CN109729433B - Video playing evaluation method and device - Google Patents

Video playing evaluation method and device Download PDF

Info

Publication number
CN109729433B
CN109729433B CN201910058188.8A CN201910058188A CN109729433B CN 109729433 B CN109729433 B CN 109729433B CN 201910058188 A CN201910058188 A CN 201910058188A CN 109729433 B CN109729433 B CN 109729433B
Authority
CN
China
Prior art keywords
factor
playing
time
target
value
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
Application number
CN201910058188.8A
Other languages
Chinese (zh)
Other versions
CN109729433A (en
Inventor
程亚男
胡嘉伟
涂龙飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing QIYI Century Science and Technology Co Ltd
Original Assignee
Beijing QIYI Century Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing QIYI Century Science and Technology Co Ltd filed Critical Beijing QIYI Century Science and Technology Co Ltd
Priority to CN201910058188.8A priority Critical patent/CN109729433B/en
Publication of CN109729433A publication Critical patent/CN109729433A/en
Application granted granted Critical
Publication of CN109729433B publication Critical patent/CN109729433B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The embodiment of the invention provides a video playing evaluation method and a video playing evaluation device, wherein the method comprises the following steps: acquiring the grade value of the definition grade factor of the played video and the numerical value of the target playing factor; determining a target evaluation function corresponding to the obtained grade value from the corresponding relation between each grade value and the evaluation function; and obtaining an evaluation result of the played video based on the target evaluation function and the value of the target playing factor. According to the technical scheme, the definition grade factor is added in the evaluation process to serve as a non-service quality characteristic, the service quality characteristic of the playing interaction factor and/or the playing experience factor is also included, and the evaluation is more comprehensive compared with the evaluation in the prior art based on the non-service quality characteristic and the service quality characteristic. The definition grade factor has correlation with the playing interaction factor and the playing experience factor, and the playing interaction factor and the playing experience factor do not have correlation, so that the number of the cross features is controlled, and the increase degree of the evaluation complexity is further controlled.

Description

Video playing evaluation method and device
Technical Field
The invention relates to the technical field of multimedia, in particular to a video playing evaluation method and device.
Background
Browsing videos on video websites is a day-to-day and numerous video websites offer more choices to users. For each video network, how to attract users and retain users becomes a key issue. The user experience is an important factor for user retention, and only when the user experience is improved, the user experience is given an opportunity to retain more users.
In order to improve the user Experience, the viewing Experience Of the user in the process Of viewing the video, namely, the QoE (Quality Of Experience), needs to be known, and then improvement is performed in a targeted manner. At present, the following two methods are mainly used for evaluating user experience, the first method is to display the playing evaluation of each time after the video is played, and the user fills in the evaluation according to the user experience, and the method is simple to operate. However, in this way, the feedback rate of the user is very low, and the feedback evaluation is influenced by subjective feeling, and lacks of certain objectivity. The second way is to evaluate the playing experience through the pause index, which has a certain objectivity, generally speaking, more pauses and longer pause time in the playing process will result in lower evaluation, and less pauses or even no pauses will result in higher evaluation. Furthermore, since the QoE is expressed by using only the stuck metric as a unique QoS (Quality Of service), the evaluation is simpler.
However, the inventor finds that the prior art has at least the following problems in the process of implementing the invention: for the second mode, only the influence of the service quality characteristics is reflected in the evaluation process, and the influence of the non-service quality characteristics is lacked, so that the evaluation is not comprehensive. If the non-service quality features are added, cross features need to be added in the evaluation process due to the correlation among the features, and the addition of the cross features increases the complexity of the evaluation. For example, if the qos features include a and B, then the non-qos feature C is added, and there is a correlation between A, B and C, then in addition to the evaluations A, B and C, the cross features a × B, B × C and C × a need to be evaluated, which greatly increases the complexity of the evaluation.
Disclosure of Invention
Embodiments of the present invention provide a method and an apparatus for evaluating video playback, so as to evaluate a more comprehensive evaluation and control an increase degree of complexity of the evaluation, compared with the prior art. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a video playing evaluation method, where the method includes:
acquiring a grade value of a definition grade factor of a played video and a numerical value of a target playing factor, wherein the target playing factor comprises a playing interaction factor and/or a playing experience factor, the playing interaction factor and the playing experience factor have no correlation, and the definition grade factor and the target playing factor have correlation;
determining an evaluation function corresponding to the obtained grade value from the corresponding relation between each grade value of the definition grade factor and the evaluation function as a target evaluation function, wherein the evaluation function is a linear function taking a playing interaction factor and/or the playing experience factor as a variable;
and obtaining a result of the target evaluation function based on the target evaluation function and the determined value of the target playing factor, and determining the result as an evaluation result of the played video.
Optionally, the obtaining a rating value of a sharpness rating factor of a played video includes:
acquiring the code rate of a played video and the playing time of the video with each code rate;
calculating the average code rate of the played video based on the obtained code rate and the playing time;
and acquiring a grade value corresponding to the average code rate from a preset grade factor corresponding relation to serve as the grade value of the played video, wherein the grade factor corresponding relation records the corresponding relation between each grade value of the definition grade factor and the code rate.
Optionally, determining, from a correspondence between each rank value of the sharpness rank factor and an evaluation function, an evaluation function corresponding to the obtained rank value as a target evaluation function includes:
acquiring a preset segmented evaluation function:
Figure BDA0001953257320000021
wherein h is an objective evaluation function, hiThe evaluation function is an evaluation function with the grade value of i, delta (i) is an activation function corresponding to the grade value of i, the value of the activation function is 1 when the activation function is activated, and the value of the activation function is 0 when the activation function is not activated;
and activating the activation function of the acquired grade value to obtain the target evaluation function.
Optionally, when the target playing factor is the playing interaction factor, the playing interaction factor includes a ratio of playing start time to playing start time, and the evaluation function is a linear function with the ratio of playing start time to playing start time as a variable;
the obtaining a result of the target evaluation function based on the target evaluation function and the obtained value of the target playing factor, and determining the result as an evaluation result of the played video includes:
obtaining an evaluation result of the played video according to the obtained value of the broadcast start time consumption and the value of the broadcast start time consumption ratio by using the following objective evaluation function:
h＝w1x1+w2x2+C1
wherein h is the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the time consumed for the broadcast, C1Is a constant term.
Optionally, when the target playback factor is the playback experience factor, the playback experience factor includes a stuck time, a stuck time duration, a stuck frequency, and a stuck time length ratio, and the evaluation function is a linear function having the stuck time, the stuck time duration, the stuck frequency, and the stuck time length ratio as variables;
the obtaining a result of the target evaluation function based on the target evaluation function and the obtained value of the target playing factor, and determining the result as an evaluation result of the played video includes:
obtaining an evaluation result of the played video according to the obtained numerical value of each playing experience factor by using the following target evaluation function:
h＝θ1z1+θ2z2+θ3z3+θ4z4+C2
wherein h is the evaluation result of the played video, z1Is the number of caltons, z2Is the duration of the stuck time, z3For the frequency of said stuck, z4Is the ratio of the length of the Katon time, theta1Is a coefficient of the number of said caltons, θ2Is a coefficient of the length of the stuck time, theta3Is the coefficient of the Cartesian frequency, θ4Is the coefficient of the Katon time length ratio, C2Is a constant term.
Optionally, when the target playback factor includes the playback interaction factor and the playback experience factor, the playback interaction factor includes a ratio of a start-up playback time to a start-up playback time, and the playback experience factor includes a ratio of a holdover time, a holdover frequency, and a holdover time, wherein the evaluation function is a linear function having the start-up playback time, the holdover frequency, and the holdover time as variables;
the obtaining a result of the target evaluation function based on the target evaluation function and the obtained value of the target playing factor, and determining the result as an evaluation result of the played video includes:
calculating an evaluation result of the played video according to the acquired numerical values of the playing interaction factors and the acquired numerical values of the playing experience factors by using the following target evaluation functions:
h＝w1x1+w2x2+θ1z1+θ2z2+θ3z3+θ4z4+C3
wherein h isrFor the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the elapsed time of the broadcast, z1Is the number of caltons, z2Is the duration of the stuck time, z3For the frequency of said stuck, z4Is the ratio of the length of the Katon time, thetar1Is a coefficient of the number of said caltons, θ2Is a coefficient of the length of the stuck time, theta3Is the coefficient of the Cartesian frequency, θ4Is the coefficient of the Katon time length ratio, C3Is a constant term.
In a second aspect, an embodiment of the present invention provides a video playback evaluation apparatus, where the apparatus includes:
the acquisition module is used for acquiring the grade value of the definition grade factor of the played video and the numerical value of the target playing factor; the target playing factor comprises a playing interaction factor and/or a playing experience factor, the playing interaction factor and the playing experience factor have no correlation, and the definition level factor and the target playing factor have correlation;
a determining module, configured to determine, from a correspondence between each level value of the clarity level factor and an evaluation function, an evaluation function corresponding to the obtained level value as a target evaluation function, where the evaluation function is a linear function in which a play interaction factor and/or the play experience factor is used as a variable;
and the obtaining module is used for obtaining a result of the target evaluation function based on the target evaluation function and the determined numerical value of the target playing factor, and determining the result as an evaluation result of the played video.
Optionally, the obtaining module is specifically configured to:
acquiring the code rate of a played video and the playing time of the video with each code rate;
calculating the average code rate of the played video based on the obtained code rate and the playing time;
and acquiring a grade value corresponding to the average code rate from a preset grade factor corresponding relation to serve as the grade value of the played video, wherein the grade factor corresponding relation records the corresponding relation between each grade value of the definition grade factor and the code rate.
Optionally, the determining module is specifically configured to:
acquiring a preset segmented evaluation function:
Figure BDA0001953257320000051
wherein h is an objective evaluation function, hiThe evaluation function is an evaluation function with the grade value of i, delta (i) is an activation function corresponding to the grade value of i, the value of the activation function is 1 when the activation function is activated, and the value of the activation function is 0 when the activation function is not activated;
and activating the activation function of the acquired grade value to obtain the target evaluation function.
Optionally, when the target playing factor is the playing interaction factor, the playing interaction factor includes a ratio of the play-up time to the play-up time, and the evaluation function is a linear function with the ratio of the play-up time to the play-up time as a variable;
the obtaining module is specifically configured to:
obtaining an evaluation result of the played video according to the obtained value of the broadcast start time consumption and the value of the broadcast start time consumption ratio by using the following objective evaluation function:
h＝w1x1+w2x2+C1
wherein h is the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the time consumed for the broadcast, C1Is a constant term.
Optionally, when the target playback factor is the playback experience factor, the playback experience factor includes a stuck time, a stuck time duration, a stuck frequency, and a stuck time length ratio, and the evaluation function is a linear function having the stuck time, the stuck time duration, the stuck frequency, and the stuck time length ratio as variables;
the obtaining module is specifically configured to:
obtaining an evaluation result of the played video according to the obtained numerical value of each playing experience factor by using the following target evaluation function:
h＝θ1z1+θ2z2+θ3z3+θ4z4+C2
wherein h is the evaluation result of the played video, z1Is the number of caltons, z2Is the duration of the stuck time, z3For the frequency of said stuck, z4Is the ratio of the length of the Katon time, theta1Is a coefficient of the number of said caltons, θ2Is a coefficient of the length of the stuck time, theta3Is the coefficient of the Cartesian frequency, θ4Is the coefficient of the Katon time length ratio, C2Is a constant term.
Optionally, when the target playback factor includes the playback interaction factor and the playback experience factor, the playback interaction factor includes a ratio of a playback start time to a playback start time, and the playback experience factor includes a ratio of a pause time, a pause frequency, and a pause time, and the evaluation function is a linear function having the ratio of the playback start time, the pause frequency, and the pause time as variables;
the obtaining module is specifically configured to:
calculating an evaluation result of the played video according to the acquired numerical values of the playing interaction factors and the acquired numerical values of the playing experience factors by using the following target evaluation functions:
h＝w1x1+w2x2+θ1z1+θ2z2+θ3z3+θ4z4+C3
wherein h isrFor the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the elapsed time of the broadcast, z1Is the cardNumber of times of pause, z2Is the duration of the stuck time, z3For the frequency of said stuck, z4Is the ratio of the length of the Katon time, thetar1Is a coefficient of the number of said caltons, θ2Is a coefficient of the length of the stuck time, theta3Is the coefficient of the Cartesian frequency, θ4Is the coefficient of the Katon time length ratio, C3Is a constant term.
In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor and the communication interface complete communication between the memory and the processor through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing any one of the video playing evaluation method steps when executing the program stored in the memory.
In yet another aspect of the present invention, there is also provided a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to execute any of the above-described video playback evaluation methods.
In another aspect of the present invention, the present invention also provides a computer program product containing instructions, which when run on a computer, causes the computer to execute any of the above-mentioned video playback evaluation methods.
In the technical scheme provided by the embodiment of the invention, the grade value of the definition grade factor of the played video and the numerical value of the target playing factor are obtained; determining an evaluation function corresponding to the obtained grade value from the corresponding relation between each grade value of the definition grade factor and the evaluation function as a target evaluation function; and obtaining a result of the target evaluation function based on the target evaluation function and the determined value of the target playing factor, and determining the result as an evaluation result of the played video. According to the technical scheme provided by the embodiment of the invention, the definition grade factor is added in the evaluation process as the non-service quality characteristic, and in addition, the service quality characteristic comprising the playing interaction factor and/or the playing experience factor is also added, and the evaluation is more comprehensive based on the non-service quality characteristic and the service quality characteristic compared with the prior art. And the definition grade factor has correlation with the playing interaction factor and the playing experience factor respectively, and the playing interaction factor and the playing experience factor do not have correlation, so that the number of the added cross features is controlled, the complexity of evaluation is avoided being greatly increased, and the increase degree of the complexity is controlled.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
Fig. 1 is a flowchart of a video playing evaluation method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a video playback evaluation apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
Compared with the prior art, in order to achieve the purpose of evaluating more comprehensively and controlling the increase degree of the evaluation complexity, the embodiment of the invention provides a video playing evaluation method and a video playing evaluation device, wherein the video playing evaluation method comprises the following steps:
determining the grade value of the definition grade factor of the played video and the numerical value of the target playing factor; the target playing factor comprises a playing interaction factor and/or a playing experience factor, the playing interaction factor and the playing experience factor are not related, and the definition level factor and the target playing factor are related;
determining an evaluation function corresponding to the determined grade value from the corresponding relation between each grade value of the definition grade factor and the evaluation function, wherein the evaluation function is a linear function taking the playing interaction factor and/or the playing experience factor as a variable;
and obtaining a result of the target evaluation function based on the target evaluation function and the determined value of the target playing factor, and determining the result as the evaluation result of the played video.
In the technical scheme provided by the embodiment of the invention, the grade value of the definition grade factor of the played video and the numerical value of the target playing factor are obtained; determining an evaluation function corresponding to the obtained grade value from the corresponding relation between each grade value of the definition grade factor and the evaluation function as a target evaluation function; and obtaining a result of the target evaluation function based on the target evaluation function and the determined value of the target playing factor, and determining the result as an evaluation result of the played video. According to the technical scheme provided by the embodiment of the invention, the definition grade factor is added in the evaluation process as the non-service quality characteristic, and in addition, the service quality characteristic comprising the playing interaction factor and/or the playing experience factor is also added, and the evaluation is more comprehensive based on the non-service quality characteristic and the service quality characteristic compared with the prior art. And the definition grade factor has correlation with the playing interaction factor and the playing experience factor respectively, and the playing interaction factor and the playing experience factor do not have correlation, so that the number of the added cross features is controlled, the complexity of evaluation is avoided being greatly increased, and the increase degree of the complexity is controlled.
First, a video playing evaluation method provided by an embodiment of the present invention is described below, as shown in fig. 1, the video playing evaluation method provided by the embodiment of the present invention includes the following steps.
S101, obtaining the grade value of the definition grade factor of the played video and the numerical value of the target playing factor.
The sharpness level factor is a feature that evaluates the sharpness of a played video. Based on the fact that the definition is a visual experience in user experience, the definition has a large influence on user evaluation, and the definition grade factor is used as a main factor influencing QoE. That is, in the evaluation process, the influence of the sharpness grade factor is considered preferentially, and the influence of other factors is considered on the basis of the sharpness grade factor.
The grade of the definition grade factor is preset, the grade division can be self-defined, and each grade represents the definition degree of the video. For example, the sharpness may be divided into 11 levels, where level 0 indicates the lowest sharpness and level 11 indicates the highest sharpness. In addition, the basis of the grade division can also be set by a user, for example, the grade division can be performed according to the code rate of the video, or the grade division can be performed according to the resolution of the video. The definition level may be divided according to other reasonable factors besides the above two factors, and is not limited herein.
In one embodiment, obtaining the level value of the sharpness level factor of the played video may include the following steps.
And acquiring the code rate of the played video and the playing time of the video with each code rate. The played video may be a video with only one bitrate, or may be a video with multiple bitrates.
When the played video is only a video with a code rate, the duration of the played video is the duration of the video with the code rate. For example, if the playing time of the played video is 3 minutes and the played video is a video with a code rate of 600, the code rate of the played video is 600, and the time of the video with the code rate is 3 minutes.
When the played video comprises videos with various code rates, each code rate in the played video can be obtained, and the playing time length of the video with each code rate is determined. For example, if the duration of the played video is 5 minutes, wherein the code rate of the video in 3 minutes is 600, and the code rate of the video in 2 minutes is 500, the obtained code rates include 500 and 600, and it can also be determined that the duration of the video with the code rate of 500 is 2 minutes, and the duration of the video with the code rate of 600 is 3 minutes.
After the code rate and the playing time of the video with each code rate are obtained, the average code rate of the played video can be calculated based on the obtained code rate and the obtained playing time. In one implementation, each obtained code rate is multiplied by the playing duration of the video corresponding to the code rate, so that each code rate can correspondingly obtain a product, the obtained products are summed, and the obtained summation result is divided by the total duration of the played video, so that the average code rate can be obtained.
For example, if the total duration of the played video is 5 minutes, wherein the bitrate of the video for 3 minutes is 600 and the bitrate of the video for another 2 minutes is 500, the average bitrate can be calculated according to the following equation:
Figure BDA0001953257320000101
the average code rate can be calculated as 560 by the above formula.
After the average bitrate for playing the video is calculated, a rank value corresponding to the average bitrate can be determined from the preset rank factor correspondence as a rank value of the played video.
And recording the corresponding relation between each grade value of the definition grade factor and the code rate in the grade factor corresponding relation. In one implementation, each level value in the level factor correspondence corresponds to a code rate range, that is, the code rates within the code rate range all correspond to the level value.
For example, the definition is divided into 10 levels, which are level 0, level 1, level 2, level 3, level 4, level 5, level 6, level 7, level 8 and level 9, where, in the level factor correspondence relationship, the code rate range corresponding to level 0 is (0, 235), the code rate range corresponding to level 1 is [235, 375), the code rate range corresponding to level 2 is [375, 1050), the code rate range corresponding to level 3 is [1050, 1750 ], the code rate range corresponding to level 4 is [1750, 2350 ], the code rate range corresponding to level 5 is [2350, 4300), the code rate range corresponding to level 6 is [4300, 5800), the code rate range corresponding to level 7 is [5800, 7000, 8000), the code rate range corresponding to level 8 is [8000, 8000), and the code rate range corresponding to level 9 is [8000, 7000 infinity). Wherein (0, 235) represents a numerical range of more than 0 and less than 235, [235, 375) represents a numerical range of more than or equal to 235 and less than 375, and [8000, + ∞ ] represents a numerical range of more than or equal to 8000. Then, based on the above-mentioned level factor correspondence relationship, when the average bitrate is 560 and the corresponding level value is 2, it may be determined that the level value of the played video is 2.
The target playing factor may include a playing interaction factor and/or a playing experience factor, where the playing interaction factor may include a seek behavior, a play start time consumption ratio, and the like, where the seek behavior refers to a behavior of a user dragging a progress bar in a video playing process. The playing experience factors may include the number of times of pause, the duration of pause, the frequency of pause, the duration of pause, etc.
It can be considered that the evaluation of the played video includes the following three cases: in the first case, the intelligibility rating factor and the play interaction factor are evaluated, the intelligibility rating factor having a correlation with the play interaction factor. In the second case, the intelligibility rating factor and the playing experience factor are evaluated, and the intelligibility rating factor and the playing experience factor have a correlation. And in the third situation, the definition grade factor, the playing interaction factor and the playing experience factor are evaluated, the definition grade factor has correlation with the playing interaction factor and the playing experience factor respectively, and the playing interaction factor and the playing experience factor do not have correlation. In a third case, the cross-feature only includes: the cross characteristics of the definition grade factor and the playing interaction factor and the cross characteristics of the definition grade factor and the playing experience factor reduce the complexity of calculation to a certain extent.
The relevance of the definition level factor and the playing interaction factor and the relevance of the definition level factor and the playing experience factor can be linear relevance.
S102, determining an evaluation function corresponding to the obtained grade value from the corresponding relation between each grade value of the definition grade factor and the evaluation function, and taking the evaluation function as a target evaluation function.
The evaluation function is a linear function with the playing interaction factor and/or the playing experience factor as variables, and each evaluation function can be preset.
The corresponding relationship between each grade value of the definition grade factor and the evaluation function may be preset, and each grade value corresponds to one evaluation function. The evaluation functions corresponding to any two rank values may be the same or different, and are not limited herein.
In one embodiment, the correspondence between each level value of the sharpness level factor and the evaluation function may be expressed as a piecewise function:
h＝δ(r)hr+Cr
where δ (r) denotes the activation function for the rank value, r denotes the rank value, hrRepresenting the evaluation function corresponding to the rank value r, h representing the determined target evaluation function, CrA constant term representing a level value r for which the constant term can be custom set. In one implementation, the constant term CrMay be trained based on the model. The constant terms of the different gradation values may be the same or different, and are not limited herein.
The above piecewise function may be specifically expressed as:
Figure BDA0001953257320000111
after the grade values are obtained, the activation function of the grade value is 1, the activation functions of other grade values are 0, the evaluation function corresponding to the grade value is activated at the moment, and the activated evaluation function is the target evaluation function.
For example, if the level value of the obtained definition level factor of the played video is 1, δ (1) is 1, and other activation functions such as δ (0), δ (2) and the like are all 0, that is, the obtained target evaluation function is: h is h1+C1。
In one embodiment, a preset piecewise evaluation function is obtained:
Figure BDA0001953257320000121
wherein h is an objective evaluation function,hiand delta (i) is an activation function corresponding to the grade value i, and takes a value of 1 when the activation function is activated and takes a value of 0 when the activation function is not activated. And activating the activation function of the acquired grade value to obtain a target evaluation function.
S103, obtaining a result of the target evaluation function based on the target evaluation function and the determined value of the target playing factor, and determining the result as the evaluation result of the played video.
When the target evaluation function is a linear function taking the playing interaction factor as a variable, the target playing factor is the playing interaction factor; when the target evaluation function is a linear function with the playing experience factor as a variable, the target playing factor is the playing experience factor; when the target evaluation function is a linear function with the play interaction factor and the play experience factor as variables, the target play factor includes the play interaction factor and the play experience factor.
And correspondingly substituting the numerical value of the target playing factor into the target evaluation function to obtain a result of the target evaluation function, wherein the result is the evaluation result of the played video. In one implementation, the evaluation result of the played video is the QoE score.
In one embodiment, the target play factor is a play interaction factor, where the play interaction factor includes play start time and/or play start time ratio. That is, the target playback factor may include only the playback start time or the playback start time, or may include both the playback start time and the playback start time. The playing start time consumption refers to the time required by the user to see the first frame of the video after the user clicks the video, and the playing start time consumption ratio refers to the ratio of the playing start time consumption to the total duration of the video.
When the target playing factor is the time consumed by playing, acquiring a numerical value of the time consumed by playing; when the target playing factor is the ratio of the consumed time of the play-on, acquiring a numerical value of the ratio of the consumed time of the play-on; and when the target playing factor comprises the occupation ratio of the playing start time and the playing start time, acquiring the value of the playing start time and the value of the occupation ratio of the playing start time.
The evaluation function is a linear function taking the ratio of the broadcast start time consumption to the broadcast start time consumption as a variable, namely an objective evaluation function is as follows:
h＝w1x1+w2x2+C1
wherein h is the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the time consumed for the broadcast, C1Is a constant term.
For example, with a rank value of r, when the rank value is r, the target evaluation function is:
hr＝wr1x1+wr2x2+Cr
where r is the rank value of the sharpness rank factor, hrFor rating of played video, x1To start broadcasting, x is time-consuming2In order to account for the time consumed by broadcast, wr1For the coefficient, w, of the time taken to start the broadcast at a rank value rr2The value is a coefficient which is the ratio of the time consumed by broadcasting when the rank value is r. w is ar1And wr2Can be custom set. w is ar1And wr2May be the same or different, and is not limited herein.
When the target play factor is the play start time, the value of the play start time ratio is considered to be 0, and the evaluation function is changed as follows:
hr＝wr1x1+Cr
at this time, the obtained value of the playing start time is substituted into the above formula, so as to obtain the evaluation result of the played video.
When the target play factor is the ratio of the play start time to the play start time, the value of the play start time may be considered to be 0, and the evaluation function is changed as follows:
hr＝wr2x2+Cr
at this time, the obtained value of the broadcast start time consumption ratio is substituted into the above formula, so that the evaluation result of the broadcast video can be obtained.
When the target playing factor includes the ratio of the playing start time to the playing start time, the obtained value of the playing start time and the value of the ratio of the playing start time to the playing start time are substituted into the following formula, so as to obtain the evaluation result of the played video:
hr＝wr1x1+wr2x2+Cr
for example, the playing interaction factor includes the ratio of the playing start time to the playing start time, and when the rank value is 1, w11Is 0.27, w12Is-0.04, CrAt 63.79, the evaluation function is:
h1＝0.27x1-0.04x2+63.79
the playing start time of the obtained played video is x1Is 0.25, the ratio of the time consumed for starting to broadcast is x2At 0.0008, the ratio of the obtained play-up time to the play-up time is substituted into the above formula to obtain 63.857468, i.e. the QoE score of the played video is 63.857468.
In the embodiment, the definition grade factor is used as a main factor for evaluation and is evaluated in combination with the playing interaction factor, so that the evaluation singleness in the prior art is avoided, the evaluation is relatively comprehensive, only the definition grade factor and the playing interaction factor and the cross characteristics between the definition grade factor and the playing interaction factor are considered, the evaluation complexity is prevented from being greatly increased, and the increase degree of the evaluation complexity is controlled.
In one embodiment, the target playback factor is a playback experience factor, wherein the playback experience factor includes at least one of a pause number, a pause time length, a pause frequency, and a pause time length ratio, that is, the target playback factor includes at least one of a pause number, a pause time length, a pause frequency, and a pause time length ratio. The pause times are the total pause times of the video in the playing process, the pause time length is the total pause time of the video in the playing process, the pause time length ratio is the ratio of the pause time length to the total video playing time length, and the pause frequency is the pause times in unit time, namely the ratio of the pause times to the total video playing time length.
The evaluation function is a linear function with the ratio of the number of times of the stuck, the length of the stuck, the frequency of the stuck and the length of the stuck as variables, namely, the target evaluation function is as follows:
h＝θ1z1+θ2z2+θ3z3+θ4z4+C2
wherein h is the evaluation result of the played video, z1Is the number of caltons, z2Is the duration of the stuck time, z3For the frequency of said stuck, z4Is the ratio of the length of the Katon time, theta1Is a coefficient of the number of said caltons, θ2Is a coefficient of the length of the stuck time, theta3Is the coefficient of the Cartesian frequency, θ4Is the coefficient of the Katon time length ratio, C2Is a constant term.
For example, with a rank value of r, when the rank value is r, the target evaluation function is:
hr＝θr1z1+θr2z2+θr3z3+θr4z4+Cr
where r is the rank value of the sharpness rank factor, hrScoring of played video, z1Is the number of caltons, z2Is the duration of the stuck-at time, z3Is the frequency of Katon, z4Is the ratio of the length of the time at pause, thetar1Is a coefficient of the number of clicks at a gradation value of r, thetar2Is the coefficient of the length of the stuck time at a level value r, thetar3Is the coefficient of the Cartin frequency at a level value r, thetar4Is the coefficient of the ratio of the length of Katon time when the grade value is r, CrRepresenting a constant term for a rank value r.
The numerical values of the factors included in the target playback factor are obtained, for example, if the target playback factor includes the number of times of pause, the length of time of pause, the frequency of pause, and the length of time of pause, the numerical values of the number of times of pause, the length of time of pause, the frequency of pause, and the length of time of pause are obtained respectively.
For a factor not included in the target playback factor, the value of the factor may be considered to be 0. For example, when the target playback factor includes the number of times of katon, the length of time of katon, and the length of time of katon, the value of the katon frequency may be considered to be 0, and the target evaluation function may be considered to be:
hr＝θr1z1+θr2z2+θr4z4+Cr
namely, the numerical value of the pause times, the numerical value of the pause time length and the numerical value of the pause time length ratio are obtained, and the obtained numerical values are substituted into the formula to obtain the evaluation result of the played video.
For another example, when the target playing factor includes the number of times of pause, the length of time of pause, and the ratio of the frequency of pause to the length of time of pause, the numerical values of the number of times of pause, the length of time of pause, the numerical value of the frequency of pause, and the value of the ratio of the length of time of pause are obtained, and the obtained numerical values are substituted into the following formula, so that the evaluation result of the played video can be calculated:
hr＝θr1z1+θr2z2+θr3z3+θr4z4+Cr
when the rank value is 2, θ21Is-0.8017, theta22Is-0.91, theta23Is-0.05, theta24Is-0.125, Cr63.79, the obtained number of times of calton z1Is 1, length of stuck time z2Is 1 second, the Carten frequency z30.00333, length of karton time ratio z40.00333, an evaluation result h can be calculated2Is 62.0777.
In the embodiment, the definition grade factor is used as a main factor for evaluation and is evaluated in combination with the playing experience factor, so that the evaluation singleness in the prior art is avoided, the evaluation is relatively comprehensive, only the definition grade factor and the playing experience factor and the cross characteristics between the definition grade factor and the playing experience factor are considered, the evaluation complexity is greatly increased, and the increase degree of the evaluation complexity is controlled.
In one embodiment, the target playback factor may include a playback interaction factor and a playback experience factor, wherein the playback interaction factor may include at least one of a playback start time and a playback start time ratio, and the playback experience factor may include at least one of a pause number, a pause duration, a pause frequency, and a pause duration ratio. That is, the number of factors included in the target playback factor may be two at least, for example, the target playback factor includes the time spent on playing and the number of times of pause; the number of factors included in the target play factor may be six at most, and in this case, the target play factor includes play-up time, play-up time ratio, pause times, pause time length, pause frequency, and pause time length ratio.
The evaluation function is a linear function with the start-up broadcast time consumption, the start-up broadcast time consumption ratio, the stuck times, the stuck time length, the stuck frequency and the stuck time length ratio as variables, namely, the target evaluation function is as follows:
h＝w1x1+w2x2+θ1z1+θ2z2+θ3z3+θ4z4+C3
wherein h isrFor the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the elapsed time of the broadcast, z1Is the number of caltons, z2Is the duration of the stuck time, z3For the frequency of said stuck, z4Is the ratio of the length of the Katon time, thetar1Is a coefficient of the number of said caltons, θ2Is a coefficient of the length of the stuck time, theta3Is the coefficient of the Cartesian frequency, θ4Is the coefficient of the Katon time length ratio, C3Is a constant term.
For example, with a rank value of r, when the rank value is r, the target evaluation function is:
hr＝wr1x1+wr2x2+θr1z1+θr2z2+θr3z3+θr4z4+Cr
where r is the rank value of the sharpness rank factor, hrFor rating of played video, x1To start broadcasting, x is time-consuming2In order to account for the time consumed by broadcast, wr1For the coefficient, w, of the time taken to start the broadcast at a rank value rr2Is a coefficient, z, of the ratio of the time consumed by the broadcast when the rank value is r1Is the number of caltons, z2Is the duration of the stuck-at time, z3Is the frequency of Katon, z4Is the ratio of the length of the time at pause, thetar1Is a coefficient of the number of clicks at a gradation value of r, thetar2Is the coefficient of the length of the stuck time at a level value r, thetar3Is the coefficient of the Cartin frequency at a level value r, thetar4Is the coefficient of the ratio of the length of Katon time when the grade value is r, CrRepresenting a constant term for a rank value r.
The values of the factors included in the target playing factor are obtained, for example, if the target playing factor includes the start playing time, the stuck times and the stuck frequency, the values of the start playing time, the stuck times and the stuck frequency are obtained respectively.
For a factor not included in the target playback factor, the value of the factor may be considered to be 0. For example, if the target playback factor includes the start-up time, the number of times of pause, the duration of pause, and the length of pause, the value of the start-up time ratio is considered to be 0, and the value of the pause frequency is considered to be 0, at this time, the target evaluation function is considered to be:
hr＝wr1x1+θr1z1+θr2z2+θr4z4+Cr
namely, after acquiring the value of the playing start time, the value of the pause times, the value of the pause time and the value of the pause time ratio, substituting the acquired values into the formula to obtain the evaluation result of the played video.
For another example, the target playing factor includes the play-up time, the play-up time ratio, the pause times, the pause time length, the pause frequency, and the pause time length ratio, and then the value of the play-up time, the value of the play-up time ratio, the value of the pause times, the value of the pause time length, the value of the pause frequency, and the value of the pause time length ratio are obtained, and the obtained values are substituted into the following formula, so as to calculate the evaluation result of the played video:
hr＝wr1x1+wr2x2+θr1z1+θr2z2+θr3z3+θr4z4+Cr
when the rank value r is 3, w31Is 0.27, w32Is-0.04, theta31Is-0.8017, theta32Is-0.91, theta33Is-0.05, theta34Is-0.125, Cr63.79, the acquired start playing time x11 second, the time consumed for starting broadcasting is x20.00333, number of caltons z1Is 3, a stuck duration z210 seconds, the Cartton frequency z3Is 0.01, length of time at pause is z40.0333, the evaluation result h can be calculated352.5501, the QoE score of the played video is 52.5501.
In the technical scheme provided by the embodiment of the invention, the grade value of the definition grade factor of the played video and the numerical value of the target playing factor are obtained; determining an evaluation function corresponding to the obtained grade value from the corresponding relation between each grade value of the definition grade factor and the evaluation function as a target evaluation function; and obtaining a result of the target evaluation function based on the target evaluation function and the determined value of the target playing factor, and determining the result as an evaluation result of the played video. According to the technical scheme provided by the embodiment of the invention, the definition grade factor is added in the evaluation process as the non-service quality characteristic, and in addition, the service quality characteristic comprising the playing interaction factor and/or the playing experience factor is also added, and the evaluation is more comprehensive based on the non-service quality characteristic and the service quality characteristic compared with the prior art. And the definition grade factor has correlation with the playing interaction factor and the playing experience factor respectively, and the playing interaction factor and the playing experience factor do not have correlation, so that the number of the added cross features is controlled, the complexity of evaluation is avoided being greatly increased, and the increase degree of the complexity is controlled.
Corresponding to the above video playing evaluation method embodiment, an embodiment of the present invention further provides a video playing evaluation device, as shown in fig. 2, where the video playing evaluation device includes:
an obtaining module 210, configured to obtain a level value of a definition level factor of a played video and a numerical value of a target playing factor; the target playing factor comprises a playing interaction factor and/or a playing experience factor, the playing interaction factor and the playing experience factor have no correlation, and the definition level factor and the target playing factor have correlation;
a determining module 220, configured to determine, from a correspondence between each level value of the definition level factor and an evaluation function, an evaluation function corresponding to the obtained level value as a target evaluation function, where the evaluation function is a linear function in which a play interaction factor and/or a play experience factor is used as a variable;
a obtaining module 230, configured to obtain a result of the target evaluation function based on the target evaluation function and the determined value of the target playing factor, and determine the result as an evaluation result of the played video.
In one embodiment, the obtaining module 210 is specifically configured to:
acquiring the code rate of a played video and the playing time of the video with each code rate;
calculating the average code rate of the played video based on the obtained code rate and the playing time;
and acquiring a grade value corresponding to the average code rate from a preset grade factor corresponding relation to serve as the grade value of the played video, wherein the grade factor corresponding relation records the corresponding relation between each grade value of the definition grade factor and the code rate.
In one embodiment, the determining module is specifically configured to:
acquiring a preset segmented evaluation function:
Figure BDA0001953257320000181
wherein h is an objective evaluation function, hiThe evaluation function is an evaluation function with the grade value of i, delta (i) is an activation function corresponding to the grade value of i, the value of the activation function is 1 when the activation function is activated, and the value of the activation function is 0 when the activation function is not activated;
and activating the activation function of the acquired grade value to obtain a target evaluation function.
In one embodiment, when the target playing factor is a playing interaction factor, the playing interaction factor includes a ratio of the play start time to the play start time, and the evaluation function is a linear function with the ratio of the play start time to the play start time as a variable;
the obtaining module 230 is specifically configured to:
obtaining an evaluation result of the played video according to the obtained value of the broadcast start time consumption and the value of the broadcast start time consumption ratio by using the following objective evaluation function:
h＝w1x1+w2x2+C1
wherein h is the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the time consumed for the broadcast, C1Is a constant term.
In one embodiment, when the target playback factor is a playback experience factor, the playback experience factor includes a stuck time, a stuck time duration, a stuck frequency, and a stuck time length ratio, and the evaluation function is a linear function having the stuck time, the stuck time duration, the stuck frequency, and the stuck time length ratio as variables;
the obtaining module is specifically configured to:
obtaining an evaluation result of the played video according to the obtained numerical value of each playing experience factor by using the following target evaluation function:
h＝θ1z1+θ2z2+θ3z3+θ4z4+C2
wherein h is the evaluation result of the played video, z1Is the number of caltons, z2Is the duration of the stuck-at time, z3In order to be the frequency of the calton,z4is the ratio of the length of the time at pause, theta1Coefficient of the number of caltons, θ2Coefficient of the duration of the stuck-at time, theta3Is the coefficient of the Carten frequency, θ4Coefficient of length to length ratio of Katon, C2Is a constant term.
In one embodiment, when the target playback factor includes a playback interaction factor and a playback experience factor, the playback interaction factor includes a ratio of start-up playback time to start-up playback time, and the playback experience factor includes a ratio of pause times, pause durations, pause frequencies, and pause time durations, wherein the evaluation function is a linear function having the start-up playback time, the start-up playback time ratio, the pause times, the pause durations, the pause frequencies, and the pause time durations as variables;
the obtaining module 230 is specifically configured to:
calculating the evaluation result of the played video according to the acquired numerical value of each playing interaction factor and the acquired numerical value of each playing experience factor by using the following target evaluation function:
h＝w1x1+w2x2+θ1z1+θ2z2+θ3z3+θ4z4+C3
wherein h isrFor the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the elapsed time of the broadcast, z1Is the number of caltons, z2Is the duration of the stuck time, z3For the frequency of said stuck, z4Is the ratio of the length of the Katon time, thetar1Is a coefficient of the number of said caltons, θ2Is a coefficient of the length of the stuck time, theta3Is the coefficient of the Cartesian frequency, θ4Is the coefficient of the Katon time length ratio, C3Is a constant term.
In the technical scheme provided by the embodiment of the invention, the grade value of the definition grade factor of the played video and the numerical value of the target playing factor are obtained; determining an evaluation function corresponding to the obtained grade value from the corresponding relation between each grade value of the definition grade factor and the evaluation function as a target evaluation function; and obtaining a result of the target evaluation function based on the target evaluation function and the determined value of the target playing factor, and determining the result as an evaluation result of the played video. According to the technical scheme provided by the embodiment of the invention, the definition grade factor is added in the evaluation process as the non-service quality characteristic, and in addition, the service quality characteristic comprising the playing interaction factor and/or the playing experience factor is also added, and the evaluation is more comprehensive based on the non-service quality characteristic and the service quality characteristic compared with the prior art. And the definition grade factor has correlation with the playing interaction factor and the playing experience factor respectively, and the playing interaction factor and the playing experience factor do not have correlation, so that the number of the added cross features is controlled, the complexity of evaluation is avoided being greatly increased, and the increase degree of the complexity is controlled.
An embodiment of the present invention further provides an electronic device, as shown in fig. 3, including a processor 310, a communication interface 320, a memory 330, and a communication bus 340, where the processor 310, the communication interface 320, and the memory 330 complete mutual communication through the communication bus 340,
a memory 330 for storing a computer program;
the processor 310, when executing the program stored in the memory 330, implements the following steps:
acquiring the grade value of the definition grade factor of the played video and the numerical value of the target playing factor; the target playing factor comprises a playing interaction factor and/or a playing experience factor, the playing interaction factor and the playing experience factor have no correlation, and the definition level factor and the target playing factor have correlation;
determining an evaluation function corresponding to the obtained grade value from the corresponding relation between each grade value of the definition grade factor and the evaluation function as a target evaluation function, wherein the evaluation function is a linear function taking a playing interaction factor and/or a playing experience factor as a variable;
and obtaining a result of the target evaluation function based on the target evaluation function and the determined value of the target playing factor, and determining the result as the evaluation result of the played video.
In the technical scheme provided by the embodiment of the invention, the grade value of the definition grade factor of the played video and the numerical value of the target playing factor are obtained; determining an evaluation function corresponding to the obtained grade value from the corresponding relation between each grade value of the definition grade factor and the evaluation function as a target evaluation function; and obtaining a result of the target evaluation function based on the target evaluation function and the determined value of the target playing factor, and determining the result as an evaluation result of the played video. According to the technical scheme provided by the embodiment of the invention, the definition grade factor is added in the evaluation process as the non-service quality characteristic, and in addition, the service quality characteristic comprising the playing interaction factor and/or the playing experience factor is also added, and the evaluation is more comprehensive based on the non-service quality characteristic and the service quality characteristic compared with the prior art. And the definition grade factor has correlation with the playing interaction factor and the playing experience factor respectively, and the playing interaction factor and the playing experience factor do not have correlation, so that the number of the added cross features is controlled, the complexity of evaluation is avoided being greatly increased, and the increase degree of the complexity is controlled.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
In another embodiment of the present invention, a computer-readable storage medium is further provided, in which instructions are stored, and when the instructions are executed on a computer, the computer is enabled to execute the video playing evaluation method in any one of the above embodiments.
In yet another embodiment of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the video playback evaluation method of any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the video playback evaluation apparatus and the electronic device, since they are substantially similar to the embodiments of the video playback evaluation method, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the embodiments of the method.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims (13)

1. A video playback evaluation method, the method comprising:
acquiring a grade value of a definition grade factor of a played video and a numerical value of a target playing factor, wherein the target playing factor comprises a playing interaction factor and/or a playing experience factor, the playing interaction factor and the playing experience factor have no correlation, and the definition grade factor and the target playing factor have correlation;
determining an evaluation function corresponding to the obtained grade value from the corresponding relation between each grade value of the definition grade factor and the evaluation function as a target evaluation function, wherein the evaluation function is a linear function taking a playing interaction factor and/or the playing experience factor as a variable; when the target playing factor is the playing interaction factor, the playing interaction factor comprises the ratio of the playing start time to the playing start time, and the evaluation function is a linear function taking the ratio of the playing start time to the playing start time as a variable; when the target playing factor is the playing experience factor, the playing experience factor comprises a pause time, a pause time length, a pause frequency and a pause time length ratio, and the evaluation function is a linear function with the pause time, the pause time length, the pause frequency and the pause time length ratio as variables; when the target playing factor comprises the playing interaction factor and the playing experience factor, the playing interaction factor comprises a playing start time and a playing start time, and the playing experience factor comprises a pause time, a pause frequency and a pause time length ratio, wherein the evaluation function is a linear function with the playing start time, the pause frequency and the pause time length ratio as variables;
and obtaining a result of the target evaluation function based on the target evaluation function and the determined value of the target playing factor, and determining the result as an evaluation result of the played video.
2. The method of claim 1, wherein obtaining the rating value of the sharpness rating factor of the played video comprises:
acquiring the code rate of a played video and the playing time of the video with each code rate;
calculating the average code rate of the played video based on the obtained code rate and the playing time;
and acquiring a grade value corresponding to the average code rate from a preset grade factor corresponding relation to serve as the grade value of the played video, wherein the grade factor corresponding relation records the corresponding relation between each grade value of the definition grade factor and the code rate.
3. The method according to claim 1, wherein the determining, as the target evaluation function, an evaluation function corresponding to the obtained rank value from the correspondence between each rank value of the sharpness rank factor and the evaluation function comprises:
acquiring a preset segmented evaluation function:
Figure FDA0002865912980000021
wherein h is an objective evaluation function, hiThe evaluation function is an evaluation function with the grade value of i, delta (i) is an activation function corresponding to the grade value of i, the value of the activation function is 1 when the activation function is activated, and the value of the activation function is 0 when the activation function is not activated;
and activating the activation function of the acquired grade value to obtain the target evaluation function.
4. The method according to claim 1, wherein when the target playback factor is the playback interaction factor, the obtaining a result of the target evaluation function based on the target evaluation function and the obtained value of the target playback factor, and determining the result as an evaluation result of the played video comprises:
obtaining an evaluation result of the played video according to the obtained value of the broadcast start time consumption and the value of the broadcast start time consumption ratio by using the following objective evaluation function:
h＝w1x1+w2x2+C1
wherein h is the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the time consumed for the broadcast, C1Is a constant term.
5. The method according to claim 1, wherein when the target playback factor is the playback experience factor, the obtaining a result of the target evaluation function based on the target evaluation function and the obtained value of the target playback factor, and determining the result as an evaluation result of the played video comprises:
obtaining an evaluation result of the played video according to the obtained numerical value of each playing experience factor by using the following target evaluation function:
h＝θ1z1+θ2z2+θ3z3+θ4z4+C2
wherein h is the evaluation result of the played video, z1Is the number of caltons, z2Is the duration of the stuck time, z3For the frequency of said stuck, z4Is the ratio of the length of the Katon time, theta1Is a coefficient of the number of said caltons, θ2Is a coefficient of the length of the stuck time, theta3Is the coefficient of the Cartesian frequency, θ4Is the coefficient of the Katon time length ratio, C2Is a constant term.
6. The method according to claim 1, wherein when the target playback factor includes the playback interaction factor and the playback experience factor, the obtaining a result of the target evaluation function based on the target evaluation function and the obtained value of the target playback factor, and determining the result as an evaluation result of the played video includes:
calculating an evaluation result of the played video according to the acquired numerical values of the playing interaction factors and the acquired numerical values of the playing experience factors by using the following target evaluation functions:
h＝w1x1+w2x2+θ1z1+θ2z2+θ3z3+θ4z4+C3
wherein h isrFor the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the elapsed time of the broadcast, z1Is the number of caltons, z2Is the duration of the stuck time, z3For the frequency of said stuck, z4Is the ratio of the length of the Katon time, thetar1Is a coefficient of the number of said caltons, θ2Is a coefficient of the length of the stuck time, theta3Is the coefficient of the Cartesian frequency, θ4Is the coefficient of the Katon time length ratio, C3Is a constant term.
7. A video playback evaluation apparatus, the apparatus comprising:
the acquisition module is used for acquiring the grade value of the definition grade factor of the played video and the numerical value of the target playing factor; the target playing factor comprises a playing interaction factor and/or a playing experience factor, the playing interaction factor and the playing experience factor have no correlation, and the definition level factor and the target playing factor have correlation;
a determining module, configured to determine, from a correspondence between each level value of the clarity level factor and an evaluation function, an evaluation function corresponding to the obtained level value as a target evaluation function, where the evaluation function is a linear function in which a play interaction factor and/or the play experience factor is used as a variable; when the target playing factor is the playing interaction factor, the playing interaction factor comprises the ratio of the playing start time to the playing start time, and the evaluation function is a linear function taking the ratio of the playing start time to the playing start time as a variable; when the target playing factor is the playing experience factor, the playing experience factor comprises a pause time, a pause time length, a pause frequency and a pause time length ratio, and the evaluation function is a linear function with the pause time, the pause time length, the pause frequency and the pause time length ratio as variables; when the target playing factor comprises the playing interaction factor and the playing experience factor, the playing interaction factor comprises a playing start time and a playing start time, and the playing experience factor comprises a pause time, a pause frequency and a pause time length ratio, wherein the evaluation function is a linear function with the playing start time, the pause frequency and the pause time length ratio as variables;
and the obtaining module is used for obtaining a result of the target evaluation function based on the target evaluation function and the determined numerical value of the target playing factor, and determining the result as an evaluation result of the played video.
8. The apparatus of claim 7, wherein the obtaining module is specifically configured to:
acquiring the code rate of a played video and the playing time of the video with each code rate;
calculating the average code rate of the played video based on the obtained code rate and the playing time;
and acquiring a grade value corresponding to the average code rate from a preset grade factor corresponding relation to serve as the grade value of the played video, wherein the grade factor corresponding relation records the corresponding relation between each grade value of the definition grade factor and the code rate.
9. The apparatus of claim 7, wherein the determining module is specifically configured to:
acquiring a preset segmented evaluation function:
Figure FDA0002865912980000041
wherein h is an objective evaluation function, hiThe evaluation function is an evaluation function with the grade value of i, delta (i) is an activation function corresponding to the grade value of i, the value of the activation function is 1 when the activation function is activated, and the value of the activation function is 0 when the activation function is not activated;
and activating the activation function of the acquired grade value to obtain the target evaluation function.
10. The apparatus of claim 7, wherein when the target playback factor is the playback interaction factor, the obtaining module is specifically configured to:
obtaining an evaluation result of the played video according to the obtained value of the broadcast start time consumption and the value of the broadcast start time consumption ratio by using the following objective evaluation function:
h＝w1x1+w2x2+C1
wherein h is the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the time consumed for the broadcast, C1Is a constant term.
11. The apparatus of claim 7, wherein when the target playback factor is the playback experience factor, the obtaining module is specifically configured to:
obtaining an evaluation result of the played video according to the obtained numerical value of each playing experience factor by using the following target evaluation function:
h＝θ1z1+θ2z2+θ3z3+θ4z4+C2
wherein h is the evaluation result of the played video, z1Is the number of caltons, z2For the duration of the said stuck-at time,z3for the frequency of said stuck, z4Is the ratio of the length of the Katon time, theta1Is a coefficient of the number of said caltons, θ2Is a coefficient of the length of the stuck time, theta3Is the coefficient of the Cartesian frequency, θ4Is the coefficient of the Katon time length ratio, C2Is a constant term.
12. The apparatus of claim 7, wherein when the target playback factor includes the playback interaction factor and the playback experience factor, the obtaining module is specifically configured to:
calculating an evaluation result of the played video according to the acquired numerical values of the playing interaction factors and the acquired numerical values of the playing experience factors by using the following target evaluation functions:
h＝w1x1+w2x2+θ1z1+θ2z2+θ3z3+θ4z4+C3
wherein h isrFor the evaluation result of the played video, x1For the start of the broadcast, x2The ratio of the time consumed for the broadcast, w1For the factor of the elapsed time from the start of broadcast, w2Is the coefficient of the ratio of the elapsed time of the broadcast, z1Is the number of caltons, z2Is the duration of the stuck time, z3For the frequency of said stuck, z4Is the ratio of the length of the Katon time, thetar1Is a coefficient of the number of said caltons, θ2Is a coefficient of the length of the stuck time, theta3Is the coefficient of the Cartesian frequency, θ4Is the coefficient of the Katon time length ratio, C3Is a constant term.
13. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1-6 when executing a program stored in the memory.
CN201910058188.8A 2019-01-22 2019-01-22 Video playing evaluation method and device Active CN109729433B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910058188.8A CN109729433B (en) 2019-01-22 2019-01-22 Video playing evaluation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910058188.8A CN109729433B (en) 2019-01-22 2019-01-22 Video playing evaluation method and device

Publications (2)

Publication Number Publication Date
CN109729433A CN109729433A (en) 2019-05-07
CN109729433B true CN109729433B (en) 2021-05-07

Family

ID=66299237

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910058188.8A Active CN109729433B (en) 2019-01-22 2019-01-22 Video playing evaluation method and device

Country Status (1)

Country Link
CN (1) CN109729433B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110113638A (en) * 2019-05-10 2019-08-09 北京奇艺世纪科技有限公司 A kind of prediction technique, device and electronic equipment
CN110139160B (en) * 2019-05-10 2022-07-22 北京奇艺世纪科技有限公司 Prediction system and method
CN110366043B (en) * 2019-08-20 2022-02-18 北京字节跳动网络技术有限公司 Video processing method and device, electronic equipment and readable medium
CN111565316B (en) * 2020-07-15 2020-10-23 腾讯科技（深圳）有限公司 Video processing method, video processing device, computer equipment and storage medium
CN112822482B (en) * 2020-12-31 2022-11-08 上海掌门科技有限公司 Method and equipment for determining evaluation score of audio and video call
CN114095763B (en) * 2021-11-25 2024-03-12 上海幻电信息科技有限公司 Video list pushing method and play quality assessment method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101635846A (en) * 2008-07-21 2010-01-27 华为技术有限公司 Method, system and device for evaluating video quality
CN103458264A (en) * 2012-05-28 2013-12-18 华为技术有限公司 Method and device for evaluating quality of media
CN105897736A (en) * 2016-05-17 2016-08-24 北京邮电大学 Method and device for assessing quality of experience (QoE) of TCP (Transmission Control Protocol) video stream service
CN106791821A (en) * 2016-12-30 2017-05-31 合网络技术（北京）有限公司 Play appraisal procedure and device
CN108271016A (en) * 2016-12-30 2018-07-10 上海大唐移动通信设备有限公司 Video quality evaluation method and device

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2106154A1 (en) * 2008-03-28 2009-09-30 Deutsche Telekom AG Audio-visual quality estimation

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101635846A (en) * 2008-07-21 2010-01-27 华为技术有限公司 Method, system and device for evaluating video quality
CN103458264A (en) * 2012-05-28 2013-12-18 华为技术有限公司 Method and device for evaluating quality of media
CN105897736A (en) * 2016-05-17 2016-08-24 北京邮电大学 Method and device for assessing quality of experience (QoE) of TCP (Transmission Control Protocol) video stream service
CN106791821A (en) * 2016-12-30 2017-05-31 合网络技术（北京）有限公司 Play appraisal procedure and device
CN108271016A (en) * 2016-12-30 2018-07-10 上海大唐移动通信设备有限公司 Video quality evaluation method and device

Also Published As

Publication number Publication date
CN109729433A (en) 2019-05-07

Similar Documents

Publication Publication Date Title
CN109729433B (en) Video playing evaluation method and device
CN108966012B (en) Video playing rate determining method and device and electronic equipment
US20140200959A1 (en) Predicting future performance of games
CN111683292B (en) Video playing method and device
CN109996122B (en) Video recommendation method and device, server and storage medium
US20180365709A1 (en) Personalized creator recommendations
CN112765400B (en) Weight updating method, content recommending method, device and equipment for interest labels
CN103577505B (en) The interest-degree prediction technique and system of media file
CN110362458A (en) Application evaluation reminding method, device, electronic equipment and readable storage medium storing program for executing
CN111163339A (en) Short video recommendation method and device
CN112785333A (en) Advertisement putting method, electronic device, storage medium and device
CN108171537B (en) User experience assessment method and device, electronic equipment and storage medium
CN112312173B (en) Anchor recommendation method and device, electronic equipment and readable storage medium
CN110134828B (en) Video off-shelf detection method and device
CN110392253B (en) Video quality evaluation method, device, equipment and storage medium
CN108804439A (en) The recommendation method and device of multimedia resource
CN108764021B (en) Cheating video identification method and device
CN112667906B (en) Method and device for recommending up main, and electronic equipment
CN113676770B (en) Member rights prediction method, member rights prediction device, electronic equipment and storage medium
CN111669656B (en) Method and device for determining wonderful degree of video clip
CN111767520B (en) User retention rate calculation method and device, electronic equipment and storage medium
CN112612688A (en) Method and device for testing equipment fluency, electronic equipment and storage medium
CN110995529B (en) Configuration data testing method and device of recommendation system and electronic equipment
CN113011985A (en) Financial product push data processing method and device
CN109561350B (en) User interest degree evaluation method and system

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