be respectively determined by combining with actual conditions, and then the weight coefficients corresponding to different playing time indexes are set according to the contribution of different playing time indexes to the video accumulated playing quality.

For example, for any video type, a fourth corresponding relationship corresponding to the video type is set, and the fourth corresponding relationship is used for storing a corresponding table entry between the play time index and the weight coefficient. For any one of the preset play time indexes, the play time index and the set weight coefficient corresponding to the play time index may be combined into a corresponding table entry, and stored in a fourth corresponding relationship between the play time index and the weight coefficient. The above operation is also performed for each of the other preset play count indexes.

The above operation is also performed for each of the other video types.

Thus, in this step, the weight coefficient corresponding to the play frequency index of the video may be searched in the fourth corresponding relationship corresponding to the video type, and used as the first weight coefficient.

On the basis of the embodiment shown in fig. 1, the cumulative playing quality of the video is determined according to the weight coefficient corresponding to each playing time index and the score corresponding to the playing time index, so that the determined cumulative playing quality of the video is more accurate and more reasonable.

In another embodiment of the present application, when determining the cumulative playing quality of a video, the playing number index of the video may be used, however, among a plurality of preset playing number indexes, the contribution of different playing number indexes to the cumulative playing quality of the video is different, and then, the video has video segments, where the video segments include a positive, a cut, and a front of the video, and the contribution of the playing number indexes of different video segments to the cumulative playing quality of the video is also different. Wherein, the front of the film comprises the advertisement before the positive film or the flower is played.

Therefore, the contribution of different playing time indexes of different video segments to the accumulative playing quality of the video can be respectively determined by combining with actual conditions, and then the weight coefficients corresponding to the different playing time indexes of different video segments are set according to the contribution of the different playing time indexes of different video segments to the accumulative playing quality of the video.

For example, a fifth corresponding relationship of the video type is set, and the fifth corresponding relationship is used for storing corresponding table entries between the video segments, the play time indexes and the weight coefficients. In this way, in this step, the weight coefficient corresponding to the video segment of the video and the play time index may be searched in the fifth corresponding relationship corresponding to the video type, and used as the first weight coefficient.

On the basis of the embodiment shown in fig. 1, the cumulative playing quality of the video is determined according to the weighting coefficients corresponding to the playing time indexes of the video segments of the video and the scores corresponding to the playing time indexes, so that the determined cumulative playing quality of the video is more accurate and reasonable.

In another embodiment of the present application, referring to fig. 7, the obtaining a second weight coefficient corresponding to the number of people playing the video includes:

in step S701, a video type of the video is determined;

In step S702, a second weighting factor corresponding to the number of people playing the video index is determined according to the video type.

In an embodiment of the present application, when determining the accumulated playing quality of the video, the number of people playing the video may be used, however, different number of people playing the video may contribute differently to the accumulated playing quality of the video among a plurality of preset number of people playing the video.

Therefore, the contribution of different player number indexes to the accumulated playing quality of the video can be respectively determined according to actual conditions, and then the weight coefficients corresponding to the different player number indexes are set according to the contribution of the different player number indexes to the accumulated playing quality of the video.

For example, for any video type, a sixth corresponding relation corresponding to the video type is set, and the sixth corresponding relation is used for storing a corresponding table item between the number of playing people index and the weight coefficient. For any one of the preset number of people playing indexes, the number of people playing index and the set weight coefficient corresponding to the number of people playing index can be combined into a corresponding table entry and stored in a sixth corresponding relation between the number of people playing index and the weight coefficient. The above operation is also performed for each of the other preset number of players indicators.

The above operation is also performed for each of the other video types.

In this way, in this step, the weighting coefficient corresponding to the number of people playing the video may be searched in the sixth corresponding relationship corresponding to the video type and used as the second weighting coefficient.

On the basis of the embodiment shown in fig. 1, the cumulative playing quality of the video is determined according to the weight coefficient corresponding to each player number index and the score corresponding to the player number index, so that the determined cumulative playing quality of the video is more accurate and reasonable.

In another embodiment of the present application, when determining the cumulative playing quality of a video, the number of people playing the video may be used, however, among a plurality of preset number of people playing indicators, the number of people playing the video is different from the number of people playing the video, and then the video has video segments, where the video segments include a feature, a flower, a front of a video, and the like, and the number of people playing the video segments is different from the number of people playing the video. Wherein, the front of the film comprises the advertisement before the positive film or the flower is played.

Therefore, the contribution of different player number indexes of different video segments to the accumulative playing quality of the video can be respectively determined according to actual conditions, and then the weight coefficients corresponding to the different player number indexes of different video segments are set according to the contribution of the different player number indexes of different video segments to the accumulative playing quality of the video.

For example, a seventh corresponding relation of the video type is set, and the seventh corresponding relation is used for storing corresponding items among the video clips, the number of players and the weight coefficient. In this way, in this step, the weighting coefficients corresponding to the video segment of the video and the player number index may be searched in the seventh correspondence corresponding to the video type and used as the second weighting coefficient.

On the basis of the embodiment shown in fig. 1, the cumulative playing quality of the video is determined according to the weight coefficient corresponding to each of the number of people playing indicators of each video segment of the video and the score corresponding to the number of people playing indicators, so that the determined cumulative playing quality of the video is more accurate and reasonable.

In another embodiment of the present application, referring to fig. 8, obtaining a third weight coefficient corresponding to the play quality indicator of the video includes:

in step S801, the video type of the video is determined;

In step S802, a third weighting factor corresponding to the video playing quality index is determined according to the video type.

In an embodiment of the present application, when determining the accumulated playing quality of a video, the playing quality index of the video is used, however, different playing quality indexes in a plurality of preset playing quality indexes contribute differently to the accumulated playing quality of the video.

Therefore, the contribution of different playing quality indexes to the video accumulated playing quality can be respectively determined by combining with actual conditions, and then the weight coefficients corresponding to different playing quality indexes are set according to the contribution of different playing quality indexes to the video accumulated playing quality.

For example, for any video type, an eighth corresponding relationship corresponding to the video type is set, and the eighth corresponding relationship is used for storing a corresponding table entry between the play quality index and the weight coefficient. For any one of the preset playing quality indexes, the playing quality index and the set weight coefficient corresponding to the playing quality index may be combined into a corresponding table entry, and stored in the eighth corresponding relationship between the playing quality index and the weight coefficient. The above operation is also performed for each of the other preset playback quality indicators.

The above operation is also performed for each of the other video types.

In this way, in this step, the weighting coefficient corresponding to the playback quality indicator of the video may be searched in the eighth corresponding relationship corresponding to the video type, and used as the third weighting coefficient.

On the basis of the embodiment shown in fig. 1, the cumulative playing quality of the video is determined according to the weight coefficient corresponding to each playing quality index and the score corresponding to the playing quality index, so that the determined cumulative playing quality of the video is more accurate and more reasonable.

In another embodiment of the present application, when determining the cumulative playing quality of a video, the playing quality indicators of the video may be used, however, among a plurality of preset playing quality indicators, the contributions of different playing quality indicators to the cumulative playing quality of the video are different, and then, the video has video segments, where the video segments include a positive, a cut, and a front of the video, and the contributions of the playing quality indicators of different video segments to the cumulative playing quality of the video are also different. Wherein, the front of the film comprises the advertisement before the positive film or the flower is played.

Therefore, the contribution of different playing quality indexes of different video segments to the accumulative playing quality of the video can be respectively determined by combining with actual conditions, and then the weight coefficients corresponding to the different playing quality indexes of different video segments are set according to the contribution of the different playing quality indexes of different video segments to the accumulative playing quality of the video.

For example, a ninth corresponding relationship of the video type is set, and the ninth corresponding relationship is used for storing corresponding table entries between the video segments, the playing quality indexes and the weight coefficients. In this way, in this step, the weighting coefficients corresponding to the video segment of the video and the playing quality index may be searched in the ninth corresponding relationship corresponding to the video type, and used as the third weighting coefficient.

On the basis of the embodiment shown in fig. 1, the cumulative playing quality of the video is determined according to the weighting coefficients corresponding to the playing quality indicators of the video segments of the video and the scores corresponding to the playing quality indicators, so that the determined cumulative playing quality of the video is more accurate and reasonable.

Referring to fig. 9, a block diagram of a video quality evaluation apparatus according to an embodiment of the present disclosure is shown, where the apparatus may specifically include the following modules:

the first obtaining module 11 is configured to obtain a score corresponding to a play time index of a video;

the second obtaining module 12 is configured to obtain a score corresponding to the number of players of the video;

a third obtaining module 13, configured to obtain a score corresponding to the play quality indicator of the video;

and the determining module 14 is configured to determine the cumulative playing quality of the video according to the score corresponding to the playing time index, the score corresponding to the number of players, and the score corresponding to the playing quality index.

Referring to fig. 10, in an alternative implementation, the first obtaining module 11 includes:

a first determining unit 111 for determining a video type of the video;

a first searching unit 112, configured to search at least one play time index applicable to the video type from a plurality of preset play time indexes;

the first obtaining unit 113 is configured to obtain a score corresponding to each found play time index of the video.

In an optional implementation manner, the first search unit 112 is specifically configured to: in a first corresponding relation between a video type and a playing time index set, searching for the playing time index set corresponding to the video type, wherein each playing time index set in the first corresponding relation comprises at least one of a plurality of preset playing time indexes.

In an optional implementation manner, the first obtaining unit 113 includes:

In an optional implementation manner, the second obtaining module 12 includes:

a second determining unit 121, configured to determine a video type of the video;

the second searching unit 122 is configured to search at least one index of the number of playing people suitable for the video type from a plurality of preset indexes of the number of playing people;

the second obtaining unit 123 is configured to obtain a score corresponding to each found number of players of the video.

In an optional implementation manner, the second search unit 122 is specifically configured to: and searching a number of playing people index set corresponding to the video type in a second corresponding relation between the video type and the number of playing people index set, wherein each number of playing people index set in the second corresponding relation comprises at least one of the preset number of playing people indexes.

In an optional implementation manner, the second obtaining unit 123 includes:

In an optional implementation manner, the third obtaining module 13 includes:

a third determining unit 131, configured to determine a video type of the video;

a third searching unit 132, configured to search at least one playing quality indicator applicable to the video type from among a plurality of preset playing quality indicators;

a third obtaining unit 133, configured to obtain a score corresponding to each found playing quality indicator of the video.

In an optional implementation manner, the third searching unit 132 is specifically configured to: and searching a playing quality index set corresponding to the video type in a third corresponding relation between the video type and the playing quality index set, wherein each playing quality index set in the third corresponding relation comprises at least one of the preset playing quality indexes.

In an optional implementation manner, the third obtaining unit 133 includes:

In an optional implementation manner, the determining module 14 includes:

a fourth obtaining unit 141, configured to obtain a first weight coefficient corresponding to the play time index of the video;

a fifth obtaining unit 142, configured to obtain a second weight coefficient corresponding to the number of people playing the video;

a sixth obtaining unit 143, configured to obtain a third weight coefficient corresponding to the playing quality indicator of the video;

M＝A*α+ (B*β+C*γ)；

In an optional implementation manner, the fourth obtaining unit 141 includes:

a first determining subunit, configured to determine a video type of the video;

In an optional implementation manner, the fifth obtaining unit 142 includes:

a third determining subunit, configured to determine a video type of the video;

In an optional implementation manner, the sixth obtaining unit 142 includes:

a fifth determining subunit, configured to determine a video type of the video;

For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

Optionally, the present application further provides a mobile terminal, including: the video quality evaluation method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the computer program is executed by the processor, each process of the video quality evaluation method embodiment is realized, the same technical effect can be achieved, and in order to avoid repetition, the details are not repeated.

Optionally, the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the video quality assessment method described above. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.

The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.

As will be appreciated by one of skill in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.

Finally, it should also be 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 terminal 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 terminal. 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 terminal that comprises the element.

The method, the apparatus, the terminal device and the storage medium for evaluating the quality of a video provided by the present application are introduced in detail, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A method for video quality assessment, the method comprising:

determining the accumulative playing quality of the video according to the value corresponding to the playing time index, the value corresponding to the player number index and the value corresponding to the playing quality index, wherein the accumulative playing quality of the video is used for reflecting the real playing condition of the video in the historical process;

the method for acquiring the score corresponding to the play time index of the video comprises the following steps: determining a video type of the video; searching at least one playing time index suitable for the video type in a plurality of preset playing time indexes; obtaining a score corresponding to each searched playing time index of the video; the playing time indexes suitable for different video types are different; wherein the plurality of preset play time indexes include: the total accumulated playing times in the history process and the accumulated playing times in the preset time period.

2. The method according to claim 1, wherein said searching for at least one index of playing times applicable to the video type among a plurality of preset indexes of playing times comprises:

3. The method according to claim 1, wherein the obtaining a score corresponding to each found play time index of the video comprises:

acquiring a video clip included in the video;

4. The method according to claim 1, wherein the obtaining of the score corresponding to the indicator of the number of people playing the video comprises:

determining a video type of the video;

5. The method of claim 4, wherein the plurality of preset playcount indicators comprises: the accumulated total number of the played people in the history process and the accumulated number of the played people in the preset time period.

6. The method according to claim 4, wherein the searching for at least one index of number of players applicable to the video type among a plurality of preset indexes of number of players comprises:

7. The method according to claim 4, wherein the obtaining a score corresponding to each found number of players for the video comprises:

acquiring a video clip included in the video;

8. The method according to claim 1, wherein the obtaining of the score corresponding to the playing quality indicator of the video comprises:

determining a video type of the video;

9. The method of claim 8, wherein the plurality of preset playback quality indicators comprise: the total playing time in the history process, the times of being completely played in the history process and the total playing time in the preset time period.

10. The method according to claim 8, wherein said searching for at least one of the plurality of preset playback quality indicators applicable to the video type comprises:

11. The method according to claim 8, wherein obtaining a score corresponding to each found playback quality indicator of the video comprises:

acquiring a video clip included in the video;

12. The method of claim 3, 7 or 11, wherein the video clips include a feature, a cut, and a pre-cut of the video.

13. The method according to claim 1, wherein the determining the cumulative playing quality of the video according to the score corresponding to the playing time index, the score corresponding to the player number index, and the score corresponding to the playing quality index comprises:

M＝A*α+(B*β+C*γ)；

14. The method according to claim 13, wherein the obtaining a first weighting factor corresponding to the play time index of the video comprises:

determining a video type of the video;

15. The method according to claim 14, wherein the determining a first weighting factor corresponding to the play time indicator of the video according to the video type comprises:

16. The method according to claim 14, wherein the determining a first weighting factor corresponding to the play time indicator of the video according to the video type comprises:

acquiring a video clip included in the video;

17. The method of claim 13, wherein the obtaining a second weight coefficient corresponding to the playcount index of the video comprises:

determining a video type of the video;

18. The method of claim 17, wherein determining the second weight coefficient corresponding to the playcount index of the video according to the video type comprises:

19. The method of claim 17, wherein determining the second weight coefficient corresponding to the playcount index of the video according to the video type comprises:

acquiring a video clip included in the video;

20. The method according to claim 13, wherein the obtaining a third weighting factor corresponding to the playing quality indicator of the video comprises:

determining a video type of the video;

21. The method according to claim 20, wherein the determining a third weighting factor corresponding to the playing quality indicator of the video according to the video type comprises:

22. The method according to claim 20, wherein the determining a third weighting factor corresponding to the playing quality indicator of the video according to the video type comprises:

acquiring a video clip included in the video;

23. An apparatus for quality assessment of video, the apparatus comprising:

the determining module is used for determining the accumulative playing quality of the video according to the score corresponding to the playing time index, the score corresponding to the player number index and the score corresponding to the playing quality index, wherein the accumulative playing quality of the video is used for reflecting the real playing condition of the video in the historical process;

24. A terminal device, comprising: memory, processor and computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, implements a method of quality assessment of video according to any one of claims 1 to 22.

25. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, implements a method of quality assessment of video according to any one of claims 1 to 22.