CN113840131B - Video call quality evaluation method and device, electronic equipment and readable storage medium - Google Patents
Video call quality evaluation method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN113840131B CN113840131B CN202010513657.3A CN202010513657A CN113840131B CN 113840131 B CN113840131 B CN 113840131B CN 202010513657 A CN202010513657 A CN 202010513657A CN 113840131 B CN113840131 B CN 113840131B
- Authority
- CN
- China
- Prior art keywords
- video
- audio
- score
- parameters
- video call
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/141—Systems for two-way working between two video terminals, e.g. videophone
Abstract
The invention discloses a video call quality evaluation method, a video call quality evaluation device, electronic equipment and a readable storage medium, and belongs to the technical field of multimedia communication. The video call quality assessment method comprises the following steps: acquiring relevant audio and video parameters of the current video call; inputting a first type parameter in the audio-video related parameters into a pre-trained first evaluation model to obtain a first score of the current video call; inputting a second type parameter in the audio-video related parameters into a pre-trained second evaluation model to obtain a second score of the current video call; determining the quality of the current video call according to the first score and the second score; the first evaluation model is trained by using a first training data set collected based on unidirectional simulation video call, and the second evaluation model is trained by using a second training data set collected based on bidirectional video call. According to the embodiment of the invention, the video call quality can be efficiently evaluated.
Description
Technical Field
The present invention relates to the field of multimedia communications technologies, and in particular, to a method and apparatus for evaluating quality of a video call, an electronic device, and a readable storage medium.
Background
With the popularization of video call services, the demand for video call quality is increasing. At present, a subjective assessment method is mainly used for assessing the video call quality. In the subjective evaluation method, subjective experience of a user using the video call service can be directly obtained. However, the subjective evaluation method requires human intervention, and only can obtain sampling evaluation results, so that the video call quality cannot be evaluated efficiently.
Disclosure of Invention
The embodiment of the invention aims to provide a video call quality assessment method, a video call quality assessment device, electronic equipment and a readable storage medium, so as to solve the problem that video call quality cannot be assessed efficiently at present.
In order to solve the technical problems, the application is realized as follows:
in a first aspect, an embodiment of the present invention provides a method for evaluating quality of a video call, including:
acquiring relevant audio and video parameters of the current video call;
inputting a first type parameter in the audio-video related parameters into a pre-trained first evaluation model to obtain a first score of the current video call;
inputting a second type parameter in the audio-video related parameters into a pre-trained second evaluation model to obtain a second score of the current video call;
determining the quality of the current video call according to the first score and the second score;
the first evaluation model is obtained by training a first training data set, and training parameters in the first training data set are obtained based on unidirectional simulation video call collection; the second evaluation model is obtained by training a second training data set, and training parameters in the second training data set are obtained based on bidirectional video call collection.
In a second aspect, an embodiment of the present invention provides a video call quality evaluation apparatus, including:
the acquisition module is used for acquiring the audio and video related parameters of the current video call;
the first evaluation module is used for inputting a first type parameter in the audio-video related parameters into a pre-trained first evaluation model to obtain a first score of the current video call;
the second evaluation module is used for inputting a second type parameter in the audio-video related parameters into a pre-trained second evaluation model to obtain a second score of the current video call;
the determining module is used for determining the quality of the current video call according to the first score and the second score;
the first evaluation model is obtained by training a first training data set, and training parameters in the first training data set are obtained based on unidirectional simulation video call collection; the second evaluation model is obtained by training a second training data set, and training parameters in the second training data set are obtained based on bidirectional video call collection.
In a third aspect, an embodiment of the present invention provides an electronic device, where the electronic device includes a processor, a memory, and a computer program stored on the memory and executable on the processor, where the computer program when executed by the processor can implement the video call quality assessment method as described above.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a video call quality assessment method as described above.
In an embodiment of the present invention, the quality of the current video call may be determined by scoring the current video call based on a first evaluation model and a second evaluation model that are trained using a first training data set collected based on unidirectional analog video calls, and a second evaluation model that is trained using a second training data set collected based on bidirectional video calls. Therefore, the influence caused by the sample size of the data set and the user interaction experience in the video call process is comprehensively considered in the model building and training process, so that the model output result can be well fitted with the user subjective experience, and the video call quality can be effectively evaluated.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 is a flowchart of a video call quality evaluation method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a video call quality evaluation process according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a video call quality evaluation device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the "first" and "second" distinguished objects generally are of the type and do not limit the number of objects, e.g., the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/" generally means a relationship in which the associated object is an "or" before and after.
In order to solve the problem that the video call quality cannot be efficiently evaluated at present, the embodiment of the invention provides a reference-free video call quality evaluation method, which can evaluate the quality of video call service under the condition that an original video sequence is not referenced, and the evaluation result can be well fit with subjective experience of a user. The no-reference means that the video call quality after transmission is calculated by only using the audio and video parameters of the receiving end and other network transmission parameters. In the video call quality assessment method, a video call subjective test result can be collected first and used as a training and verification data set of an objective assessment model, a unidirectional simulation video call and a bidirectional video call are combined in the establishment process of the data set, then an objective assessment model is established, the objective assessment model comprises a plurality of sub-assessment models, each sub-assessment model is trained by using different types of data sets respectively, finally video call quality assessment is carried out based on the trained objective assessment model, namely, video call quality scores are obtained through assessment, and the quality of corresponding video calls is determined based on the video call quality scores.
For unidirectional analog video call, a single user can watch a video file recorded in advance to give subjective scores. The call mode is easy to develop, and when the data set for training the evaluation model is collected based on unidirectional analog video call, a large amount of data can be collected, so that model training and verification are facilitated. For a two-way video call, subjective scores are respectively given by users participating in the call after the call is ended. The method considers the influence of interaction experience in the video call service on the user, and compared with a data set obtained based on unidirectional simulation video call, the evaluation model trained based on the data set obtained based on bidirectional video call is used, so that the evaluation result can be better fit with subjective experience of the user. However, the two-way video call mode is complex to develop, and a large amount of data is inconvenient to collect.
Therefore, in the model building and training process, the influence caused by the sample size of the data set and the user interaction experience in the video call process is comprehensively considered, and the obtained objective evaluation model can better fit the subjective user experience in the video call process, so that the video call quality can be evaluated efficiently based on the objective evaluation model.
Referring to fig. 1, fig. 1 is a flowchart of a video call quality evaluation method according to an embodiment of the present invention, where the method is applied to an electronic device, as shown in fig. 1, and the method includes the following steps:
step 101: and acquiring the audio and video related parameters of the current video call.
In this embodiment, the audio/video related parameters do not depend on the original video of the video call. The audio-video related parameters may include, but are not limited to: 1) Parameters related to audio and video quality factors, such as video coding mode, audio coding mode, video code rate, audio code rate, video frame rate, video resolution, etc.; 2) Parameters related to terminal factors such as terminal type, terminal resolution, etc.; the terminal type is, for example, a personal computer (Personal Computer, PC), a television TV, a mobile phone, etc.; 3) Parameters related to network transmission impairment factors, such as video delay, audio delay, video packet loss rate, audio packet loss rate, etc.
Step 102: and inputting the first type of parameters in the audio and video related parameters into a pre-trained first evaluation model to obtain a first score of the current video call.
In this embodiment, the first evaluation model is obtained by training with a first training data set, and training parameters in the first training data set are obtained based on unidirectional analog video call collection. Therefore, the first training data set is collected based on unidirectional simulation video call, and a large amount of data can be collected, so that the data volume of training parameters in the first training data set is ensured, and model training and verification are facilitated.
It can be appreciated that the first type of parameters in the above-mentioned audio-video related parameters are the same as the type of model input training parameters in the first training dataset.
Step 103: and inputting the second type of parameters in the audio and video related parameters into a pre-trained second evaluation model to obtain a second score of the current video call.
In this embodiment, the second evaluation model is obtained by training with a second training data set, and training parameters in the second training data set are obtained based on bidirectional video call collection. Therefore, the second training data set is collected based on the bidirectional video call, and the influence of interaction experience in the video call service on the user can be considered, so that the evaluation result of the second evaluation model trained by the second training data set is better fit with subjective experience of the user.
It can be appreciated that the second type of parameter in the above-mentioned audio-video related parameters is the same type as the model input training parameters in the second training dataset.
Step 104: and determining the quality of the current video call according to the first score and the second score.
Optionally, after the first score and the second score are obtained, an overall quality score of the current video call may be calculated based on a preset rule (such as a weighted average manner, etc.), and the quality of the current video call may be determined based on the overall quality score. For example, if the overall quality score is below a preset threshold (e.g., 0.4, 0.45, etc.), it may be determined that the quality of the current video call is poor; or if the overall quality score is greater than or equal to a preset threshold, it may be determined that the quality of the current video call is good.
The video call quality evaluation method in the embodiment of the invention can score the current video call based on a first evaluation model and a second evaluation model which are trained on the basis of a first training data set collected on the basis of unidirectional analog video call, and the second evaluation model is trained on the basis of a second training data set collected on the basis of bidirectional video call, so as to determine the quality of the current video call. Therefore, the influence caused by the sample size of the data set and the user interaction experience in the video call process is comprehensively considered in the model building and training process, so that the model output result can be well fitted with the user subjective experience, and the video call quality can be effectively evaluated.
In the embodiment of the invention, considering the complexity of developing the subjective test of the video call and the condition that a large amount of sample data is required for model training, and the influence of different types of parameters on the video call process of the user is different, the first evaluation model and the second evaluation model can comprise a plurality of evaluation models, and each evaluation model is obtained by training by using different types of data sets. Therefore, on the premise that data set collection and model training are more conveniently carried out, the model accuracy is better improved, and the video call quality is better evaluated.
Optionally, the first evaluation model may include an audio quality evaluation model, a video quality evaluation model, and an audio video quality evaluation model. The first type of parameters may include audio parameters, video parameters, and terminal parameters. The process of obtaining the first score of the current video call in step 102 may include:
inputting the audio parameters into the audio quality assessment model to obtain an audio quality score of the current video call;
inputting the video parameters and terminal parameters (such as terminal type and terminal resolution) into the video quality assessment model to obtain a video quality score of the current video call;
and inputting the audio quality score and the video quality score into the audio and video quality assessment model to obtain the first score.
Therefore, by dividing the first assessment model into the audio quality assessment model, the video quality assessment model and the audio and video quality assessment model, different data sets can be used for training aiming at different assessment models, so that the model accuracy is improved, and the video call quality is better assessed.
Optionally, the audio parameters may include at least one of: audio coding mode, audio code rate, audio packet loss rate, etc. The video parameters may include at least one of: video coding mode, video code rate, video frame rate, video packet loss rate, etc. The terminal parameters may include at least one of: terminal type, terminal resolution, etc.
Optionally, the second evaluation model may include an audio-video interaction delay evaluation model and an audio-video interaction synchronization evaluation model. The second score includes an audio-video interaction delay score and an audio-video interaction synchronization score. The second type of parameters includes audio delay and video delay. The process of obtaining the second score of the current video call in step 103 may include:
inputting the audio time delay and the video time delay into the audio-video interaction time delay evaluation model to obtain an audio-video interaction time delay score of the current video call;
and inputting the audio time delay and the video time delay into the audio-video interaction synchronization evaluation model to obtain the audio-video interaction synchronization score of the current video call.
Therefore, by dividing the second evaluation model into the audio-video interaction time delay evaluation model and the audio-video interaction synchronization evaluation model, different evaluation models can be trained respectively, so that the model accuracy is improved, and the video call quality is better evaluated.
Optionally, the determining the quality of the current video call in step 104 may include: inputting the first score and the second score into a pre-trained video call quality evaluation module to obtain a quality score of the current video call; and determining the quality of the current video call according to the quality score of the current video call. Thus, the quality score of the current video call is obtained by means of the pre-trained video call quality evaluation module, and the quality score of the video call can be accurately obtained.
The video call quality evaluation process in the embodiment of the present invention will be described with reference to fig. 2.
In the embodiment of the present invention, as shown in fig. 2, because factors influencing user experience mainly include video/audio quality factors, terminal related factors and network transmission damage factors in the video call process, the overall evaluation model can be divided into several evaluation models according to these factors without depending on the original video of the video call:
1) Audio quality assessment model: according to the audio coding mode, the audio code rate and the audio packet loss rate of the video call, calculating the audio quality score of the video call, as follows:
quality_a=f (audio coding, audio code rate, audio packet loss rate)
2) Video quality assessment model: according to the video coding mode, video code rate, video frame rate, video packet loss rate, terminal type and terminal resolution of the video call, calculating to obtain the video quality score of the video call, as follows:
SQuality v ＝
f (video coding, video code rate, video frame rate, video packet loss rate, terminal type, terminal resolution)
3) Audio and video quality assessment model: according to the audio quality score and the video quality score of the video call, the audio and video quality score of the video call is comprehensively calculated as follows:
SQuality＝f(SQuality_a,SQuality_v)
4) Audio and video interaction time delay evaluation model: according to the audio time delay and the video time delay of the video call, the audio-video interaction time delay score of the video call is calculated, as follows:
sdelay=f (audio delay, video delay)
5) Audio and video interaction synchronization evaluation model: according to the audio time delay and the video time delay of the video call, the audio-video interaction synchronization score of the video call is calculated, as follows:
ssync=f (audio delay, video delay)
6) Video call quality assessment model: according to the audio and video quality score, the audio and video interaction time delay score and the audio and video interaction synchronization score of the video call, the overall quality score of the video call is comprehensively calculated, and the overall quality score is obtained as follows:
S_MOS＝f(SQuality,SDelay,SSync)
specifically, according to the characteristics of the different evaluation models in the above 1) to 6), different data sets may be selected for training in this embodiment. The influence of the video and audio quality factors and the terminal factors on the user video call experience is similar to the influence of the user watching video stream experience, so that the subjective test data set can be collected by using a unidirectional analog video call mode. When a user performs a video call, because interaction between two parties is involved, the user is more sensitive to audio and video time delay and audio and video synchronization caused by a network, and therefore, a subjective test data set needs to be collected by developing a bidirectional video call.
Optionally, when collecting the data set based on the unidirectional analog video call mode, video sequences with different resolutions and different frame rates can be used, different video coding formats and audio coding formats are used for coding the data set according to the set code rate, packet loss processing is performed through a packet loss tool, and a user performs operations of watching video, listening to audio or watching video and listening to audio simultaneously on different terminal devices to record three subjective scores of audio, video and audio-video respectively. Furthermore, the video coding mode, the video code rate, the video frame rate, the video resolution, the video packet loss rate, the terminal type and the terminal resolution used in the mode can be arranged into a video data set, and subjective scores given by a user are used as corresponding labels to train a video quality evaluation model; the audio resolution, the audio code rate, the audio coding format and the audio packet loss rate are used for being arranged into an audio data set, subjective scores given by a user are used as corresponding labels, and the subjective scores are used for training an audio quality assessment model; and taking the audio scores and the video scores as inputs, taking subjective scores of users on the audio and video quality as labels, and training an audio and video quality evaluation module.
Optionally, when collecting the data set based on the bidirectional video call mode, different audio parameters, video parameters, terminal types and network packet loss rates can be used, different audio and video time delays (including the case that the audio time delays are the same or different, and/or including the case that the video time delays are the same or different) are set, the user performs the video call, and the participating users after the call is ended respectively give subjective scores about the time delays, the audio and video synchronization (under the case that the audio time delays and the video time delays are different), and the overall call quality. Because the audio and video quality model is trained by using the data set collected based on the unidirectional analog video call, the bidirectional video call is developed mainly by combining different audio time delays and video time delays, so that the complexity of subjective test development is reduced, and the data collection is facilitated. Further, the video time delay, the audio time delay and the subjective scores of the users collected in the mode are arranged into a data set, and the data set is used for training an audio-video interaction time delay module, an audio-video interaction synchronization module and a video call quality evaluation module respectively.
The video call quality evaluation model proposed in this embodiment, each evaluation model function may be obtained through artificial intelligence (Artificial Intelligence, AI) or a fitting method according to a training data set, or may be obtained through modeling. The video call quality evaluation model obtained through training by the method provided by the scheme comprehensively considers the influence of audio and video factors, terminal factors and network transmission factors on user experience, especially considers the influence of audio and video time delay and synchronization on video call service, can evaluate the user experience in actual video call service, and does not need original video source and video frame information.
In one embodiment, as shown in fig. 2, when a quality evaluation is performed on a video call, an audio quality score obtained based on an audio quality evaluation model may be 0.21, a video quality score obtained based on a video quality evaluation model may be 0.22, and the audio quality score 0.21 and the video quality score 0.22 are further input into the audio and video quality evaluation model, so that an audio and video quality score is 0.35; in addition, the audio-video interaction time delay score obtained based on the audio-video interaction time delay evaluation model can be 0.23, the audio-video interaction synchronization score obtained based on the audio-video interaction synchronization evaluation model can be 0.24, the audio-video quality score of 0.35, the audio-video interaction time delay score of 0.23 and the audio-video interaction synchronization score of 0.24 are further input into the video call quality evaluation model, and the quality score (namely the overall quality score) of the obtained video call is 0.46. Further, if the preset score threshold is 0.4, the quality of the video call can be determined to be good because 0.46 is greater than 0.4.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a video call quality assessment apparatus according to an embodiment of the present invention, where the apparatus is applied to an electronic device, as shown in fig. 3, the video call quality assessment apparatus 30 may include:
the obtaining module 31 is configured to obtain an audio/video related parameter of a current video call;
a first evaluation module 32, configured to input a first type parameter of the audio/video related parameters into a first pre-trained evaluation model, to obtain a first score of the current video call;
a second evaluation module 33, configured to input a second type of parameter of the audio/video related parameters into a second pre-trained evaluation model, to obtain a second score of the current video call;
a determining module 34, configured to determine a quality of the current video call according to the first score and the second score;
the first evaluation model is obtained by training a first training data set, and training parameters in the first training data set are obtained based on unidirectional simulation video call collection; the second evaluation model is obtained by training a second training data set, and training parameters in the second training data set are obtained based on bidirectional video call collection.
Optionally, the first evaluation model includes an audio quality evaluation model, a video quality evaluation model, and an audio and video quality evaluation model; the first type of parameters comprise audio parameters, video parameters and terminal parameters;
the first evaluation module 32 includes:
the first evaluation unit is used for inputting the audio parameters into the audio quality evaluation model to obtain the audio quality score of the current video call;
the second evaluation unit is used for inputting the video parameters and the terminal parameters into the video quality evaluation model to obtain the video quality score of the current video call;
and the third evaluation unit is used for inputting the audio quality score and the video quality score into the audio and video quality evaluation model to obtain the first score.
Optionally, the audio parameters include at least one of: audio coding mode, audio code rate and audio packet loss rate;
and/or, the video parameters include at least one of: video coding mode, video code rate, video frame rate and video packet loss rate;
and/or, the terminal parameters include at least one of the following: terminal type, terminal resolution.
Optionally, the second evaluation model includes an audio-video interaction delay evaluation model and an audio-video interaction synchronization evaluation model; the second score comprises an audio-video interaction delay score and an audio-video interaction synchronization score;
the second type of parameters include audio delay and video delay;
the second evaluation module 33 includes:
the fourth evaluation unit is used for inputting the audio time delay and the video time delay into the audio-video interaction time delay evaluation model to obtain an audio-video interaction time delay score of the current video call;
and the fifth evaluation unit is used for inputting the audio time delay and the video time delay into the audio-video interaction synchronization evaluation model to obtain the audio-video interaction synchronization score of the current video call.
Optionally, the determining module 34 includes:
a sixth evaluation unit, configured to input the first score and the second score into a pre-trained video call quality evaluation module, to obtain a quality score of the current video call;
and the determining unit is used for determining the quality of the current video call according to the quality score of the current video call.
It can be appreciated that the video call quality evaluation device 30 according to the embodiment of the present invention can implement the processes of the method embodiment shown in fig. 1 and achieve the same technical effects, and for avoiding repetition, the description is omitted here.
In addition, the embodiment of the invention further provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the computer program can realize each process of the embodiment of the method shown in fig. 1 and achieve the same technical effect when being executed by the processor, and the repetition is avoided.
Referring to fig. 4, an embodiment of the present invention further provides an electronic device 40, which includes a bus 41, a transceiver 42, an antenna 43, a bus interface 44, a processor 45, and a memory 46.
In an embodiment of the present invention, the electronic device 40 further includes: a computer program stored on the memory 46 and executable on the processor 45. Alternatively, the computer program may implement the following steps when executed by the processor 45:
acquiring relevant audio and video parameters of the current video call;
inputting a first type parameter in the audio-video related parameters into a pre-trained first evaluation model to obtain a first score of the current video call; the first evaluation model is obtained by training a first training data set, and training parameters in the first training data set are obtained based on unidirectional simulation video call collection;
inputting a second type parameter in the audio-video related parameters into a pre-trained second evaluation model to obtain a second score of the current video call; the second evaluation model is obtained by training a second training data set, and training parameters in the second training data set are obtained based on bidirectional video call collection;
determining the quality of the current video call according to the first score and the second score;
it will be appreciated that the computer program, when executed by the processor 45, may implement the processes of the method embodiment shown in fig. 1 and achieve the same technical effects, and will not be repeated here.
In fig. 4, a bus architecture (represented by bus 41), the bus 41 may comprise any number of interconnected buses and bridges, with the bus 41 linking together various circuits, including one or more processors, represented by processor 45, and memory, represented by memory 46. The bus 41 may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., which are well known in the art and, therefore, will not be described further herein. Bus interface 44 provides an interface between bus 41 and transceiver 42. The transceiver 42 may be one element or may be a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor 45 is transmitted over a wireless medium via the antenna 43, and further, the antenna 43 receives data and transmits the data to the processor 45.
The processor 45 is responsible for managing the bus 41 and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory 46 may be used to store data used by processor 45 in performing operations.
Alternatively, the processor 45 may be CPU, ASIC, FPGA or a CPLD.
The embodiment of the present invention further provides a computer readable storage medium, on which a computer program is stored, where the computer program when executed by a processor can implement each process of the embodiment of the method shown in fig. 1 and achieve the same technical effects, and in order to avoid repetition, a description is omitted here.
Computer-readable media include both permanent and non-permanent, removable and non-removable media, and information storage may be implemented 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. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should be noted that, in this document, 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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a service classification device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.
Claims (6)
1. A video call quality assessment method, comprising:
acquiring relevant audio and video parameters of the current video call;
inputting a first type parameter in the audio-video related parameters into a pre-trained first evaluation model to obtain a first score of the current video call;
inputting a second type parameter in the audio-video related parameters into a pre-trained second evaluation model to obtain a second score of the current video call;
determining the quality of the current video call according to the first score and the second score;
the first evaluation model is obtained by training a first training data set, training parameters in the first training data set are obtained based on unidirectional simulation video call collection, and the first type parameters are the same as the training parameters in the first training data set in type; the second evaluation model is obtained by training a second training data set, training parameters in the second training data set are obtained based on bidirectional video call collection, and the second type parameters are the same as the training parameters in the second training data set;
the first evaluation model comprises an audio quality evaluation model, a video quality evaluation model and an audio and video quality evaluation model;
the first type of parameters comprise audio parameters, video parameters and terminal parameters;
inputting a first type parameter in the audio-video related parameters into a pre-trained first evaluation model to obtain a first score of the current video call, wherein the first score comprises:
inputting the audio parameters into the audio quality assessment model to obtain audio quality scores of subjective experiences of the fitting users of the current video call;
inputting the video parameters and the terminal parameters into the video quality evaluation model to obtain video quality scores of subjective experiences of fitting users of the current video call;
inputting the audio quality score and the video quality score into the audio and video quality assessment model to obtain the first score fitting subjective experience of a user;
the second evaluation model comprises an audio-video interaction delay evaluation model and an audio-video interaction synchronization evaluation model; the second score comprises an audio-video interaction delay score and an audio-video interaction synchronization score;
the second type of parameters include audio delay and video delay;
inputting a second type parameter of the audio-video related parameters into a pre-trained second evaluation model to obtain a second score of the current video call, wherein the second score comprises:
inputting the audio time delay and the video time delay into the audio-video interaction time delay evaluation model to obtain audio-video interaction time delay scores of the subjective experience of the fitting user of the current video call;
and inputting the audio time delay and the video time delay into the audio-video interaction synchronization evaluation model to obtain the audio-video interaction synchronization score of the subjective experience of the fitting user of the current video call.
2. The method of claim 1, wherein the audio parameters include at least one of: audio coding mode, audio code rate and audio packet loss rate;
and/or, the video parameters include at least one of: video coding mode, video code rate, video frame rate and video packet loss rate;
and/or, the terminal parameters include at least one of the following: terminal type, terminal resolution.
3. The method of claim 1, wherein determining the quality of the current video call based on the first score and the second score comprises:
inputting the first score and the second score into a pre-trained video call quality evaluation module to obtain a quality score of the current video call;
and determining the quality of the current video call according to the quality score of the current video call.
4. A video call quality assessment apparatus, comprising:
the acquisition module is used for acquiring the audio and video related parameters of the current video call;
the first evaluation module is used for inputting a first type parameter in the audio-video related parameters into a pre-trained first evaluation model to obtain a first score of the current video call;
the second evaluation module is used for inputting a second type parameter in the audio-video related parameters into a pre-trained second evaluation model to obtain a second score of the current video call;
the determining module is used for determining the quality of the current video call according to the first score and the second score;
the first evaluation model is obtained by training a first training data set, training parameters in the first training data set are obtained based on unidirectional simulation video call collection, and the first type parameters are the same as the training parameters in the first training data set in type; the second evaluation model is obtained by training a second training data set, training parameters in the second training data set are obtained based on bidirectional video call collection, and the second type parameters are the same as the training parameters in the second training data set;
the first evaluation model comprises an audio quality evaluation model, a video quality evaluation model and an audio and video quality evaluation model;
the first type of parameters comprise audio parameters, video parameters and terminal parameters;
the first evaluation module includes:
the first evaluation unit is used for inputting the audio parameters into the audio quality evaluation model to obtain audio quality scores of subjective experiences of the fitting users of the current video call;
the second evaluation unit is used for inputting the video parameters and the terminal parameters into the video quality evaluation model to obtain video quality scores of subjective experiences of the fitting users of the current video call;
the third evaluation unit is used for inputting the audio quality score and the video quality score into the audio and video quality evaluation model to obtain the first score fitting the subjective experience of the user;
the second evaluation model comprises an audio-video interaction delay evaluation model and an audio-video interaction synchronization evaluation model; the second score comprises an audio-video interaction delay score and an audio-video interaction synchronization score;
the second type of parameters include audio delay and video delay;
the second evaluation module includes:
the third evaluation unit is used for inputting the audio time delay and the video time delay into the audio-video interaction time delay evaluation model to obtain audio-video interaction time delay scores of subjective experiences of fitting users of the current video call;
and the fourth evaluation unit is used for inputting the audio time delay and the video time delay into the audio-video interaction synchronization evaluation model to obtain the audio-video interaction synchronization score of the subjective experience of the fitting user of the current video call.
5. An electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, implements the method of any one of claims 1 to 3.
6. A computer readable storage medium, characterized in that it stores thereon a program or instructions, which when executed by a processor, implements the method according to any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010513657.3A CN113840131B (en) | 2020-06-08 | 2020-06-08 | Video call quality evaluation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010513657.3A CN113840131B (en) | 2020-06-08 | 2020-06-08 | Video call quality evaluation method and device, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113840131A CN113840131A (en) | 2021-12-24 |
| CN113840131B true CN113840131B (en) | 2023-08-01 |
Family
ID=78963617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010513657.3A Active CN113840131B (en) | 2020-06-08 | 2020-06-08 | Video call quality evaluation method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113840131B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115866235A (en) * | 2021-09-23 | 2023-03-28 | 中兴通讯股份有限公司 | Video quality evaluation method and device, electronic equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180034581A1 (en) * | 2016-07-27 | 2018-02-01 | International Business Machines Corporation | Quality of service assessment for conferences |
| US10608920B2 (en) * | 2017-01-06 | 2020-03-31 | Martello Technologies Corporation | Performance testing audio/video communications in network |
| CN109302603A (en) * | 2017-07-25 | 2019-02-01 | 中国移动通信集团北京有限公司 | A kind of video speech quality appraisal procedure and device |
| CN109714557A (en) * | 2017-10-25 | 2019-05-03 | 中国移动通信集团公司 | Method for evaluating quality, device, electronic equipment and the storage medium of video calling |
| CN109120924B (en) * | 2018-10-30 | 2020-06-02 | 宁波菊风系统软件有限公司 | Quality evaluation method for real-time video communication |
| CN110536095A (en) * | 2019-08-30 | 2019-12-03 | Oppo广东移动通信有限公司 | Call method, device, terminal and storage medium |
-
2020
- 2020-06-08 CN CN202010513657.3A patent/CN113840131B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113840131A (en) | 2021-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111314733A (en) | Method and apparatus for evaluating video sharpness | |
| CN113923441A (en) | Video quality evaluation method and device and electronic equipment | |
| CN111738010B (en) | Method and device for generating semantic matching model | |
| CN103517135A (en) | Method, system and television capable of playing MP4-format video files continuously | |
| CN111782543A (en) | Method, related device and system for evaluating in cloud | |
| CN111897976A (en) | Virtual image synthesis method and device, electronic equipment and storage medium | |
| CN101616315A (en) | A kind of method for evaluating video quality, device and system | |
| CN107911424A (en) | A kind of read-on-command function interacted with client realizes system, method and intelligent watch | |
| CN113840131B (en) | Video call quality evaluation method and device, electronic equipment and readable storage medium | |
| CN110347875B (en) | Video scene classification method and device, mobile terminal and storage medium | |
| CN109451334B (en) | User portrait generation processing method and device and electronic equipment | |
| CN111209432A (en) | Information acquisition method and device, electronic equipment and computer readable medium | |
| CN112836395A (en) | Vehicle driving data simulation method and device, electronic equipment and storage medium | |
| CN108874673A (en) | The test method and device of application program | |
| JP2006324865A (en) | Device, method and program for estimating network communication service satisfaction level | |
| CN111861204A (en) | Course mobile learning evaluation system and method based on intelligent platform | |
| CN102572501A (en) | Video quality evaluation method and device capable of taking network performance and video self-owned characteristics into account | |
| CN111654761A (en) | Video processing method, system, device and medium based on online education | |
| CN111078533A (en) | Automatic testing method and device, computer equipment and storage medium | |
| WO2023045365A1 (en) | Video quality evaluation method and apparatus, electronic device, and storage medium | |
| US11507803B2 (en) | System for generating synthetic digital data for data multiplication | |
| CN110347597B (en) | Interface testing method and device of picture server, storage medium and mobile terminal | |
| CN115150901B (en) | Method, device and storage medium for determining quality difference cell in communication network | |
| CN113177176A (en) | Feature construction method, content display method and related device | |
| CN112395695A (en) | Method and system for establishing simulation scene in real time |
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 |