CN116074586A - Video experience quality prediction method and device, electronic equipment and storage medium - Google Patents
Video experience quality prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116074586A CN116074586A CN202211601452.6A CN202211601452A CN116074586A CN 116074586 A CN116074586 A CN 116074586A CN 202211601452 A CN202211601452 A CN 202211601452A CN 116074586 A CN116074586 A CN 116074586A
- Authority
- CN
- China
- Prior art keywords
- video
- predicted
- pause
- quality
- expressed
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000006870 function Effects 0.000 claims description 73
- 238000012512 characterization method Methods 0.000 claims description 26
- 238000000605 extraction Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 11
- 230000000007 visual effect Effects 0.000 description 11
- 238000011161 development Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The disclosure provides a method, a device, an electronic device and a storage medium for predicting video experience quality, comprising: acquiring a video to be predicted, and determining the presentation quality of the video to be predicted; responding to a pause event in the video to be predicted, and generating an influence function of the pause event on the video to be predicted; and predicting the experience quality of the video to be predicted according to the presentation quality of the video to be predicted and the influence function. According to the method and the device, the influence function of the video to be detected is determined through the pause event in the video to be detected, and then the experience quality of the video to be detected is predicted through the influence function and the presentation quality of the video to be detected, so that a final prediction result can more accurately reflect the experience of a viewer.
Description
Technical Field
The present invention relates to the field of streaming media transmission technologies, and in particular, to a method and apparatus for predicting quality of experience of video, an electronic device, and a storage medium.
Background
With the continuous development of streaming video, the demand of consumers for streaming video is increasing. This has led to the development of streaming video at the present stage, which has been directed towards a stage of improving quality of service from the emphasis on the scale of users. As consumer demands for video viewing experience are continuously increasing, improving the video experience quality (Quality of Experience, qoE) of users becomes a major competitive factor in streaming video services.
In the prior art, most of the conventional methods for predicting quality of experience (QoE) of video are only considered, and parameters in the network technology layer have an influence on the viewing process. But in actual viewing, the quality of video experience (QoE) is also affected by the presentation quality of the video itself and by the pause event of the viewer during viewing of the video.
Disclosure of Invention
In view of the above, an object of the present disclosure is to provide a method, an apparatus, an electronic device, and a storage medium for predicting video experience quality.
As one aspect of the present disclosure, there is provided a method for predicting quality of experience of video, including:
acquiring a video to be predicted, and determining the presentation quality of the video to be predicted;
responding to a pause event in the video to be predicted, and generating an influence function of the pause event on the video to be predicted;
and predicting the experience quality of the video to be predicted according to the presentation quality of the video to be predicted and the influence function.
Optionally, the determining the presentation quality of the video to be predicted includes:
determining a characterization problem of the video to be predicted;
and determining the presentation quality of the video to be predicted based on the characterization problem.
Optionally, the determining the presentation quality of the video to be predicted based on the characterization problem includes:
extracting image features of the video to be predicted based on the characterization problem to obtain a feature extraction graph;
determining the presentation quality of the video to be tested based on the feature extraction graph;
wherein the presentation quality is expressed as:
P n ＝V(X n ,R n )
wherein the P is n Expressed as the presentation quality, the V is expressed as a quality fraction of the video to be predicted, the X n An nth frame represented as streaming video, said R n An nth frame represented as an original quality video.
Optionally, the generating an influence function of the pause event on the video to be predicted includes:
substituting the pause event into an exponential decay function to determine pause loss of the pause event;
summing the pause losses of the pause event to obtain a set of the pause losses;
generating an influence function of the pause event on the video to be predicted based on the set of pause losses;
wherein the pause loss of the pause event is expressed as:
wherein S is k (t) is denoted as a pause loss,
a proportional function expressed as an decay function, t expressed as a time instance, f expressed as a frame rate, i k And l k Represented as assuming that the kth pause event is located at [ i ] k ，i k +l k ]On, k represents the time length of the pause, T 0 Expressed as unsatisfactory rate, T 1 Expressed as the relative intensity of memory.
Optionally, the step of summing the pause losses of the pause event to obtain a set of pause losses is expressed as:
wherein S (t) is expressed as a set of pause losses, S k (t) is denoted as pause loss, N is the total number of pause events.
Optionally, the generating an influence function of the pause event on the video to be predicted based on the set of pause losses includes:
discretizing the pause loss set to obtain an influence function of the pause event on the video to be predicted;
wherein the influence function is expressed as:
wherein S is n Expressed as an influence function；
Expressed as a converted form after discrete processing of S (t), where n is expressed as an instance of discrete time, i.e. the number of pause events, and f is expressed as the frame rate.
Optionally, the predicting the quality of experience of the video to be predicted according to the quality of presentation of the video to be predicted and the influence function is expressed as:
Q n ＝P n +S n
wherein Q is n Expressed as quality of experience, P n Expressed as presentation quality, S n Represented as an influence function.
As a second aspect of the present disclosure, the present disclosure further provides a device for predicting quality of experience of video, including:
a presentation quality determination module configured to: acquiring a video to be predicted, and determining the presentation quality of the video to be predicted;
an influence function determination module configured to: receiving a pause event in the video to be predicted, and generating an influence function of the pause event on the video to be predicted;
a quality of experience prediction module configured to: and predicting the experience quality of the video to be predicted according to the presentation quality and the influence function.
As a third aspect of the disclosure, the disclosure further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for predicting the quality of experience of video provided by the disclosure when executing the program.
As a fourth aspect of the disclosure, the disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of the above.
As described above, the present disclosure provides a method, apparatus, electronic device, and storage medium for predicting quality of experience of video. In the method, firstly, a video to be detected is obtained, the presenting quality of the video to be detected is determined, then an influence function of the video to be detected is determined based on a pause event in the video to be detected, and finally the experience quality of the video to be detected is predicted based on the presenting quality and the influence function.
Drawings
In order to more clearly illustrate the technical solutions of the present disclosure or related art, the drawings required for the embodiments or related art description will be briefly described below, and it is apparent that the drawings in the following description are only embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort to those of ordinary skill in the art.
Fig. 1A is a schematic diagram of a method for predicting quality of experience of video according to an embodiment of the disclosure.
Fig. 1B is a schematic diagram of a method for determining a video characterization problem to be measured according to an embodiment of the disclosure.
Fig. 1C is a schematic diagram of a method for determining a video presentation quality to be tested according to an embodiment of the present disclosure.
Fig. 1D is a schematic diagram of a method for determining an influence function according to an embodiment of the disclosure.
Fig. 2 is a schematic structural diagram of a prediction apparatus for video experience quality according to an embodiment of the present disclosure.
Fig. 3 is a schematic structural diagram of an electronic device according to a method for predicting quality of experience of video according to an embodiment of the present disclosure.
Detailed Description
For the purposes of promoting an understanding of the principles and advantages of the disclosure, reference will now be made to the embodiments illustrated in the drawings and specific language will be used to describe the same.
It should be noted that unless otherwise defined, technical or scientific terms used in the embodiments of the present disclosure should be given the ordinary meaning as understood by one of ordinary skill in the art to which the present disclosure pertains. The terms "first," "second," and the like, as used in embodiments of the present disclosure, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
In the prior art, the prediction of quality of experience (QoE) of video is mostly only considered by the relevant parameters of network technology, but not considering the presentation quality of the video itself and the pause event that occurs when the viewer views the video, and the association problem between them.
In order to solve the above problems, the present disclosure provides a method, an apparatus, an electronic device, and a storage medium for predicting video experience quality. Through the method, the video presentation quality is firstly determined, then the pause event generated in the video watching process is received, the influence function of the pause event on the video is determined according to the pause event, finally the video experience quality is predicted through the video presentation quality and the influence function of the pause event, and finally the video is improved and perfected through the prediction result of the video experience quality.
Having described the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are specifically described below.
Fig. 1A is a schematic diagram of a method for predicting quality of experience of video according to an embodiment of the disclosure.
The method for predicting the quality of experience of the video shown in fig. 1A further comprises the steps of:
step S10: and acquiring a video to be predicted, and determining the presentation quality of the video to be predicted.
In some embodiments, when the embodiments of the present application want to improve and perfect streaming video itself, the embodiments of the present application may predict the quality of experience of the streaming video through the viewing experience of the viewer, and further improve and perfect the streaming video through the quality of experience.
In some embodiments, the embodiments of the present application may first obtain a portion of streaming media video to be predicted through a streaming media video platform, and then play the portion of streaming media video to a viewer, so as to collect a play experience of the viewer, so as to determine a presentation quality of the portion of streaming media video itself. It can be appreciated that in order to make the determined result of the presentation quality more accurate, the embodiments of the present application may select a large number of viewers with different preferences to watch the streaming video.
In some embodiments, the process of determining the quality of presentation may be accomplished through a pre-set visual question-and-answer model (VQA). The visual question-answering model (VQA) may first collect viewer preferences and categorize and aggregate the collected preferences. For example, viewer a likes horror type video, viewer B likes fun type video, and viewer C also likes horror type video. Viewers a and C may be classified as one category and set to "horror" and viewer B as one category and set to "fun". The present embodiment may then input the results of the above-described categorization summary into the visual question-answering model (VQA) as a "library" of visual question-answering models (VQA). Finally, the embodiment of the application plays the video to be predicted to the viewers A, B and C, and then judges the presentation quality of the video to be predicted based on the aforementioned "library". It will be appreciated that in order to make the final determined presentation quality more accurate, embodiments of the present application may also select viewers with larger age spans as the test population.
In some embodiments, the viewer's preferences depend on a number of factors. For example, the type of video, network parameters, and video length are only described in this disclosure by taking the type of video as an example, but in actual operation, more factors affecting the preference of the viewer may be collected in advance and input into a "library" of the visual question-answer model, so that the finally determined video presentation quality may be more accurate.
Fig. 1B is a schematic diagram of a method for determining a video characterization problem to be measured according to an embodiment of the disclosure.
In some embodiments, as shown in fig. 1B, a further development of step S10 specifically includes the following steps:
s101: and determining the characterization problem of the video to be predicted.
In some embodiments, after the embodiments of the present application determine the "library" of the visual question-answer model (VQA), the embodiments of the present application may determine the presentation quality of the video to be predicted through the "library". Specifically, embodiments of the present application may first determine that a characterization problem of a video to be predicted is the quality of the presentation of the video. The video to be predicted and the characterization question are then input into a visual question-and-answer model (VQA).
In some embodiments, the characterization problem, that is, the relevant content about the video to be predicted that the embodiments of the present application want to know, in the present embodiment, because the embodiments of the present application want to determine the presentation quality of the video to be predicted, the embodiments of the present application may set the characterization problem as the presentation quality of the video to be predicted.
S102: and determining the presentation quality of the video to be predicted based on the characterization problem.
In some embodiments, after the embodiment of the present application inputs the characterization problem and the video to be predicted into the visual question-answering model (VQA), the embodiment of the present application may perform feature extraction on the video to be predicted through the visual question-answering model (VQA) based on the characterization problem, then compare the result of feature extraction with the content in the foregoing "library", and finally determine the presentation quality of the video to be predicted through the compared result.
Fig. 1C is a schematic diagram of a method for determining a video presentation quality to be tested according to an embodiment of the present disclosure.
In some embodiments, as shown in fig. 1C, a further development of step S102 is described, specifically including the following steps:
s1021: and extracting image features of the video to be predicted based on the characterization problem to obtain a feature extraction graph.
In some embodiments, the embodiments of the present application may perform feature extraction of video information on a video to be predicted based on the determined characterization problem (the presentation quality of the video) described above. Specifically, in the embodiment of the present application, a video to be predicted may be decomposed in units of frames, then information extraction is performed on each decomposed frame, and finally, the results of information extraction are combined to finally generate a feature extraction map.
S1022: and determining the presentation quality of the video to be tested based on the feature extraction graph.
In some embodiments, when the embodiment of the present application extracts each frame feature of the video to be predicted and obtains a feature extraction map, the embodiment of the present application may analyze the feature extraction map. For example, the embodiment of the application can determine that the type of the video to be predicted is a horror type or a funneling type through the feature extraction graph. The embodiment of the application can compare the analysis result with a library of videos to be predicted, evaluate the quality score of the videos to be predicted after comparison, and finally determine the presentation quality of the videos to be predicted according to the quality score.
In some embodiments, if the type of video to be predicted is horror, the quality score of the video to be predicted is higher for the viewer A, C. If the video to be predicted is of the smiling type, the quality score of the video to be predicted is higher for viewer B.
In some embodiments, after obtaining the quality score of the video to be predicted for each viewer, the embodiments of the present application may determine, based on the quality score, the presentation quality of the video to be predicted through a visual question-answer model (VQA), which may be specifically expressed as:
P n ＝V(X n ,R n )
wherein the P is n Expressed as the presentation quality, and V expressed as the quality of the video to be predictedScore of X n An nth frame represented as streaming video, said R n An nth frame represented as an original quality video.
In some embodiments of the present invention, in some embodiments,
as described above, in this step, the video to be predicted is acquired first, and the problem of characterization of the video to be predicted is determined. The video to be predicted and the characterization questions are input into a visual question-and-answer model (VQA) to determine the presentation quality of the video to be predicted, and finally the quality of experience of the video to be predicted can be predicted through the presentation quality of the video to be predicted. However, during actual operation, the quality of experience of a video may also depend on the impact of a pause event in the video, and thus, embodiments of the present application analyze pause events in the video.
Step S20: and responding to a pause event in the video to be predicted, and generating an influence function of the pause event on the video to be predicted.
In some embodiments, after determining the presentation quality of the video to be predicted, the embodiments of the present application may acquire a pause event in the video to be predicted, and determine an impact function of the video to be predicted based on the acquired pause event.
In some embodiments, the pause event may depend on the presentation quality of the video to be predicted (factors other than the viewer's personal intention), the network condition when the video to be predicted is viewed (factors other than the viewer's personal intention), and the like. As for the former, it is understood that when the viewer is not satisfied with the content of the video to be predicted, the viewer may autonomously press the pause key to end the play of the video to be predicted. At this time, the influence function of the pause event on the video to be predicted may be considered by integrating the presentation quality of the video to be predicted, i.e. the presentation quality of the video to be predicted may be used as the influence function of the pause event, which is not excessively extended in this embodiment.
In some embodiments, when the pause event is caused by a factor other than the individual intention of the viewer (e.g., network condition, etc.), the pause event in this case may be collected, and the collected pause event may be analyzed, and an influence function of the pause event on the video to be predicted may be determined according to the analysis result.
Fig. 1D is a schematic diagram of a method for determining an influence function according to an embodiment of the disclosure.
In some embodiments, as shown in fig. 1D, a further development of step S20 is described, specifically including the following steps:
s201: substituting the pause event into an exponential decay function to determine a pause loss of the pause event.
In some embodiments, after collecting pause events in the video to be predicted, the embodiments of the present application may determine pause loss of the video to be predicted for each pause event by an exponential decay function. It will be appreciated that there may be a large number of pause events in the video to be predicted, and therefore embodiments of the present application require calculation of the pause loss generated by each pause event occurrence.
In some embodiments, determining a pause loss for the video to be predicted for each pause event may also be expressed as:
wherein S is k (t) is denoted as a pause loss,
a proportional function expressed as an decay function, t expressed as a time instance, f expressed as a frame rate, i k And l k Represented as assuming that the kth pause event is located at [ i ] k ，i k +l k ]On, k represents the time length of the pause, T 0 Expressed as unsatisfactory rate, T 1 Expressed as the relative intensity of memory.
S202: and summing the pause losses of the pause events to obtain a set of the pause losses.
In some embodiments, after the embodiment of the present application calculates the pause loss of each of the pause losses, the embodiment of the present application may sum the calculated pause losses to obtain a set of pause losses generated by all pause events in the video to be predicted.
In some embodiments, the set of pause losses can be expressed as:
wherein S (t) is expressed as a set of pause losses, S k (t) is denoted as pause loss, N is denoted as pause
S203: an impact function of the pause event on the video to be predicted is generated based on the set of pause losses.
In some embodiments, when the embodiment of the present application determines the influence function of the pause event on the video to be predicted, the embodiment of the present application may first perform discretization processing on the set of pause losses determined above, and then generate the influence function of the pause event on the video to be predicted based on the result of the discretization processing.
In some embodiments, discretization may be understood as mapping finite individuals in infinite space into finite space, thereby increasing the space-time efficiency of the algorithm. In this embodiment, the discretizing processing of the set of pause losses may be specifically that each pause loss in the set of pause losses is firstly ordered according to the size, then the de-duplication processing is performed on each pause loss after the ordering, and finally an index is built for the pause loss after the de-duplication processing, so as to obtain the discretizing processing result of the set of pause losses.
In some embodiments, the results of discretization processing of the set of pause losses may be used as an impact function of the final pause event on the video to be predicted, and may be specifically expressed as:
wherein S is n Represented as an influence function;
expressed as a converted form after discrete processing of S (t), where n is expressed as an instance of discrete time, i.e. the number of pause events, and f is expressed as the frame rate.
In this step, as described above, the embodiment of the present application determines the pause event in the video to be predicted first, then calculates the pause loss generated by the pause event in the video to be predicted, and finally obtains the influence function of the pause event in the video to be predicted by discretizing the pause loss. Next, embodiments of the present application will predict the quality of experience of the video to be predicted by the aforementioned presentation quality and impact function.
Step S30: and predicting the experience quality of the video to be predicted according to the presentation quality of the video to be predicted and the influence function.
In some embodiments, the quality of experience of the video to be predicted depends on the presentation quality of the video to be predicted itself and the impact function of the pause event in the video to be predicted. Therefore, when predicting the quality of experience of the video to be predicted, the embodiment of the application comprehensively considers the influence of the presentation quality and the influence function, namely, gathers the influence generated by the presentation quality and the influence function, and further predicts the quality of experience of the video to be predicted.
In some embodiments, the quality of experience of the video to be predicted can be expressed as:
predicting the quality of experience of the video to be predicted by number, which is expressed as:
Q n ＝P n +S n
wherein Q is n Expressed as quality of experience, P n Expressed as presentation quality, S n Represented as an influence function.
As described above, in the present disclosure, first, a video to be predicted is acquired and a characterization problem of the video to be predicted is determined, and then the presentation quality of the video to be predicted is determined by based on the characterization problem of the video to be predicted. Then, calculating pause loss generated by pause events in the video to be predicted, and discretizing the pause loss to obtain an influence function of the pause events on the video to be predicted. And finally, predicting the experience quality of the video to be predicted through the presentation quality of the video to be predicted and the influence function of the pause event on the video to be predicted.
In summary, in the process of predicting the quality of experience of video, the present disclosure fully considers the quality evaluation of video by a viewer when viewing video, and the influence of a pause event generated in video playing on the viewing experience of the viewer. The final predicted experience quality can reflect the watching experience of the viewer more accurately, and the video operation platform is convenient to improve and perfect the video more pertinently.
Based on the same technical concept, the present disclosure further provides a device for predicting video experience quality, which corresponds to the method of any embodiment, and the method for predicting video experience quality according to any embodiment can be implemented by using the device for predicting video experience quality provided by the present disclosure.
Fig. 2 is a schematic structural diagram of a prediction apparatus for video experience quality according to an embodiment of the present disclosure.
The prediction apparatus for video experience quality shown in fig. 2 further includes the following modules:
a presentation quality determination module 10, an impact function determination module 20, and a quality of experience prediction module 30;
wherein the presentation quality determination module 10 is configured to: and acquiring a video to be predicted, and determining the presentation quality of the video to be predicted. The method specifically comprises the following steps:
determining a characterization problem of the video to be predicted;
extracting image features of the video to be predicted based on the characterization problem to obtain a feature extraction graph;
determining the presentation quality of the video to be tested based on the feature extraction graph;
wherein the presentation quality is expressed as:
P n ＝V(X n ,R n )
wherein the P is n Expressed as the presentation quality, the V is expressed as a quality fraction of the video to be predicted, the X n An nth frame represented as streaming video, said R n An nth frame represented as an original quality video.
The influence function determination module 20 is configured to: and receiving a pause event in the video to be predicted, and generating an influence function of the pause event on the video to be predicted. The method specifically comprises the following steps:
substituting the pause event into an exponential decay function to determine pause loss of the pause event;
summing the pause losses of the pause event to obtain a set of the pause losses;
generating an influence function of the pause event on the video to be predicted based on the set of pause losses;
wherein the pause loss of the pause event is expressed as:
wherein S is k (t) is denoted as a pause loss,
a proportional function expressed as an decay function, t expressed as a time instance, f expressed as a frame rate, i k And l k Represented as assuming that the kth pause event is located at [ i ] k ，i k +l k ]On, k represents the time length of the pause, T 0 Expressed as unsatisfactory rate, T 1 Expressed as relative intensity of memory;
the step of summing the pause losses of the pause event to obtain a set of pause losses, expressed as:
wherein S (t) is expressed as a set of pause losses, S k (t) is denoted as pause loss, N is the total number of pause events.
Discretizing the pause loss set to obtain an influence function of the pause event on the video to be predicted;
wherein the influence function is expressed as:
wherein S is n Represented as an influence function;
expressed as a converted form after discrete processing of S (t), where n is expressed as an instance of discrete time, i.e. the number of pause events, and f is expressed as the frame rate.
The quality of experience prediction module 30 is configured to: and predicting the experience quality of the video to be predicted according to the presentation quality and the influence function. The method specifically comprises the following steps:
wherein the quality of experience is expressed as:
Q n ＝P n +S n
wherein Q is n Expressed as quality of experience, P n Expressed as presentation quality, S n Represented as an influence function.
Based on the same technical concept, the disclosure also provides an electronic device corresponding to the method of any embodiment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the method for predicting the video experience quality according to any embodiment when executing the program.
Fig. 3 shows a more specific hardware architecture of an electronic device according to this embodiment, where the device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 implement communication connections therebetween within the device via a bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit ), microprocessor, application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc. for executing relevant programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory ), static storage device, dynamic storage device, or the like. Memory 1020 may store an operating system and other application programs, and when the embodiments of the present specification are implemented in software or firmware, the associated program code is stored in memory 1020 and executed by processor 1010.
The input/output interface 1030 is used to connect with an input/output module for inputting and outputting information. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various types of sensors, etc., and the output devices may include a display, speaker, vibrator, indicator lights, etc.
It should be noted that although the above-described device only shows processor 1010, memory 1020, input/output interface 1030, communication interface 1040, and bus 1050, in an implementation, the device may include other components necessary to achieve proper operation. Furthermore, it will be understood by those skilled in the art that the above-described apparatus may include only the components necessary to implement the embodiments of the present description, and not all the components shown in the drawings.
The electronic device of the foregoing embodiment is configured to implement the corresponding method for predicting the quality of experience of video in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which is not described herein.
Based on the same technical concept, corresponding to the method of any embodiment described above, the present disclosure further provides a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method for predicting video experience quality according to any embodiment described above.
The computer readable media of the present embodiments, including both permanent and non-permanent, removable and non-removable media, may be used to implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device.
The storage medium of the foregoing embodiments stores computer instructions for causing the computer to execute the method for predicting video experience quality according to any one of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the disclosure, including the claims, is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined under the idea of the present disclosure, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present disclosure as described above, which are not provided in details for the sake of brevity.
Additionally, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures, in order to simplify the illustration and discussion, and so as not to obscure the embodiments of the present disclosure. Furthermore, the devices may be shown in block diagram form in order to avoid obscuring the embodiments of the present disclosure, and this also accounts for the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform on which the embodiments of the present disclosure are to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the disclosure, it should be apparent to one skilled in the art that embodiments of the disclosure can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative in nature and not as restrictive.
While the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of those embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.
The disclosed embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Accordingly, any omissions, modifications, equivalents, improvements, and the like, which are within the spirit and principles of the embodiments of the disclosure, are intended to be included within the scope of the disclosure.
Claims (10)
1. A method for predicting quality of experience of a video, comprising:
acquiring a video to be predicted, and determining the presentation quality of the video to be predicted;
responding to a pause event in the video to be predicted, and generating an influence function of the pause event on the video to be predicted;
and predicting the experience quality of the video to be predicted according to the presentation quality of the video to be predicted and the influence function.
2. The method of claim 1, wherein the determining the presentation quality of the video to be predicted comprises:
determining a characterization problem of the video to be predicted;
and determining the presentation quality of the video to be predicted based on the characterization problem.
3. The method of claim 2, wherein the determining the presentation quality of the video to be predicted based on the characterization question comprises:
extracting image features of the video to be predicted based on the characterization problem to obtain a feature extraction graph;
determining the presentation quality of the video to be tested based on the feature extraction graph;
wherein the presentation quality is expressed as:
P n ＝V(X n ,R n )
wherein the P is n Expressed as the presentation quality, the V is expressed as a quality fraction of the video to be predicted, the X n An nth frame represented as streaming video, said R n An nth frame represented as an original quality video.
4. The method of claim 1, wherein the generating an impact function of the pause event on the video to be predicted comprises:
substituting the pause event into an exponential decay function to determine pause loss of the pause event;
summing the pause losses of the pause event to obtain a set of the pause losses;
generating an influence function of the pause event on the video to be predicted based on the set of pause losses;
wherein the pause loss of the pause event is expressed as:
wherein S is k (t) is denoted as a pause loss,
a proportional function expressed as an decay function, t expressed as a time instance, f expressed as a frame rate, i k And l k Represented as assuming that the kth pause event is located at [ i ] k ，i k +l k ]On, k represents the time length of the pause, T 0 Expressed as unsatisfactory rate, T 1 Expressed as the relative intensity of memory.
5. The method of claim 4, wherein summing the pause losses for the pause event results in a set of pause losses expressed as:
wherein S (t) is expressed as a set of pause losses, S k (t) is denoted as pause loss, N is the total number of pause events.
6. The method of claim 4, wherein the generating an impact function of the pause event on the video to be predicted based on the set of pause losses comprises:
discretizing the pause loss set to obtain an influence function of the pause event on the video to be predicted;
wherein the influence function is expressed as:
wherein S is n Represented as an influence function;
expressed as a converted form after discrete processing of S (t), where n is expressed as an instance of discrete time, i.e. the number of pause events, and f is expressed as the frame rate.
7. The method of claim 1, wherein predicting the quality of experience of the video to be predicted from the quality of presentation of the video to be predicted and the impact function is expressed as:
Q n ＝P n +S n
wherein Q is n Expressed as quality of experience, P n Expressed as presentation quality, S n Represented as an influence function.
8. A video quality of experience prediction apparatus, comprising:
a presentation quality determination module configured to: acquiring a video to be predicted, and determining the presentation quality of the video to be predicted;
an influence function determination module configured to: receiving a pause event in the video to be predicted, and generating an influence function of the pause event on the video to be predicted;
a quality of experience prediction module configured to: and predicting the experience quality of the video to be predicted according to the presentation quality and the influence function.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 7 when the program is executed by the processor.
10. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211601452.6A CN116074586A (en) | 2022-12-13 | 2022-12-13 | Video experience quality prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211601452.6A CN116074586A (en) | 2022-12-13 | 2022-12-13 | Video experience quality prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116074586A true CN116074586A (en) | 2023-05-05 |
Family
ID=86181184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211601452.6A Pending CN116074586A (en) | 2022-12-13 | 2022-12-13 | Video experience quality prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116074586A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103501434A (en) * | 2013-09-17 | 2014-01-08 | 北京奇艺世纪科技有限公司 | Method and device for analyzing quality of video |
| 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 |
| US20170048297A1 (en) * | 2011-12-16 | 2017-02-16 | Netflix Corporation | Measuring user quality of experience for a streaming media service |
| CN109451303A (en) * | 2018-12-24 | 2019-03-08 | 合肥工业大学 | A kind of modeling method for user experience quality QoE in VR video |
| CN111401637A (en) * | 2020-03-16 | 2020-07-10 | 湖南大学 | User experience quality prediction method fusing user behavior and expression data |
-
2022
- 2022-12-13 CN CN202211601452.6A patent/CN116074586A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170048297A1 (en) * | 2011-12-16 | 2017-02-16 | Netflix Corporation | Measuring user quality of experience for a streaming media service |
| CN103501434A (en) * | 2013-09-17 | 2014-01-08 | 北京奇艺世纪科技有限公司 | Method and device for analyzing quality of video |
| 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 |
| CN109451303A (en) * | 2018-12-24 | 2019-03-08 | 合肥工业大学 | A kind of modeling method for user experience quality QoE in VR video |
| CN111401637A (en) * | 2020-03-16 | 2020-07-10 | 湖南大学 | User experience quality prediction method fusing user behavior and expression data |
Non-Patent Citations (3)
| Title |
|---|
| 奚子为: "无线网络视频体验质量（QoE）的建模与预测研究", 中国优秀硕士学位论文, 15 August 2020 (2020-08-15), pages 1 - 47 * |
| 杨箭;: "基于用户行为与内容综合分析评估的视频推荐方法研究", 电子技术与软件工程, no. 13, 1 July 2016 (2016-07-01) * |
| 马栋林;王孝通;张澍寰;郭娅婷;: "基于用户行为的教学视频内容质量评价方法", 兰州理工大学学报, no. 03, 15 June 2020 (2020-06-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20170076321A1 (en) | Predictive analytics in an automated sales and marketing platform | |
| CN112905839A (en) | Model training method, model using device, storage medium and equipment | |
| US10129504B2 (en) | Method and system for measuring quality of video call | |
| CN110278447B (en) | Video pushing method and device based on continuous features and electronic equipment | |
| CN112037223B (en) | Image defect detection method and device and electronic equipment | |
| CN109446025B (en) | Operation behavior playback method and device, electronic equipment and readable medium | |
| CN117235586B (en) | Hotel customer portrait construction method, system, electronic equipment and storage medium | |
| CN109376419B (en) | Data model generation method and device, electronic equipment and readable medium | |
| CN104205850A (en) | Signal analysis and generation of transient information | |
| CN112182281B (en) | Audio recommendation method, device and storage medium | |
| CN114417146A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN110378936B (en) | Optical flow calculation method and device and electronic equipment | |
| CN117453509A (en) | Webpage performance grading method, device, equipment and medium | |
| CN116074586A (en) | Video experience quality prediction method and device, electronic equipment and storage medium | |
| CN110555861A (en) | optical flow calculation method and device and electronic equipment | |
| CN111798263A (en) | Transaction trend prediction method and device | |
| CN111832354A (en) | Target object age identification method and device and electronic equipment | |
| CN111612158A (en) | Model deployment method, device, equipment and storage medium | |
| CN114510305B (en) | Model training method and device, storage medium and electronic equipment | |
| CN113360773B (en) | Recommendation method and device, storage medium and electronic equipment | |
| CN114298403A (en) | Method and device for predicting attention degree of work | |
| CN113420809A (en) | Video quality evaluation method and device and electronic equipment | |
| US10203833B2 (en) | Recommending application modifications using image area counts | |
| KR101735420B1 (en) | Apparatus and method for inspecting user interface | |
| CN117729358B (en) | Data processing method, apparatus, device, computer readable storage medium and product |
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 |