CN114095763B - Video list pushing method and play quality assessment method - Google Patents
Video list pushing method and play quality assessment method Download PDFInfo
- Publication number
- CN114095763B CN114095763B CN202111412110.5A CN202111412110A CN114095763B CN 114095763 B CN114095763 B CN 114095763B CN 202111412110 A CN202111412110 A CN 202111412110A CN 114095763 B CN114095763 B CN 114095763B
- Authority
- CN
- China
- Prior art keywords
- video
- target
- equipment
- mth
- videos
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000001303 quality assessment method Methods 0.000 title claims abstract description 22
- 230000000694 effects Effects 0.000 claims abstract description 118
- 238000013441 quality evaluation Methods 0.000 claims abstract description 51
- 230000004044 response Effects 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims description 100
- 238000013507 mapping Methods 0.000 claims description 58
- 238000003860 storage Methods 0.000 claims description 25
- 230000002452 interceptive effect Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 230000003139 buffering effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 9
- 238000004519 manufacturing process Methods 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000006978 adaptation Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000013442 quality metrics Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26258—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/432—Content retrieval operation from a local storage medium, e.g. hard-disk
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/482—End-user interface for program selection
- H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The embodiment of the application discloses a video list pushing method, which comprises the following steps: determining a plurality of videos in response to a video list request provided by a target device; determining a play quality assessment value of each of the plurality of videos in the target device; ranking the playing quality evaluation values of the videos from high to low to obtain ranking results; and generating a target video list based on the sorting result and pushing the target video list to the target device, wherein all videos in the target video list are sorted from high to low according to respective playing quality evaluation values. According to the technical scheme provided by the embodiment of the application, whether the video is pushed or the ordering position of the video in the push list is determined according to the play quality evaluation value, so that dynamic output of the video in target equipment (such as large-screen equipment) is determined. Based on the playing quality evaluation value, the playing effect of the video which is first seen by the user can be the best, so that the viewing experience of the user is improved.
Description
Technical Field
The present disclosure relates to the field of computers, and in particular, to a video list pushing method, a system, a computer device, and a computer readable storage medium.
Background
With the development of internet technology, different network platforms each develop different content types. For example, PGC (Professional Generated Content, professional production content) types typified by aiqi, netflix, and OGV (Occupationally Generated Video, professional production video) types, UGC (User Generated Content, user original content) types typified by a network platform such as Youtube, bilibilli. PGC types and OGV types are typically better guaranteed video output quality due to professional production. However, with the popularity of mobile networks (e.g., 4G) and small screen devices (e.g., smartphones), UGC-type video (hereinafter referred to as UGC video) is increasing. The core of UGC is to advocate each user to show or provide its original content to other users through a platform. UGC allows people to be content producers, so that massive videos can be quickly produced to enrich the mental lives of people.
UGC video is typically captured by a large number of non-professional persons via non-professional devices, with very different video quality. UGC video is authored for small screen devices, i.e., its video parameters, etc. are better adapted to the small screen device. Most UGC videos are played on large screen devices (such as televisions and projectors), and the playing effect is poor.
Disclosure of Invention
An object of an embodiment of the present application is to provide a video list pushing method, a system, a playing quality evaluation method, a computer device and a computer readable storage medium, which are used for solving the above technical problems.
An aspect of an embodiment of the present application provides a video list pushing method, where the method includes:
determining a plurality of videos in response to a video list request provided by a target device;
determining a play quality assessment value of each of the plurality of videos in the target device;
ranking the playing quality evaluation values of the videos from high to low to obtain ranking results; and
And generating a target video list based on the sorting result, and pushing the target video list to the target equipment, wherein all videos in the target video list are sorted from high to low according to respective playing quality evaluation values.
Optionally, the determining a playing quality evaluation value of each video in the plurality of videos in the target device includes:
calculating the target quality assessment value by one or more of the following parameters:
the target matching degree is the matching degree between the video metadata of each video and the target equipment parameters of the target equipment;
A target playing effect evaluation value which is the playing effect evaluation value of each video on the target equipment;
and obtaining the target popularity according to the interactive data of each video.
Optionally, the method further comprises:
inquiring the mth target matching degree between the target equipment and the mth video from the cache; the buffer memory is used for storing the matching degree between each video in one or more videos and different devices in advance, the mth video is any video in the videos, and m is a positive integer larger than 0; and
And if the mth target matching degree between the target equipment and the mth video is not queried, calculating the mth target matching degree according to the target equipment parameters and the video meta-information of the mth video.
Optionally, the method further comprises:
determining a target equipment grade of the target equipment according to the target equipment parameters;
inquiring an mth target playing effect evaluation value of an mth video from a cache according to the target equipment grade and the target equipment model of the target equipment; the buffer memory is used for storing play effect evaluation values of one or more videos on devices with different device grades and different device models in advance, wherein the mth video is any one video in the videos, and m is a positive integer greater than 0; and
And if the mth target playing effect evaluation value is not queried according to the target equipment grade and the target equipment model, querying the mth target playing effect evaluation value from the cache according to the target equipment grade.
Optionally, the target device level is one of a plurality of device levels; the method further comprises the steps of obtaining play effect evaluation values of all equipment levels in advance:
obtaining a play log of each device, and calculating a play effect evaluation value of each device;
grading according to the equipment parameters of each equipment, calculating the playing effect evaluation mean value of each equipment grade, and obtaining the mapping relation between each equipment grade and the corresponding playing effect evaluation mean value; the play effect evaluation average value of one equipment level is the average value of the play effect evaluation values of all the equipment under the equipment level.
Optionally, the cache is further configured to store:
the popularity of each video identifier corresponds to that of the plurality of video identifiers, and each video identifier is associated with one video;
a plurality of video tags each associated with one or more videos, respectively, each correspond to a popularity of the video tag.
Optionally, the method further comprises:
According to the mth video identification of the mth video, inquiring the mth popularity associated with the mth video identification from the cache;
and if the mth popularity is not inquired according to the mth video identification, acquiring the mth popularity from the cache according to one or more video tags associated with the mth video.
An aspect of an embodiment of the present application further provides a video list pushing system, including:
a first determining module, configured to determine a plurality of videos in response to a video list request provided by a target device;
a second determining module, configured to determine a play quality evaluation value of each of the plurality of videos in the target device;
the sorting module is used for sorting the playing quality evaluation values of the videos from high to low so as to obtain a sorting result; and
And the pushing module is used for generating a target video list based on the sorting result and pushing the target video list to the target equipment, and all videos in the target video list are sorted from high to low according to respective playing quality evaluation values.
An aspect of the embodiments of the present application further provides a play quality assessment method, including:
Obtaining a plurality of matching degrees according to video metadata of each video and equipment parameters of each equipment, and establishing a first mapping relation among each matching degree, corresponding video and corresponding equipment; each matching degree is calculated according to video metadata of one video and equipment parameters of one equipment;
determining the equipment model and equipment grade of each equipment according to the equipment parameters of each equipment; determining a play effect evaluation value of each device according to the play log of each device; establishing a second mapping relation between the equipment model, the equipment grade and the corresponding play effect evaluation value of each equipment;
calculating popularity of each video according to the interactive data associated with each video; establishing a third mapping relation between the video identification of each video and the corresponding popularity, and/or a fourth mapping relation between the video label of each video and the corresponding popularity, wherein the video label is used for describing the characteristics of the video;
updating the first mapping relation, the second mapping relation, the third mapping relation and the fourth mapping relation into a cache;
The first mapping relation, the second mapping relation, the third mapping relation and the fourth mapping relation which are positioned in the cache are used for being read by a processor and used for evaluating the playing quality evaluation value of the video in the equipment.
Optionally, the method further comprises:
establishing a fifth mapping relation between each equipment level and the corresponding playing effect evaluation mean value; the playing effect evaluation average value of one equipment level is the average value of the playing effect evaluation values of all the equipment under the equipment level.
An aspect of the embodiments of the present application further provides a computer device, where the computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the steps of the video list pushing method or the playing quality assessment method as described above.
An aspect of the embodiments of the present application further provides a computer readable storage medium having a computer program stored therein, the computer program being executable by at least one processor to cause the at least one processor to perform the steps of a play quality assessment method as the video list pushing method described above.
The video list pushing method, the video list pushing system, the video list playing quality evaluation method, the video list playing quality evaluation device and the computer readable storage medium provided by the embodiment of the application comprise the following advantages:
and determining whether to push the video or the ordering position of the video in the push list according to the play quality evaluation value, thereby determining to realize dynamic output of the video in target equipment (such as large screen equipment). Based on the playing quality evaluation value, the playing effect of the video which is first seen by the user can be the best, so that the viewing experience of the user is improved.
Drawings
Fig. 1 schematically illustrates an application environment diagram of a play quality assessment method according to an embodiment of the present application;
fig. 2 schematically shows a flowchart of a play quality assessment method according to a first embodiment of the present application;
fig. 3 schematically illustrates a use case diagram of a play quality assessment method according to a first embodiment of the present application;
fig. 4 schematically shows a flowchart of a video list pushing method according to a second embodiment of the present application;
fig. 5-8 schematically show a flowchart of the added steps of a video list pushing method according to a second embodiment of the present application;
fig. 9 schematically shows a block diagram of a video list pushing system according to a third embodiment of the present application;
Fig. 10 schematically shows a block diagram of a play quality assessment system according to a fourth embodiment of the present application;
fig. 11 schematically shows a hardware architecture diagram of a computer device according to a fifth embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
It should be noted that the descriptions of "first," "second," etc. in the embodiments of the present application are for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be regarded as not exist and not within the protection scope of the present application.
In the description of the present application, it should be understood that the numerical references before the steps do not identify the order of performing the steps, but are only used for convenience in describing the present application and distinguishing each step, and thus should not be construed as limiting the present application.
Through the analysis of the inventor, the OGV is still the dominant type of main stream resources on a large screen at present, such as Aiqi technology, netflix and the like. The video output quality can be better ensured because of professional institutions production. In contrast, the production of UGC type is very random, and with the popularization of intelligent machines and 4G networks, users can shoot videos at any time and upload platforms. The video quality of UGC varies widely, affected by the shooting device and the own shooting level.
Meanwhile, the large screen consumption is still mainly based on OGV, but the playing times and the duration ratio of UGC are gradually increased, and especially in the young population of Z age. Taking the B station as an example, the playing times and the duration of UGC videos on a large screen are more than 60 percent. This also means that users will consume UGC video on a large screen more and more.
Users consume UGC video on large screens, often without a good viewing experience on mobile devices. In one aspect, many UGC videos are themselves authored on a mobile device basis; on the other hand, compared with large-screen equipment such as televisions, the mobile equipment has the advantages that the software and hardware parameters of the mobile equipment are more suitable for playing UGC videos. However, no third party mechanism or UGC production platform within the industry provides a relatively standard set of large screen output schemes that fit UGC videos. The existing mode is to directly put the head UGC with good playing effect on the mobile equipment on a large screen for users to consume, which causes the problems that feedback of users on the large screen side, namely too blurred pictures, 4k video playing and clamping and the like, is often received. Therefore, there is also a large difference between the playing quality of UGC video on a large screen and the viewing expectations of users.
Thus the following problems are addressed: (1) There is no large screen output scheme and evaluation method for UGC video. (2) The large screen output mode of the UGC video is usually a reference to the playing effect on the mobile device, and the adaptation degree of the video itself and the large screen device is not considered. 3) Even if the difference on the large screen is taken into consideration, the general practice is not flexible enough, for example, for a low-end set, 4k high definition is not outputted, and the like.
The application provides a video large screen playing quality evaluation scheme, in the scheme, video playing quality can be evaluated in real time according to video parameters, playing equipment, user experience and other multidimensional degrees, and video is dynamically output on a large screen, so that the following effects are achieved: (1) UGC videos cannot be output to equipment with too low matching degree, for example, low-quality videos are output to high-end equipment, and blurring effect is aggravated; or the high-quality video is output to the low-end equipment, resulting in abnormal play. (2) And besides the fixed matching condition between the video and the equipment, the output score from the video to the equipment is comprehensively measured by combining the on-line user feedback and the actual effect of the equipment, so that the dynamic update of a calculation engine is realized.
The following is a term explanation of the present application:
UGC: user Generated Content, the user produces the content.
PGC: professional Generated Content, professional production content.
OGV: occupationally Generated Video professional institutions produce videos including platform purchased or homemade sitcoms, animations, movies, televised shows, variety and the like.
Video resolution: the video area size, in pixels (px), e.g., 1920 x 1080.
Video frame rate: frame number per second (fps).
Color depth: a primary color (e.g., RGB) can be divided into how many ranks N, e.g., 8 bits, and 2^8 =256 ranks can be represented.
Video code rate: data volume per second (bps, bit), equal to resolution x frame rate x color depth.
Device resolution: w is h, how many pixels can be displayed. E.g. 2k, indicating that the horizontal display resolution has 2000 pixels.
Device refresh rate: refresh times per second, in Hz.
Encoding/decoding: the original file of the audio and video is generally oversized, and the encoding is used for reducing the data size and facilitating transmission; the decoding is to obtain the original audio and video file.
Definition: video quality metrics, such as 1080p, 1080p60 frames, etc., with specified resolution, code rate and frame rate.
Fig. 1 schematically shows an environment architecture diagram of a video list pushing method according to an embodiment of the present application. In an exemplary embodiment, as shown in FIG. 1, a computer device 2 may connect a plurality of devices 4 over a network.
The computer device 2 may push the video list into the device (large screen device) 4 via the network.
The computer device 2 may be comprised of a single or multiple computing devices, such as a rack server, a blade server, a tower server, or a rack server (including individual servers, or a server cluster comprised of multiple servers), among others. The one or more computer devices may include virtualized computing instances. The computer device may load the virtual machine based on a virtual image and/or other data defining particular software (e.g., operating system, application specific, server) for emulation. As the demand for different types of processing services changes, different virtual machines may be loaded and/or terminated on the one or more computer devices.
The network may include various network devices such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and/or the like. The network may include physical links such as coaxial cable links, twisted pair cable links, fiber optic links, combinations thereof, and/or the like. The network may include wireless links, such as cellular links, satellite links, wi-Fi links, and/or the like.
Device 4 may be configured to access computer device 2. The device 4 may comprise any type of computer device, for example: and electronic equipment with larger display interfaces such as intelligent televisions, projectors, personal computers and the like.
Hereinafter, the present application will provide a video quality assessment method, a video list pushing method, a system, a computer device, and a computer-readable storage medium.
Example 1
Fig. 2 schematically shows a flowchart of a play quality assessment method according to an embodiment of the present application. The method may be performed in the computer device 2. As shown in fig. 2, the play quality evaluation method may include steps S200 to S206, in which:
step S200, obtaining a plurality of matching degrees according to video metadata of each video and equipment parameters of each equipment, and establishing a first mapping relation among each matching degree, corresponding video and corresponding equipment; each matching degree is calculated according to video metadata of one video and equipment parameters of one equipment.
The video metadata may include the following metrics: video resolution, video frame rate, video rate, coding, etc.
The device parameters may include the following metrics: screen refresh rate, device resolution, screen size, decoding.
For example, the matching degree M can be calculated by the following formula:
wherein i is used to refer to an index.
a i The weight (0-1) of each index score can be dynamically adjusted according to the recall effect.
α i Is given as index scoring parameter according to experimental evaluation effect, e.g. resolution index alpha i ＝4。
α i The acquisition process is as follows:
step one: different videos are played in a large number of devices, and evaluation is performed from different evaluation dimensions such as screen-display times, time-consuming first frame loading, blocking times, definition, asynchronous audio and video, and the like, so that a large number of evaluation effect scores are obtained.
Step two: and calculating index score parameters of the indexes according to the scores of the evaluating effects and the indexes corresponding to the evaluating effects.
x i For index scoring, e.g., (1) resolution index, thenR v For video resolution, R d For device resolution; (2) a frame rate indicator, which is a video frame rate/device refresh rate; (3) the code rate index is the code rate value of the video code rate; (4) And the coding index is a first value if the coding and decoding are adapted, and is a second value if the coding and decoding are adapted. It should be noted that some indexes are separate indexes, such as code rate indexes, some indexes are non-separate indexes, such as resolution indexes, which are the ratio of video resolution to device resolution, and frame rate indexes are the same.
Step S202, determining the equipment model and the equipment grade of each equipment according to the equipment parameters of each equipment; determining a play effect evaluation value of each device according to the play log of each device; and establishing a second mapping relation among the equipment model numbers, the equipment grades and the corresponding play effect evaluation values of the equipment.
Establishing a fifth mapping relation between each equipment level and the corresponding playing effect evaluation mean value; the playing effect evaluation average value of one equipment level is the average value of the playing effect evaluation values of all the equipment under the equipment level. The play effect evaluation mean corresponding to the device class can be directly used by a large number of devices in a larger range.
The play log may include the following indicators: a click-through rate, an abnormal loading rate, a first frame loading time-consuming level, and the like.
Step one: and playing different videos in a large number of devices to obtain the play logs of the large number of devices.
Step two: a play effect evaluation value S1 of each device is calculated.
Taking one of the devices a as an example, the play effect evaluation value S1 can be calculated by the following formula:
where j is used to refer to an indicator, such as a click through rate.
b j Weights (0 to ultra) for each index score1) Dynamic adjustment can be performed according to effect recall.
Beta is a parameter, and according to the experimental evaluation effect score, the initial value is 1.
The beta acquisition process is as follows: and playing different videos in a large number of devices, acquiring user evaluation values fed back by the devices, and calculating play effect evaluation values of the devices based on the formula and the current beta value. Fitting is performed based on the user evaluation value and the play effect evaluation value, so that the value of beta is modified according to the fitting result.
y j For index scores, such as device a's abnormal load rate, click through rate, first frame load time-consuming level, etc.
Step three: according to the partial device parameters (such as operating system version, CPU level, GPU level, memory level) of each device, a large number of devices are classified into different device levels, such as high level, medium level and low level.
Step four: and carrying out average value operation on the play effect evaluation values S1 of the devices of the same device level to obtain play effect evaluation values of the same device level, and storing the play effect evaluation values of the device levels and the corresponding play effect evaluation values into a database.
Step S204, calculating popularity of each video according to the associated interaction data of each video; and establishing a third mapping relation between the video identification of each video and the corresponding popularity, and/or establishing a fourth mapping relation between the video label of each video and the corresponding popularity, wherein the video label is used for describing the characteristics of the video.
The interactive data may include a play rate, a praise ratio, a coin-in ratio, a collection ratio.
The playback completion rate is the playback completion rate of the video, that is, how many people are complete and 100% of all users who see the video. Out of 100, 30 people have seen the video, and the rate of playback is 30%. If the playback rate is low, this indicates that the video is not sufficiently attractive to the user to see the end.
The praise ratio, the ratio of praise/visitor number in the statistical period, is used as one of the judgment indexes reflecting the popularity of the video in the flow pool.
The coin ratio, the ratio of the number of coins/the number of visitors in the counting period, is used as one of judging indexes reflecting the popularity of the video in the flow pool.
The collection ratio, the ratio of collection number/visitor number in the statistics period, is used as one of judging indexes reflecting the popularity of the video in the flow pool.
For example, the popularity S2 may be calculated by the following formula:
where k is used to refer to an indicator, such as the rate of completion.
c k The weight (0-1) of each index score can be dynamically adjusted according to the recall effect.
z k The index score is, for example, the video playing rate, coin-in ratio, praise rate, collection rate and the like.
Step S206, updating the first mapping relation, the second mapping relation, the third mapping relation and the fourth mapping relation into a cache.
The storage may be in the form of Key-Value pairs (Key-Value).
The first mapping relationship, the second mapping relationship, the third mapping relationship and the fourth mapping relationship in the cache are used for being read by a processor and used for evaluating a playing quality evaluation value S of the video in the device, and the playing quality evaluation value S is obtained through the following formula:
s=ms1×s2 equation (4)
For example, a play quality evaluation value S of a video A played on a certain device B is calculated AB ：
S AB ＝M AB *S1 AB *S2 AB
M AB The matching degree between the video metadata of the video A and the device parameters of the device B is obtained;
S1 AB device class pair for device BA corresponding play effect evaluation value;
S2 AB is the popularity of video a.
The playing quality evaluation value S AB For determining whether to push video a to device B. If the playing quality evaluation value S AB Below the lowest output threshold, video a is not pushed to device B. The minimum output threshold may be custom.
The playing quality evaluation value S AB For determining an ordering of video a among the plurality of videos being pushed. For example, the play quality evaluation value S AB The higher the video a is, the more forward in the ranking, the more preferentially pushed to the user.
The play quality assessment method provided by the embodiment of the application comprises the following advantages:
(1) The method can evaluate the playing quality evaluation value of the video on the equipment in real time according to the video parameters, the equipment parameters, the interactive data and other dimensionalities, and determine whether to push the video or the ordering position of the video in a push list, thereby determining to realize the dynamic output of the video on the equipment (such as large-screen equipment). Based on the playing quality evaluation value, the playing effect of the video which is first seen by the user can be the best, so that the viewing experience of the user is improved.
(2) In the prior art, the large screen output mode of the UGC video is usually referred to the playing effect on the small screen device, and the adaptation degree of the video and the large screen device is not considered.
In other words, UGC video is not output to devices with too low a matching degree, for example, low quality video is output to high-end devices, resulting in aggravated blurring effect; or the high-quality video is output to the low-end equipment, resulting in abnormal play.
(3) Besides the matching degree between the video and the equipment, the interactive data of each video watching object and the actual effect of the equipment are further combined, and the playing quality evaluation value of the video played on the equipment is comprehensively measured.
In order to make the embodiments of the present application better and more clearly apparent, as shown in fig. 3, a specific application example is provided below.
The first, consult table one, through the weight parameter of the dynamic configuration each index of the configuration module, namely realize a i And b j And c k There is no need to restart the relevant application.
List one
Secondly, a large number of play logs of the equipment in the video playing process are obtained in real time through the monitoring platform. The play log is data generated when each device plays the video, such as a click-through rate, an abnormal loading rate and a first frame loading time-consuming level.
The play effect evaluation value of each device may be calculated by the Job offline module.
For example, each run is as follows:
1) Inquiring a play log of the day before the equipment dimension, namely a click-through rate, a loading anomaly rate and a first frame loading time-consuming grade; calculating a play effect evaluation value s1_score of each device according to the play log; device levels and device models of the respective devices are acquired, and key= { level } _ { model } _ s1_score is stored in a database. Where level represents the device class (high, medium, low) of the device, and model is the device model of the device.
The device level may be differentiated according to the memory size, the cpu core number, the operating system version, and the like.
2) The average play effect evaluation value of each device level is calculated and stored in the database as key= { level } _s1_score.
The corresponding relationship between the device class and the memory and the CPU … can be referred to as table two.
Watch II
The actual evaluation score is a subjective effect evaluation value of the video played by the user on each equipment level, and each subjective effect evaluation value can be used for mutual evidence with the average playing effect evaluation value of the corresponding equipment level.
It should be noted that the Job offline module may update the data into the cache every other day.
Thirdly, according to the interactive data of each video obtained by the monitoring platform, calculating the popularity of each video through the Job offline module, generating the mapping relation between the video identification/video label and the popularity of the video, and updating the mapping relation into a cache.
For example, each run is as follows: 1) Inquiring a tag list and interactive data of the video; 2) Calculating the popularity of each video s2_score, and storing the popularity of each video s2_score into a database in a way of key= { cid } -s2_score, wherein cid is the video identification of each video; 3) The popularity of a video tag is the average of the popularity of all videos with the tag, and is stored in a database in a key= { tag } -s2_score, and tag is the identification of each video tag. It should be noted that the Job offline module may update the data into the cache every other hour.
Example two
For various technical details (e.g., calculation formulas, etc.) in this embodiment, reference may be made to embodiment one.
Fig. 4 schematically shows a flowchart of a second video pushing method according to an embodiment of the present application. The method may be performed in the computer device 2. As shown in fig. 4, the video pushing method may include steps S400 to S406, in which:
step S400, in response to a video list request provided by a target device, determining a plurality of videos.
The plurality of videos may be randomly derived from a video pool;
the plurality of videos may also be obtained from a video pool based on the current scene (e.g., "hot") of the target device.
Step S402, determining a playing quality evaluation value of each of the plurality of videos in the target device.
Step S404, ranking the playing quality evaluation values of the videos from high to low to obtain a ranking result.
Step S406, based on the sorting result, generating a target video list and pushing the target video list to the target device, where all videos in the target video list are sorted from high to low according to respective playing quality evaluation values.
The video pushing method provided by the embodiment of the application comprises the following advantages:
And determining whether to push the video or the ordering position of the video in the push list according to the play quality evaluation value, thereby determining to realize dynamic output of the video in target equipment (such as large screen equipment). Based on the playing quality evaluation value, the playing effect of the video which is first seen by the user can be the best, so that the viewing experience of the user is improved.
As an alternative embodiment, the step S402 may include: calculating the target quality assessment value by one or more of the following parameters: the target matching degree is the matching degree between the video metadata of each video and the target equipment parameters of the target equipment; a target playing effect evaluation value which is the playing effect evaluation value of each video on the target equipment; and obtaining the target popularity according to the interactive data of each video.
In the prior art, the large-screen output mode of many videos is usually referred to the playing effect on the small-screen device, and the adaptation degree of the videos and the large-screen device is not considered, in this optional embodiment, the adaptation degree (matching degree) of the videos and the large-screen device is fully considered, and the videos with possibly poor playing effect in the large-screen device are not pushed or pushed backwards, so that the user can watch the videos with good playing effect in the large-screen device as much as possible. In other words, the video is not output to the device with too low matching degree, for example, the low-quality video is output to the high-end device, so that the blurring effect is aggravated; or the high-quality video is output to the low-end equipment, resulting in abnormal play.
In addition, besides the matching degree between the video and the equipment, the interactive data of each video watching object and the actual effect of the equipment are further combined, and the playing quality evaluation value of the video played on the equipment is comprehensively measured.
As an alternative embodiment, as shown in fig. 5, the method further includes: step S500, inquiring the mth target matching degree between the target equipment and the mth video from the cache; the buffer memory is used for storing the matching degree between each video in one or more videos and different devices in advance, the mth video is any video in the videos, and m is a positive integer larger than 0; and step S502, if the mth target matching degree between the target device and the mth video is not queried, calculating the mth target matching degree according to the target device parameter and the video meta-information of the mth video. Referring back to fig. 3, the computer device 10000 queries from the cache according to the video identifier of the mth video and the device identifier (buvid) of the target device, so as to quickly obtain the mth target matching degree. In the case of failure in the query, the target device parameters of the target device are queried according to the device identifier of the target device, and the mth target matching degree is calculated by the formula (1) as in the first embodiment. The calculated mth target matching degree not only can be used for calculating a playing quality evaluation value, but also can be updated into the cache so as to facilitate the subsequent direct access. In this optional embodiment, the mth target matching degree may be obtained efficiently by caching the query and performing real-time computation in the case of a query failure.
As an alternative embodiment, as shown in fig. 6, the method further includes: step S600, determining a target equipment grade of the target equipment according to the target equipment parameters; step S602, inquiring an mth target playing effect evaluation value of an mth video from a cache according to the target equipment grade and the target equipment model of the target equipment; the buffer memory is used for storing play effect evaluation values of one or more videos on devices with different device grades and different device models in advance, wherein the mth video is any one video in the videos, and m is a positive integer greater than 0; and step S604, if the mth target playing effect evaluation value is not queried according to the target equipment grade and the target equipment model, querying the mth target playing effect evaluation value from the cache according to the target equipment grade. Referring back to fig. 3, the computer device 10000 queries from the cache key= { level } _ { model } _ s1_score that matches both the target device class and the target device model, thereby obtaining an accurate target playback effect evaluation value. If the key = { level } _ { model } -s1_score that does not match the target device level and the target device model simultaneously, then query the key = { level } -s1_score that matches the target device level. In this optional embodiment, the target play effect evaluation value is queried accurately, and in case of failure in the accurate query, the target play effect evaluation value is queried with fuzzy, that is, the query is performed solely through the equipment level, so as to obtain the target play effect evaluation value efficiently and effectively.
As an alternative embodiment, the target device class is one of a plurality of device classes. As shown in fig. 7, the method further includes the step of acquiring in advance play effect evaluation values of respective device levels: step S700, obtaining a play log of each device, and calculating a play effect evaluation value of each device; step S702, grading is carried out according to the equipment parameters of each equipment, and the playing effect evaluation mean value of each equipment grade is calculated to obtain the mapping relation between each equipment grade and the corresponding playing effect evaluation mean value; the play effect evaluation average value of one equipment level is the average value of the play effect evaluation values of all the equipment under the equipment level. In this alternative embodiment, the calculation of the rating and play effect evaluation value may refer to embodiment one.
As an alternative embodiment, the cache is further configured to store:
the popularity of each video identifier corresponds to that of the plurality of video identifiers, and each video identifier is associated with one video;
a plurality of video tags each associated with one or more videos, respectively, each correspond to a popularity of the video tag.
In this alternative embodiment, the popularity of each video can be accurately queried through video identification.
In the event of failure of an exact query, popularity of video of one or more similar dimensions may be achieved through the video tags. The popularity of the video-based tag can be rapidly evaluated through similar videos.
As an alternative embodiment, as shown in fig. 8, the method further includes: step S800, according to the mth video identification of the mth video, inquiring the mth popularity associated with the mth video identification from the cache; step S802, if the mth popularity is not queried according to the mth video identifier, acquiring the mth popularity from the cache according to one or more video tags associated with the mth video. When the mth video has a plurality of video labels, each video label corresponds to one popularity, the highest popularity is taken as the popularity of the mth video. In this optional embodiment, the popularity of the mth video may be accurately queried, and in case of failure of the accurate query, the popularity of the mth video may be rapidly evaluated based on the video tag of the mth video.
To make the embodiments of the present application better understood, continuing with the parameter fig. 3, one specific application example is provided below.
1) The M operator firstly inquires whether the cache has the calculated matching degree according to key= { cid } _ { buvid } _ m_score, and if so, the M operator directly returns; otherwise, the video meta-information is queried in real time, the matching degree between the video meta-information and the video meta-information is calculated according to the formula (1), and then the video meta-information is written into the cache. cid represents the video identification of the video, and buvid represents the device identification of the device.
2) S1, inquiring the play effect evaluation value according to the equipment grade and the equipment model, and inquiring only by using the equipment grade if the inquiry is empty.
3) And S2, inquiring the popularity according to the video identification of the video, and inquiring the popularity by adopting a video tag (tag) of the video if the inquiry is empty. When multiple tags are associated with a video, the maximum popularity is taken.
4) And (4) calculating the playing quality evaluation value of each video in the equipment according to the formula (4) by an aggregation operator.
5) Taking the hot function as an example, when the hot video is processed, the video playing effect firstly seen by a user is optimal according to the high-to-low ordering of the playing quality evaluation values.
Example III
Fig. 9 schematically shows a block diagram of a video list pushing system according to a third embodiment of the present application. The video list pushing system may be partitioned into one or more program modules, which are stored in a storage medium and executed by one or more processors to accomplish the embodiments of the present application. Program modules in the embodiments of the present application refer to a series of computer program instruction segments capable of implementing specific functions, and the following description specifically describes the functions of each program module in the embodiment.
As shown in fig. 9, the video list pushing system 900 may include a first determining module 910, a second determining module 920, a sorting module 930, and a pushing module 940, where:
a first determining module 910, configured to determine a plurality of videos in response to a video list request provided by a target device;
a second determining module 920, configured to determine a play quality evaluation value of each video of the plurality of videos in the target device;
a ranking module 930, configured to rank the playing quality evaluation values of the videos from high to low, so as to obtain a ranking result; and
And the pushing module 940 is configured to generate a target video list based on the ranking result and push the target video list to the target device, where all videos in the target video list are ranked from high to low according to respective play quality evaluation values.
As an optional embodiment, the second determining module 920 is further configured to:
calculating the target quality assessment value by one or more of the following parameters:
the target matching degree is the matching degree between the video metadata of each video and the target equipment parameters of the target equipment;
a target playing effect evaluation value which is the playing effect evaluation value of each video on the target equipment;
And obtaining the target popularity according to the interactive data of each video.
As an optional embodiment, the system further includes a matching degree obtaining module, configured to:
inquiring the mth target matching degree between the target equipment and the mth video from the cache; the buffer memory is used for storing the matching degree between each video in one or more videos and different devices in advance, the mth video is any video in the videos, and m is a positive integer larger than 0; and
And if the mth target matching degree between the target equipment and the mth video is not queried, calculating the mth target matching degree according to the target equipment parameters and the video meta-information of the mth video.
As an optional embodiment, the system further includes a play effect evaluation value acquisition module, configured to:
determining a target equipment grade of the target equipment according to the target equipment parameters;
inquiring an mth target playing effect evaluation value of an mth video from a cache according to the target equipment grade and the target equipment model of the target equipment; the buffer memory is used for storing play effect evaluation values of one or more videos on devices with different device grades and different device models in advance, wherein the mth video is any one video in the videos, and m is a positive integer greater than 0; and
And if the mth target playing effect evaluation value is not queried according to the target equipment grade and the target equipment model, querying the mth target playing effect evaluation value from the cache according to the target equipment grade.
As an alternative embodiment, the target device class is one of a plurality of device classes;
the play effect evaluation value acquisition module is further configured to:
obtaining a play log of each device, and calculating a play effect evaluation value of each device;
grading according to the equipment parameters of each equipment, calculating the playing effect evaluation mean value of each equipment grade, and obtaining the mapping relation between each equipment grade and the corresponding playing effect evaluation mean value; the play effect evaluation average value of one equipment level is the average value of the play effect evaluation values of all the equipment under the equipment level.
As an alternative embodiment, the cache is further configured to store:
the popularity of each video identifier corresponds to that of the plurality of video identifiers, and each video identifier is associated with one video;
a plurality of video tags each associated with one or more videos, respectively, each correspond to a popularity of the video tag.
As an alternative embodiment, the system further comprises a popularity acquisition module for:
According to the mth video identification of the mth video, inquiring the mth popularity associated with the mth video identification from the cache;
and if the mth popularity is not inquired according to the mth video identification, acquiring the mth popularity from the cache according to one or more video tags associated with the mth video.
Example IV
Fig. 10 schematically shows a block diagram of a play quality assessment system according to a fourth embodiment of the present application. The video list pushing system may be partitioned into one or more program modules, which are stored in a storage medium and executed by one or more processors to accomplish the embodiments of the present application. Program modules in the embodiments of the present application refer to a series of computer program instruction segments capable of implementing specific functions, and the following description specifically describes the functions of each program module in the embodiment.
As shown in fig. 10, the play quality assessment system 1000 can include a first setup module 1010, a second setup module 1020, a third setup module 1030, and an update module 1040, wherein:
a first establishing module 1010, configured to obtain a plurality of matching degrees according to the video metadata of each video and the device parameters of each device, and establish a first mapping relationship between each matching degree, the corresponding video, and the corresponding device; each matching degree is calculated according to video metadata of one video and equipment parameters of one equipment;
A second establishing module 1020, configured to determine a device model and a device class of each device according to the device parameters of each device; determining a play effect evaluation value of each device according to the play log of each device; establishing a second mapping relation between the equipment model, the equipment grade and the corresponding play effect evaluation value of each equipment;
a third establishing module 1030, configured to calculate popularity of each video according to the interactive data associated with each video; establishing a third mapping relation between the video identification of each video and the corresponding popularity, and/or a fourth mapping relation between the video label of each video and the corresponding popularity, wherein the video label is used for describing the characteristics of the video;
an updating module 1040, configured to update the first mapping relationship, the second mapping relationship, the third mapping relationship, and the fourth mapping relationship to a cache;
the first mapping relation, the second mapping relation, the third mapping relation and the fourth mapping relation which are positioned in the cache are used for being read by a processor and used for evaluating the playing quality evaluation value of the video in the equipment.
As an alternative embodiment, the system may further comprise a fourth setup module for
Establishing a fifth mapping relation between each equipment level and the corresponding playing effect evaluation mean value; the playing effect evaluation average value of one equipment level is the average value of the playing effect evaluation values of all the equipment under the equipment level.
Example five
Fig. 11 schematically shows a hardware architecture diagram of a computer device 2 adapted to implement a video list pushing method according to a fifth embodiment of the present application. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with instructions set or stored in advance. For example, it may be a rack server, a blade server, a tower server, or a rack server (including an independent server or a server cluster composed of a plurality of servers), etc. As shown in fig. 11, the computer device 2 includes at least, but is not limited to: the memory 10010, processor 10020, network interface 10030 may be communicatively linked to each other via a system bus. Wherein:
memory 10010 includes at least one type of computer-readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 10010 may be an internal storage module of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 10010 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 2. Of course, the memory 10010 may also include both an internal memory module of the computer device 2 and an external memory device thereof. In this embodiment, the memory 10010 is typically used for storing an operating system installed on the computer device 2 and various application software, such as program codes of a video list pushing method. In addition, the memory 10010 may be used to temporarily store various types of data that have been output or are to be output.
The processor 10020 may be a central processing unit (Central Processing Unit, simply CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 10020 is generally configured to control overall operation of the computer device 2, such as performing control and processing related to data interaction or communication with the computer device 2, and the like. In this embodiment, the processor 10020 is configured to execute program codes or process data stored in the memory 10010.
The network interface 10030 may comprise a wireless network interface or a wired network interface, which network interface 10030 is typically used to establish a communication link between the computer device 2 and other computer devices. For example, the network interface 10030 is used to connect the computer device 2 with an external device through a network, establish a data transmission channel and a communication link between the computer device 2 and the external device, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a global system for mobile communications (Global System of Mobile communication, abbreviated as GSM), wideband code division multiple access (Wideband Code Division Multiple Access, abbreviated as WCDMA), a 4G network, a 5G network, bluetooth (Bluetooth), wi-Fi, etc.
It should be noted that fig. 11 only shows a computer device having components 10010-10030, but it should be understood that not all of the illustrated components are required to be implemented, and more or fewer components may be implemented instead.
In this embodiment, the video list pushing method stored in the memory 10010 may be further divided into one or more program modules and executed by one or more processors (the processor 10020 in this embodiment) to complete the embodiments of the present application.
Example six
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the video list pushing method in the embodiments.
In this embodiment, the computer-readable storage medium includes a flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the computer readable storage medium may be an internal storage unit of a computer device, such as a hard disk or a memory of the computer device. In other embodiments, the computer readable storage medium may also be an external storage device of a computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), etc. that are provided on the computer device. Of course, the computer-readable storage medium may also include both internal storage units of a computer device and external storage devices. In this embodiment, the computer readable storage medium is typically used to store an operating system and various types of application software installed on a computer device, such as program codes of the video list pushing method in the embodiment. Furthermore, the computer-readable storage medium may also be used to temporarily store various types of data that have been output or are to be output.
It will be apparent to those skilled in the art that the modules or steps of the embodiments of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may alternatively be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than what is shown or described, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.
It should be noted that the foregoing is only a preferred embodiment of the present application, and is not intended to limit the scope of the patent protection of the present application, and all equivalent structures or equivalent processes using the descriptions and the contents of the present application or direct or indirect application to other related technical fields are included in the scope of the patent protection of the present application.
Claims (12)
1. A video list pushing method, the method comprising:
determining a plurality of videos in response to a video list request provided by a target device;
determining a play quality assessment value of each of the plurality of videos in the target device;
ranking the playing quality evaluation values of the videos from high to low to obtain ranking results; and
Generating a target video list based on the sorting result and pushing the target video list to the target device, wherein all videos in the target video list are sorted from high to low according to respective playing quality evaluation values;
the playing quality evaluation value is obtained by calculating based on a target matching degree, wherein the target matching degree of the mth video is the matching degree between video metadata of the mth video and target equipment parameters of the target equipment, and the target matching degree is obtained by inquiring from a cache or is obtained by calculating according to the target equipment parameters and the video metadata of the mth video.
2. The video list pushing method according to claim 1, wherein the determining a play quality evaluation value of each of the plurality of videos in the target device includes:
Calculating a target quality assessment value by one or more of the following parameters:
the target matching degree is the matching degree between the video metadata of each video and the target equipment parameters of the target equipment;
a target playing effect evaluation value which is the playing effect evaluation value of each video on the target equipment;
and obtaining the target popularity according to the interactive data of each video.
3. The video list pushing method according to claim 2, further comprising:
inquiring the mth target matching degree between the target equipment and the mth video from the cache; the buffer memory is used for storing the matching degree between each video in one or more videos and different devices in advance, the mth video is any video in the videos, and m is a positive integer larger than 0; and
And if the mth target matching degree between the target equipment and the mth video is not queried, calculating the mth target matching degree according to the target equipment parameters and the video meta-information of the mth video.
4. The video list pushing method of claim 2, wherein the method further comprises:
Determining a target equipment grade of the target equipment according to the target equipment parameters;
inquiring an mth target playing effect evaluation value of an mth video from a cache according to the target equipment grade and the target equipment model of the target equipment; the buffer memory is used for storing play effect evaluation values of one or more videos on devices with different device grades and different device models in advance, wherein the mth video is any one video in the videos, and m is a positive integer greater than 0; and
And if the mth target playing effect evaluation value is not queried according to the target equipment grade and the target equipment model, querying the mth target playing effect evaluation value from the cache according to the target equipment grade.
5. The video list pushing method of claim 4 wherein the target device level is one of a plurality of device levels; the method further comprises the steps of obtaining play effect evaluation values of all equipment levels in advance:
obtaining a play log of each device, and calculating a play effect evaluation value of each device;
grading according to the equipment parameters of each equipment, calculating the playing effect evaluation mean value of each equipment grade, and obtaining the mapping relation between each equipment grade and the corresponding playing effect evaluation mean value; the play effect evaluation average value of one equipment level is the average value of the play effect evaluation values of all the equipment under the equipment level.
6. The video list pushing method according to any one of claims 3 to 5, wherein the buffering is further configured to store:
the popularity of each video identifier corresponds to that of the plurality of video identifiers, and each video identifier is associated with one video;
a plurality of video tags each associated with one or more videos, respectively, each correspond to a popularity of the video tag.
7. The video list pushing method of claim 6, further comprising:
according to the mth video identification of the mth video, inquiring the mth popularity associated with the mth video identification from the cache;
and if the mth popularity is not inquired according to the mth video identification, acquiring the mth popularity from the cache according to one or more video tags associated with the mth video.
8. A video list pushing system, the system comprising:
a first determining module, configured to determine a plurality of videos in response to a video list request provided by a target device;
a second determining module, configured to determine a play quality evaluation value of each of the plurality of videos in the target device;
The sorting module is used for sorting the playing quality evaluation values of the videos from high to low so as to obtain a sorting result; and
The pushing module is used for generating a target video list based on the sorting result and pushing the target video list to the target equipment, and all videos in the target video list are sorted from high to low according to respective playing quality evaluation values;
the playing quality evaluation value is obtained by calculating based on a target matching degree, wherein the target matching degree of the mth video is the matching degree between video metadata of the mth video and target equipment parameters of the target equipment, and the target matching degree is obtained by inquiring from a cache or is obtained by calculating according to the target equipment parameters and the video metadata of the mth video.
9. A play quality evaluation method, comprising:
obtaining a plurality of matching degrees according to video metadata of each video and equipment parameters of each equipment, and establishing a first mapping relation among each matching degree, corresponding video and corresponding equipment; each matching degree is calculated according to video metadata of one video and equipment parameters of one equipment;
Determining the equipment model and equipment grade of each equipment according to the equipment parameters of each equipment; determining a play effect evaluation value of each device according to the play log of each device; establishing a second mapping relation between the equipment model, the equipment grade and the corresponding play effect evaluation value of each equipment;
calculating popularity of each video according to the interactive data associated with each video; establishing a third mapping relation between the video identification of each video and the corresponding popularity, and/or a fourth mapping relation between the video label of each video and the corresponding popularity, wherein the video label is used for describing the characteristics of the video;
updating the first mapping relation, the second mapping relation, the third mapping relation and the fourth mapping relation into a cache;
the first mapping relation, the second mapping relation, the third mapping relation and the fourth mapping relation which are positioned in the cache are used for being read by a processor and used for evaluating the playing quality evaluation value of the video in the equipment.
10. The play quality assessment method according to claim 9, further comprising:
establishing a fifth mapping relation between each equipment level and the corresponding playing effect evaluation mean value; the playing effect evaluation average value of one equipment level is the average value of the playing effect evaluation values of all the equipment under the equipment level.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor is adapted to implement the steps of the method of any one of claims 1 to 7 and 9 to 10 when the computer program is executed.
12. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program executable by at least one processor to cause the at least one processor to perform the steps of the method of any one of claims 1 to 7 and 9 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111412110.5A CN114095763B (en) | 2021-11-25 | 2021-11-25 | Video list pushing method and play quality assessment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111412110.5A CN114095763B (en) | 2021-11-25 | 2021-11-25 | Video list pushing method and play quality assessment method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114095763A CN114095763A (en) | 2022-02-25 |
| CN114095763B true CN114095763B (en) | 2024-03-12 |
Family
ID=80304398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111412110.5A Active CN114095763B (en) | 2021-11-25 | 2021-11-25 | Video list pushing method and play quality assessment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114095763B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011217209A (en) * | 2010-03-31 | 2011-10-27 | Sony Corp | Electronic apparatus, content recommendation method, and program |
| US8813156B1 (en) * | 2012-05-22 | 2014-08-19 | Google Inc. | Resolution recommendation for displaying content items |
| CN104219575A (en) * | 2013-05-29 | 2014-12-17 | 酷盛(天津）科技有限公司 | Related video recommending method and system |
| CN109729433A (en) * | 2019-01-22 | 2019-05-07 | 北京奇艺世纪科技有限公司 | A kind of video playing appraisal procedure and device |
| CN111125429A (en) * | 2019-12-20 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Video pushing method and device and computer readable storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130046623A1 (en) * | 2011-08-17 | 2013-02-21 | Telefonaktiebolaget L M Ericsson (Publ) | Method For Providing a Recommendation, Recommender System, and Recommender Computer Program Product |
| US8719261B2 (en) * | 2011-12-02 | 2014-05-06 | Verizon Patent And Licensing Inc. | Dynamic catalog ranking |
| US10834406B2 (en) * | 2016-12-12 | 2020-11-10 | Netflix, Inc. | Device-consistent techniques for predicting absolute perceptual video quality |
| KR20200079913A (en) * | 2018-12-26 | 2020-07-06 | 삼성전자주식회사 | Method for dynamically recommending catalog and electonic device therof |
-
2021
- 2021-11-25 CN CN202111412110.5A patent/CN114095763B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011217209A (en) * | 2010-03-31 | 2011-10-27 | Sony Corp | Electronic apparatus, content recommendation method, and program |
| US8813156B1 (en) * | 2012-05-22 | 2014-08-19 | Google Inc. | Resolution recommendation for displaying content items |
| CN104219575A (en) * | 2013-05-29 | 2014-12-17 | 酷盛(天津）科技有限公司 | Related video recommending method and system |
| CN109729433A (en) * | 2019-01-22 | 2019-05-07 | 北京奇艺世纪科技有限公司 | A kind of video playing appraisal procedure and device |
| CN111125429A (en) * | 2019-12-20 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Video pushing method and device and computer readable storage medium |
Non-Patent Citations (3)
| Title |
|---|
| IceBreaker: Solving Cold Start Problem for Video Recommendation Engines;Yaman Kumar 等;《IEEE》;全文 * |
| 个性化电影主题播单推荐系统的设计与实现;张雪纯;《中国优秀硕士学位论文全文数据库电子期刊》;全文 * |
| 面向UHDTV的多分辨率视频显示质量评估研究;赵娜;宋佳润;邹文杰;;液晶与显示(10);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114095763A (en) | 2022-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ghadiyaram et al. | A subjective and objective study of stalling events in mobile streaming videos | |
| Sinno et al. | Large-scale study of perceptual video quality | |
| He et al. | Rubiks: Practical 360-degree streaming for smartphones | |
| CN110121098B (en) | Video playing method and device, storage medium and electronic device | |
| KR101571443B1 (en) | Video Recommendation based on Video Co-occurrence Statistics | |
| US20220232222A1 (en) | Video data processing method and apparatus, and storage medium | |
| Li et al. | A cost-constrained video quality satisfaction study on mobile devices | |
| CN109120949B (en) | Video message pushing method, device, equipment and storage medium for video set | |
| US20170318317A1 (en) | Method, device, and server for producing video frame set | |
| CN112291634B (en) | Video processing method and device | |
| CN111858969B (en) | Multimedia data recommendation method, device, computer equipment and storage medium | |
| Yu et al. | Subjective quality assessment of user-generated content gaming videos | |
| CN106980666B (en) | Method and device for recommending video | |
| CN114598919A (en) | Video processing method, video processing device, computer equipment and storage medium | |
| CN112714338B (en) | Video transmission method, video playing method, video transmission device, video playing device, computer equipment and storage medium | |
| CN114095763B (en) | Video list pushing method and play quality assessment method | |
| CN113296666A (en) | Anchor exposure data reporting method and device, terminal equipment and storage medium | |
| Leszczuk | Optimising task-based video quality: A journey from subjective psychophysical experiments to objective quality optimisation | |
| CN112804566A (en) | Program recommendation method, device and computer readable storage medium | |
| CN115190357A (en) | Video abstract generation method and device | |
| US10764578B2 (en) | Bit rate optimization system and method | |
| US20230142432A1 (en) | Content Generating Device, Content Distribution System, Content Generating Method, And Content Generating Program | |
| Xin et al. | User-centric QoE model of visual perception for mobile videos | |
| US20240236436A9 (en) | Bullet-screen comment display | |
| US20240137619A1 (en) | Bullet-screen comment display |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |