Video quality assessment method, device and network equipment

Abstract

The present invention provides a video quality assessment method, device and network equipment to solve the problem that the existing video quality assessment method cannot fully reflect the degree of influence of network quality and the applicability is not high enough. The method of the present invention includes: when a first video is transmitted through a mobile communication network, obtaining network side information corresponding to the first video; according to the network side information, obtaining the service priority coefficient, video interaction score and video viewing score of the first video; according to the service priority coefficient, the video interaction score and the video viewing score, obtaining the quality assessment value of the first video. The present invention can complete the video quality assessment without using the video content information, thereby protecting the privacy of the user, and by using the network side information corresponding to the video, it can more finely assess the impact of the network quality on the video quality, provide the applicability of the video quality assessment, and facilitate subsequent users to optimize the network quality.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to a video quality assessment method, device and network equipment. Background Art

[0002] Currently, a variety of methods have been proposed for reference-free evaluation of video quality (i.e., when the quality information of the video source cannot be obtained, only the quality of the video at the receiving end is evaluated). One of the more common methods is to imitate the voice evaluation method under the communication network and perform vMOS scoring on video services. The calculation of the score needs to combine information such as video content quality, video interaction experience, and video viewing experience.

[0003] However, for users who focus on network service quality to ensure video business experience, existing video quality assessment methods cannot fully reflect the impact of network quality and are not applicable enough. Summary of the invention

[0004] The purpose of the present invention is to provide a video quality assessment method, device and network equipment, which are used to solve the problem that the existing video quality assessment method cannot fully reflect the impact of network quality and is not sufficiently applicable.

[0005] In order to achieve the above object, the present invention provides a video quality assessment method, comprising:

[0006] In the case of transmitting the first video through the mobile communication network, obtaining network side information corresponding to the first video;

[0007] According to the network side information, obtain a service priority coefficient, a video interaction score, and a video viewing score of the first video;

[0008] A quality assessment value of the first video is obtained according to the service priority coefficient, the video interaction score, and the video viewing score.

[0009] Wherein, the network side information includes network configuration information and network transmission information;

[0010] The obtaining, according to the network side information, a service priority coefficient, a video interaction score, and a video viewing score of the first video includes:

[0011] Obtaining a service priority coefficient of the first video according to the network configuration information;

[0012] The video interaction score and the video viewing score are obtained according to the network transmission information.

[0013] The network configuration information includes: allocation and reservation priority ARP level, network service quality identifier and network bearer type.

[0014] Wherein, obtaining the video interaction score and the video viewing score according to the network transmission information includes:

[0015] Obtaining a service experience indicator corresponding to the first video according to the network transmission information;

[0016] Based on the service experience index, the video interaction score and the video viewing score are calculated.

[0017] The obtaining, according to the network transmission information, a service experience indicator corresponding to the first video includes:

[0018] The network transmission information is used through a preset neural network, a preset machine learning algorithm or a preset calculation strategy to obtain a service experience indicator corresponding to the first video.

[0019] The service experience indicators include: the number of drags, initial buffering delay, average playback request delay, number of freezes, freeze duration, and viewing time during the user's viewing of the first video;

[0020] The calculating the video interaction score and the video viewing score based on the service experience indicator includes:

[0021] Calculating the video interaction score according to the number of dragging times, the initial buffering delay, the average playback request delay, and the viewing time;

[0022] The video viewing score is calculated according to the number of freezes, the freeze duration, and the viewing duration.

[0023] The obtaining, according to the service priority coefficient, the video interaction score and the video viewing score, a quality assessment value of the first video includes:

[0024] Based on the formula Calculate and obtain a quality assessment value of the first video;

[0025] Among them, nvMOS represents the quality assessment value, alPriority represents the service priority coefficient, sInteraction represents the video interaction score, sView represents the video viewing score, α represents the weight ratio of the video interaction score in the quality assessment, and β represents the weight ratio of the video viewing score in the quality assessment.

[0026] Wherein, after obtaining the quality evaluation value of the first video according to the service priority coefficient, the video interaction score and the video viewing score, the method further includes:

[0027] When the quality assessment value of the first video is lower than a first assessment threshold and the service priority coefficient is higher than a first preset threshold, adjusting the network slice where the first video is located;

[0028] When the quality evaluation value of the first video is lower than a second evaluation threshold, and the video interaction score is lower than a second preset threshold, and / or the video viewing score is lower than a second preset threshold, the network configuration parameters are adjusted.

[0029] The present invention also provides a video quality assessment device, comprising:

[0030] A first acquisition module, configured to acquire network side information corresponding to the first video when the first video is transmitted through a mobile communication network;

[0031] A second acquisition module is used to obtain a service priority coefficient, a video interaction score, and a video viewing score of the first video according to the network side information;

[0032] An evaluation module is used to obtain a quality evaluation value of the first video according to the service priority coefficient, the video interaction score and the video viewing score.

[0033] The present invention also provides a network device, comprising a processor and a transceiver, wherein the transceiver receives and sends data under the control of the processor, and the processor is used to perform the following operations:

[0034] In the case of transmitting the first video through the mobile communication network, obtaining network side information corresponding to the first video;

[0035] According to the network side information, obtaining a service priority coefficient, a video interaction score, and a video viewing score of the first video;

[0036] A quality assessment value of the first video is obtained according to the service priority coefficient, the video interaction score, and the video viewing score.

[0037] The network side information includes network configuration information and network transmission information; the processor is also used for:

[0038] Obtaining a service priority coefficient of the first video according to the network configuration information;

[0039] The video interaction score and the video viewing score are obtained according to the network transmission information.

[0040] The network configuration information includes: allocation and reservation priority ARP level, network service quality identifier and network bearer type.

[0041] Wherein, the processor is further used for:

[0042] Obtaining a service experience indicator corresponding to the first video according to the network transmission information;

[0043] Based on the service experience index, the video interaction score and the video viewing score are calculated.

[0044] Wherein, the processor is further used for:

[0045] The network transmission information is used through a preset neural network, a preset machine learning algorithm or a preset calculation strategy to obtain a service experience indicator corresponding to the first video.

[0046] The service experience index includes: the number of drags, initial buffering delay, average playback request delay, number of freezes, freeze duration, and viewing duration during the user's viewing of the first video; the processor is further configured to:

[0047] Calculating the video interaction score according to the number of dragging times, the initial buffering delay, the average playback request delay, and the viewing time;

[0048] The video viewing score is calculated according to the number of freezes, the freeze duration, and the viewing duration.

[0049] Wherein, the processor is further used for:

[0050] Based on the formula Calculate and obtain a quality assessment value of the first video;

[0051] Among them, nvMOS represents the quality assessment value, alPriority represents the service priority coefficient, sInteraction represents the video interaction score, sView represents the video viewing score, α represents the weight ratio of the video interaction score in the quality assessment, and β represents the weight ratio of the video viewing score in the quality assessment.

[0052] Wherein, the processor is further used for:

[0053] When the quality assessment value of the first video is lower than a first assessment threshold and the service priority coefficient is higher than a first preset threshold, adjusting the network slice where the first video is located;

[0054] When the quality evaluation value of the first video is lower than a second evaluation threshold, and the video interaction score is lower than a second preset threshold, and / or the video viewing score is lower than a second preset threshold, the network configuration parameters are adjusted.

[0055] The present invention also provides a network device, comprising a memory, a processor and a program stored in the memory and executable on the processor; when the processor executes the program, the video quality assessment method as described above is implemented.

[0056] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the video quality assessment method as described above are implemented.

[0057] The above technical solution of the present invention has at least the following beneficial effects:

[0058] In an embodiment of the present invention, when a first video is transmitted through a mobile communication network, network side information corresponding to the first video is obtained; based on the network side information, a service priority coefficient, a video interaction score, and a video viewing score of the first video are obtained; based on the service priority coefficient, the video interaction score, and the video viewing score, a quality assessment value of the first video is obtained. In this way, video quality assessment can be completed without using video content information, thereby protecting user privacy, and by using the network side information corresponding to the video, the impact of network quality on video quality can be evaluated more finely, the applicability of video quality assessment is provided, and it is convenient for subsequent users to optimize network quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram showing a flow chart of a video quality assessment method according to an embodiment of the present invention;

[0060] Figure 2 A schematic diagram showing a module of a video quality assessment device according to an embodiment of the present invention;

[0061] Figure 3 A schematic diagram showing the structure of a network device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0063] Aiming at the problem that the existing video quality assessment method cannot fully reflect the influence of network quality and the applicability is not high enough, the present invention provides a video quality assessment method, device and network equipment.

[0064] In order to enable those skilled in the art to better understand the method of the embodiment of the present invention, the following description is first made.

[0065] At present, quality assurance of video services based on no-reference evaluation (i.e., when the quality information of the video source cannot be obtained, only the quality evaluation of the video at the receiving end is performed) is generally carried out in the following steps:

[0066] 1. Obtain user-side data of video services, including: a) video content information, such as video resolution, frame rate, bit rate, etc.; b) video service interactive experience data, such as initial buffering delay, delay information during playback, etc.; c) video service viewing experience data, such as the number of freezes, freeze duration, number of screen distortion, etc.

[0067] 2. Calculate the video content score, interactive experience score and viewing experience score based on business-side user experience related data through a certain calculation fitting formula.

[0068] 3. Based on certain principles, the comprehensive score of video service experience is calculated through a certain formula. The general principle is: the higher the video content score, the higher the interactive experience score, the higher the viewing experience score, and the higher the comprehensive service experience score.

[0069] 4. When the comprehensive score of the video service decreases, take relevant measures to ensure the service experience based on the reasons for the decrease.

[0070] The current guarantee method is carried out from the perspective of video content providers, and does not fully consider the differentiation of quality assurance of similar video services in different scenarios. However, in actual applications, even for the same type of video services, different business scenarios and different users are likely to correspond to different guarantee priorities.

[0071] Currently, video quality assurance work based on a non-reference evaluation method requires the use of video content quality-related data when calculating the video experience score. However, for some specific users, such as operators and equipment manufacturers, who are more concerned about the impact of network transmission quality on video service experience and users who ensure service experience by optimizing network services, video content information is difficult to obtain, and current technology cannot fully reflect the impact of network quality, and its applicability is not high enough.

[0072] In order to solve the above problems, Figure 1 As shown, an embodiment of the present invention provides a video quality assessment method, which is applied to a network device, including:

[0073] Step 101, when a first video is transmitted through a mobile communication network, obtaining network side information corresponding to the first video;

[0074] Here, obtaining the network side information corresponding to the first video means obtaining the network side information related to the first video.

[0075] Step 102: obtaining a service priority coefficient, a video interaction score, and a video viewing score of the first video according to the network side information;

[0076] In this step, the service priority coefficient is used to reflect the strictness of the video quality assurance requirements. The service priority coefficient is negatively correlated with the video quality. That is, the higher the service priority coefficient, the stricter the video quality assurance requirements, that is, the stricter the requirements for the interaction score and the viewing score. Under the premise of the same interaction score and viewing score, the higher the service priority coefficient, the worse the overall video quality.

[0077] The video interaction score is used to reflect the quality of the video interaction experience. The video interaction score is positively correlated with the video quality. That is, the higher the video interaction score, the better the interaction experience.

[0078] The video viewing score is used to reflect the quality of the video viewing experience. The video viewing score is positively correlated with the video quality. That is, the higher the video viewing score, the better the viewing experience.

[0079] Step 103: Obtain a quality assessment value of the first video according to the service priority coefficient, the video interaction score, and the video viewing score.

[0080] The video quality assessment method of the embodiment of the present invention obtains network side information corresponding to the first video when the first video is transmitted through a mobile communication network; obtains the service priority coefficient, video interaction score and video viewing score of the first video based on the network side information; and obtains the quality assessment value of the first video based on the service priority coefficient, video interaction score and video viewing score. In this way, the video quality assessment can be completed without using the video content information, thereby protecting the privacy of the user, and by using the network side information corresponding to the video, the impact of the network quality on the video quality can be evaluated more finely, the applicability of the video quality assessment is provided, and it is convenient for subsequent users to optimize the network quality.

[0081] As an optional implementation, the network side information includes network configuration information and network transmission information; accordingly, step 102 of the present invention may include:

[0082] Obtaining a service priority coefficient of the first video according to the network configuration information;

[0083] The video interaction score and the video viewing score are obtained according to the network transmission information.

[0084] It should be noted that the network configuration information is information pre-configured by the network device, that is, information about the service allocation involved in the first video by the network device.

[0085] Optionally, the network configuration information includes: allocation and reservation priority ARP level, network service quality identifier and network bearer type.

[0086] Based on this, as an optional implementation, obtaining the service priority coefficient of the first video according to the network configuration information may specifically include:

[0087] Based on the following formula:

[0088] al Priority=f1(Bt)*f2(Pr)*f3(Qs),

[0089]

[0090]

[0091] The service priority coefficient of the first video is calculated, where alPriority represents the service priority coefficient, and its value range is [0,1), Bt represents the network bearer type, Pr represents the ARP level, and Qs represents the network service quality identification configuration value.

[0092] Here, Dedicated EPS Bearer is a dedicated EPS bearer, and Default EPS Bearer is a default EPS bearer. Among them, EPS (Evolved Packet System) is an evolved packet system.

[0093] Optionally, Bt can specifically represent the 4G network bearer type, and Qs represents the 5G network service representing the 5QI configuration value.

[0094] It should be noted that the closer alPriority is to 1, the higher the priority is and the stricter the requirements for viewing and interactive experience are.

[0095] The network transmission information is network-side transmission data related to the video acquired in real time during the video transmission through the mobile communication network. Here, the network transmission information is related to the network quality of the mobile communication network.

[0096] Optionally, the network transmission information includes, but is not limited to: video duration, data request response delay, air interface delay, request loopback time, data packet transmission loopback time, transmission window size, and the cell and region where the video service is located.

[0097] Based on this, as an optional implementation, obtaining the video interaction score and the video viewing score according to the network transmission information may specifically include:

[0098] Obtaining a service experience indicator corresponding to the first video according to the network transmission information;

[0099] Furthermore, this step may specifically include:

[0100] The network transmission information is used through a preset neural network, a preset machine learning algorithm or a preset calculation strategy to obtain a service experience indicator corresponding to the first video.

[0101] Here, the preset calculation strategy may be a calculation strategy formulated based on expert experience.

[0102] It should be noted that, by using a preset neural network, a preset machine learning algorithm or a preset computing strategy, network transmission information is input to predict or calculate the service experience indicators required for calculating the video interaction score and the video viewing score.

[0103] Optionally, the service experience indicators include: the number of dragging times, initial buffering delay, average playback request delay, number of freezes, freeze duration and viewing time when the user watches the first video.

[0104] Based on the service experience index, the video interaction score and the video viewing score are calculated.

[0105] Furthermore, this step may specifically include:

[0106] Calculating the video interaction score according to the number of dragging times, the initial buffering delay, the average playback request delay, and the viewing time;

[0107] This step may specifically include:

[0108] Based on the following formula:

[0109] sInteraction=f4(Dn,Id,Pd,Vt),

[0110]

[0111] The video interaction score is calculated, where Dn represents the number of drags, Id represents the initial buffering delay (ms), Pd represents the average playback request delay (ms), Vt represents the viewing time (s), sInteraction represents the video interaction score, γ represents the weight ratio of the initial buffering delay in the video interaction, and δ represents the weight ratio of the average playback request delay in the video interaction.

[0112] It should be noted that the value range of sInteraction is 1 to 5, and the larger the value, the better the interactive experience.

[0113] Here, information such as the number of drags, initial buffering delay, playback request delay, and resolution switching times in the video service will affect the video interaction score.

[0114] The video viewing score is calculated according to the number of freezes, the freeze duration, and the viewing duration.

[0115] This step may specifically include:

[0116] Based on the following formula:

[0117] sView=5-4*f5(Ln,Lt,Vt),

[0118] The video viewing score is calculated, where sView represents the video viewing score, Ln represents the number of freezes, Lt represents the total freeze duration (s), and Vt represents the viewing duration (s).

[0119] Here, information such as the number of video freezes and pauses will affect the video viewing score.

[0120] As an optional implementation, step 103 of the method in the embodiment of the present invention may specifically include:

[0121] Based on the formula Calculate and obtain a quality assessment value of the first video;

[0122] Among them, nvMOS represents the quality assessment value, alPriority represents the service priority coefficient, sInteraction represents the video interaction score, sView represents the video viewing score, α represents the weight ratio of the video interaction score in the quality assessment, and β represents the weight ratio of the video viewing score in the quality assessment.

[0123] It should be noted that the calculation process of alPriority, the calculation process of sInteraction and the calculation process of sView can be specifically referred to the description of the corresponding parts above, which will not be repeated here.

[0124] It needs to be further explained that the above method obtains the influencing factors affecting the video quality through network side information, which are the business priority coefficient, the video interaction score and the video viewing score, and finally obtains the quality assessment value for evaluating the video quality based on the influencing factors. Through a large amount of network side data and the quality assessment value of the video, a mapping relationship between the network side data and the quality assessment value of the video is obtained, and then a trained model is obtained through model training of a neural network or machine learning, based on the model, that is, the network side information is input into the model, and the quality assessment value of the corresponding video is output.

[0125] In order to ensure the video service quality of the first video, as an optional implementation, after obtaining the quality evaluation value of the first video according to the service priority coefficient, the video interaction score and the video viewing score, the method of the embodiment of the present invention may further include:

[0126] When the quality assessment value of the first video is lower than a first assessment threshold and the service priority coefficient is higher than a first preset threshold, adjusting the network slice where the first video is located;

[0127] Here, the quality assessment value of the first video is lower than the first assessment threshold, and the service priority coefficient is higher than the first preset threshold, indicating that the quality assessment value has decreased and is affected by the service priority coefficient. Here, without reducing the priority allocation, the network slice where the first video is located is adjusted, and the quality assessment value of the first video is continuously monitored until the quality assessment value of the first video is higher than the first evaluation threshold.

[0128] Of course, it is not limited to adjusting the network slice allocation strategy, but also the QoS level can be adjusted.

[0129] When the quality evaluation value of the first video is lower than a second evaluation threshold, and the video interaction score is lower than a second preset threshold, and / or the video viewing score is lower than a second preset threshold, the network configuration parameters are adjusted.

[0130] Here, the quality assessment value of the first video is lower than the second assessment threshold, and the video interaction score is lower than the second preset threshold, and / or the video viewing score is lower than the second preset threshold, indicating that the quality assessment value has decreased and is affected by the video interaction score and / or the video viewing score. Here, by adjusting the network configuration parameters, for example, by adjusting the network configuration of the cell where the video service is located, the regional positioning-related area, and the overall network coverage, the network configuration parameters are optimized, and the quality assessment value of the first video is continuously monitored until the quality assessment value of the first video is higher than the second evaluation threshold.

[0131] Here, by adjusting the network configuration parameters, the purpose of optimizing network coverage, optimizing switching strategies, allocating more network resources to specific users, etc. can be achieved.

[0132] The video quality assessment method of the embodiment of the present invention obtains network side information corresponding to the first video when the first video is transmitted through a mobile communication network; obtains the service priority coefficient, video interaction score and video viewing score of the first video based on the network side information; and obtains the quality assessment value of the first video based on the service priority coefficient, video interaction score and video viewing score. In this way, the video quality assessment can be completed without using the video content information, thereby protecting the privacy of the user, and by using the network side information corresponding to the video, the impact of the network quality on the video quality can be evaluated more finely, the applicability of the video quality assessment is provided, and it is convenient for subsequent users to optimize the network quality.

[0133] like Figure 2As shown, an embodiment of the present invention further provides a video quality assessment device, the device comprising:

[0134] A first acquisition module 201 is used to acquire network side information corresponding to the first video when the first video is transmitted through a mobile communication network;

[0135] A second acquisition module 202 is used to obtain a service priority coefficient, a video interaction score, and a video viewing score of the first video according to the network side information;

[0136] The evaluation module 203 is used to obtain a quality evaluation value of the first video according to the service priority coefficient, the video interaction score and the video viewing score.

[0137] Optionally, the network side information includes network configuration information and network transmission information; accordingly, the second acquisition module 202 may include:

[0138] A first processing submodule, configured to obtain a service priority coefficient of the first video according to the network configuration information;

[0139] The second processing submodule is used to obtain the video interaction score and the video viewing score according to the network transmission information.

[0140] Optionally, the network configuration information includes: allocation and reservation priority ARP level, network service quality identifier and network bearer type.

[0141] Optionally, the second submodule is specifically used for:

[0142] A first processing unit, configured to obtain a service experience indicator corresponding to the first video according to the network transmission information;

[0143] The second processing unit is used to calculate the video interaction score and the video viewing score based on the service experience index.

[0144] Optionally, the first processing unit is specifically configured to:

[0145] The network transmission information is used through a preset neural network, a preset machine learning algorithm or a preset calculation strategy to obtain a service experience indicator corresponding to the first video.

[0146] Optionally, the service experience indicator includes: the number of dragging times, initial buffering delay, average playback request delay, number of freezes, freeze duration and viewing time during the user's viewing of the first video; accordingly, the second processing unit is specifically configured to:

[0147] Calculating the video interaction score according to the number of dragging times, the initial buffering delay, the average playback request delay, and the viewing time;

[0148] The video viewing score is calculated according to the number of freezes, the freeze duration, and the viewing duration.

[0149] Optionally, the evaluation module 203 may include:

[0150] Evaluation submodule, used to:

[0151] Based on the formula Calculate and obtain a quality assessment value of the first video;

[0152] Among them, nvMOS represents the quality assessment value, alPriority represents the service priority coefficient, sInteraction represents the video interaction score, sView represents the video viewing score, α represents the weight ratio of the video interaction score in the quality assessment, and β represents the weight ratio of the video viewing score in the quality assessment.

[0153] Optionally, the video quality assessment device may further include:

[0154] A first optimization module, configured to adjust the network slice where the first video is located when the quality evaluation value of the first video is lower than a first evaluation threshold and the service priority coefficient is higher than a first preset threshold;

[0155] The second optimization module is used to adjust the network configuration parameters when the quality evaluation value of the first video is lower than a second evaluation threshold, the video interaction score is lower than a second preset threshold, and / or the video viewing score is lower than a second preset threshold.

[0156] The video quality assessment device of the embodiment of the present invention obtains network side information corresponding to the first video when the first video is transmitted through a mobile communication network; obtains the service priority coefficient, video interaction score and video viewing score of the first video based on the network side information; obtains the quality assessment value of the first video based on the service priority coefficient, video interaction score and video viewing score. In this way, the video quality assessment can be completed without using the video content information, thereby protecting the privacy of the user, and by using the network side information corresponding to the video, it can more finely assess the impact of the network quality on the video quality, provide the applicability of the video quality assessment, and facilitate subsequent users to optimize the network quality.

[0157] It should be noted here that the above-mentioned device provided by the embodiment of the present invention can implement all the method steps implemented by the above-mentioned network device side method embodiment, and can achieve the same technical effect. The parts and beneficial effects that are the same as the method embodiment in this embodiment will not be described in detail here.

[0158] In order to better achieve the above goals, Figure 3 As shown, an embodiment of the present invention further provides a network device, including a processor 300 and a transceiver 310, wherein the transceiver 310 receives and sends data under the control of the processor, and the processor 300 is used to perform the following process:

[0159] In the case of transmitting the first video through the mobile communication network, obtaining network side information corresponding to the first video;

[0160] According to the network side information, obtain a service priority coefficient, a video interaction score, and a video viewing score of the first video;

[0161] A quality assessment value of the first video is obtained according to the service priority coefficient, the video interaction score, and the video viewing score.

[0162] Optionally, the network side information includes network configuration information and network transmission information; the processor 300 is further configured to:

[0163] Obtaining a service priority coefficient of the first video according to the network configuration information;

[0164] The video interaction score and the video viewing score are obtained according to the network transmission information.

[0165] Optionally, the network configuration information includes: allocation and reservation priority ARP level, network service quality identifier and network bearer type.

[0166] Optionally, the processor 300 is further configured to:

[0167] Obtaining a service experience indicator corresponding to the first video according to the network transmission information;

[0168] Based on the service experience index, the video interaction score and the video viewing score are calculated.

[0169] Optionally, the processor 300 is further configured to:

[0170] The network transmission information is used through a preset neural network, a preset machine learning algorithm or a preset calculation strategy to obtain a service experience indicator corresponding to the first video.

[0171] Optionally, the service experience indicator includes: the number of dragging times, initial buffering delay, average playback request delay, number of freezes, freeze duration, and viewing duration during the user's viewing of the first video; the processor 300 is further configured to:

[0172] Calculating the video interaction score according to the number of dragging times, the initial buffering delay, the average playback request delay, and the viewing time;

[0173] The video viewing score is calculated according to the number of freezes, the freeze duration, and the viewing duration.

[0174] Optionally, the processor 300 is further configured to:

[0175] Based on the formula Calculate and obtain a quality assessment value of the first video;

[0176] Among them, nvMOS represents the quality assessment value, alPriority represents the service priority coefficient, sInteraction represents the video interaction score, sView represents the video viewing score, α represents the weight ratio of the video interaction score in the quality assessment, and β represents the weight ratio of the video viewing score in the quality assessment.

[0177] Optionally, the processor 300 is further configured to:

[0178] When the quality assessment value of the first video is lower than a first assessment threshold and the service priority coefficient is higher than a first preset threshold, adjusting the network slice where the first video is located;

[0179] When the quality evaluation value of the first video is lower than a second evaluation threshold, and the video interaction score is lower than a second preset threshold, and / or the video viewing score is lower than a second preset threshold, the network configuration parameters are adjusted.

[0180] The network device of the embodiment of the present invention obtains network side information corresponding to the first video when transmitting the first video through the mobile communication network; obtains the service priority coefficient, video interaction score and video viewing score of the first video based on the network side information; obtains the quality assessment value of the first video based on the service priority coefficient, video interaction score and video viewing score. In this way, the video quality assessment can be completed without using the video content information, thereby protecting the privacy of the user, and by using the network side information corresponding to the video, the impact of the network quality on the video quality can be evaluated more finely, the applicability of the video quality assessment is provided, and it is convenient for subsequent users to optimize the network quality.

[0181] An embodiment of the present invention also provides a network device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, each process in the video quality assessment method embodiment described above is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0182] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, each process in the above-mentioned video quality assessment method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0183] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0184] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A device that specifies functions in one or more processes and / or one or more blocks.

[0185] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable storage medium produce a paper product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0186] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that the computer or other programmable device executes a series of operating steps to produce a computer-implemented process, thereby providing instructions executed on the computer or other programmable device for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0187] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A video quality assessment method, applied to a network device, characterized in that: include: In the case of transmitting the first video through the mobile communication network, obtaining network side information corresponding to the first video; According to the network side information, a service priority coefficient, a video interaction score and a video viewing score of the first video are obtained; the service priority coefficient is used to reflect the strictness of the video quality assurance requirement, and the service priority coefficient is negatively correlated with the video quality; the video interaction score is used to reflect the quality of the video interaction experience, and the video interaction score is positively correlated with the video quality; the video viewing score is used to reflect the quality of the video viewing experience, and the video viewing score is positively correlated with the video quality; Obtaining a quality assessment value of the first video according to the service priority coefficient, the video interaction score, and the video viewing score; The network side information includes network configuration information and network transmission information, wherein the network configuration information includes: allocation and reservation priority ARP level, network service quality identifier and network bearer type; The obtaining, according to the network side information, a service priority coefficient, a video interaction score, and a video viewing score of the first video includes: Obtaining a service priority coefficient of the first video according to the network configuration information; Obtaining the video interaction score and the video viewing score according to the network transmission information; The obtaining, according to the network configuration information, a service priority coefficient of the first video may specifically include: Based on the following formula: alPriority=f1(Bt)*f2(Pr)*f3(Qs), Calculate and obtain the service priority coefficient of the first video, where alPriority represents the service priority coefficient, and its value range is [0,1), Bt represents the network bearer type, Pr represents the ARP level, and Qs represents the network service quality identifier configuration value; The obtaining, according to the service priority coefficient, the video interaction score and the video viewing score, a quality assessment value of the first video includes: Based on the formula Calculate and obtain a quality assessment value of the first video; Among them, nvMOS represents the quality assessment value, alPriority represents the service priority coefficient, sInteraction represents the video interaction score, sView represents the video viewing score, α represents the weight ratio of the video interaction score in the quality assessment, and β represents the weight ratio of the video viewing score in the quality assessment.

2. The method according to claim 1, characterized in that: The obtaining the video interaction score and the video viewing score according to the network transmission information includes: Obtaining a service experience indicator corresponding to the first video according to the network transmission information; Based on the service experience index, the video interaction score and the video viewing score are calculated.

3. The method according to claim 2, characterized in that The obtaining, according to the network transmission information, a service experience indicator corresponding to the first video includes: The network transmission information is used through a preset neural network, a preset machine learning algorithm or a preset calculation strategy to obtain a service experience indicator corresponding to the first video.

4. The method according to claim 2, characterized in that: The service experience indicators include: the number of drags, initial buffering delay, average playback request delay, number of freezes, freeze duration, and viewing time during the user's viewing of the first video; The calculating the video interaction score and the video viewing score based on the service experience indicator includes: Calculating the video interaction score according to the number of dragging times, the initial buffering delay, the average playback request delay, and the viewing time; The video viewing score is calculated according to the number of freezes, the freeze duration, and the viewing duration.

5. The method according to claim 1, characterized in that After obtaining the quality evaluation value of the first video according to the service priority coefficient, the video interaction score and the video viewing score, the method further includes: When the quality assessment value of the first video is lower than a first assessment threshold and the service priority coefficient is higher than a first preset threshold, adjusting the network slice where the first video is located; When the quality evaluation value of the first video is lower than a second evaluation threshold, and the video interaction score is lower than a second preset threshold, and / or the video viewing score is lower than a second preset threshold, the network configuration parameters are adjusted.

6. A video quality assessment device, characterized in that: include: A first acquisition module, configured to acquire network side information corresponding to the first video when the first video is transmitted through a mobile communication network; A second acquisition module is used to obtain a service priority coefficient, a video interaction score and a video viewing score of the first video according to the network side information; the service priority coefficient is used to reflect the strictness of the video quality assurance requirement, and the service priority coefficient is negatively correlated with the video quality; the video interaction score is used to reflect the quality of the video interaction experience, and the video interaction score is positively correlated with the video quality; the video viewing score is used to reflect the quality of the video viewing experience, and the video viewing score is positively correlated with the video quality; An evaluation module, configured to obtain a quality evaluation value of the first video according to the service priority coefficient, the video interaction score and the video viewing score; The network side information includes network configuration information and network transmission information, wherein the network configuration information includes: allocation and reservation priority ARP level, network service quality identifier and network bearer type; The second acquisition module includes: A first processing submodule, configured to obtain a service priority coefficient of the first video according to the network configuration information; A second processing submodule, configured to obtain the video interaction score and the video viewing score according to the network transmission information; The first processing submodule is specifically used for: Based on the following formula: alPriority=f1(Bt)*f2(Pr)*f3(Qs), Calculate and obtain the service priority coefficient of the first video, where alPriority represents the service priority coefficient, and its value range is [0,1), Bt represents the network bearer type, Pr represents the ARP level, and Qs represents the network service quality identifier configuration value; The evaluation module includes: Evaluation submodule, used to: Based on the formula Calculate and obtain a quality assessment value of the first video; Among them, nvMOS represents the quality assessment value, alPriority represents the service priority coefficient, sInteraction represents the video interaction score, sView represents the video viewing score, α represents the weight ratio of the video interaction score in the quality assessment, and β represents the weight ratio of the video viewing score in the quality assessment.

7. A network device comprising a processor and a transceiver, wherein the transceiver receives and sends data under the control of the processor, characterized in that: The processor is configured to perform the following operations: In the case of transmitting the first video through the mobile communication network, obtaining network side information corresponding to the first video; According to the network side information, a service priority coefficient, a video interaction score, and a video viewing score of the first video are obtained; the service priority coefficient is used to reflect the strictness of the video quality assurance requirement, and the service priority coefficient is negatively correlated with the video quality; the video interaction score is used to reflect the quality of the video interaction experience, and the video interaction score is positively correlated with the video quality; the video viewing score is used to reflect the quality of the video viewing experience, and the video viewing score is positively correlated with the video quality; Obtaining a quality assessment value of the first video according to the service priority coefficient, the video interaction score, and the video viewing score; The network side information includes network configuration information and network transmission information, wherein the network configuration information includes: allocation and reservation priority ARP level, network service quality identifier and network bearer type; The processor is further configured to: Obtaining a service priority coefficient of the first video according to the network configuration information; Obtaining the video interaction score and the video viewing score according to the network transmission information; The obtaining, according to the network configuration information, a service priority coefficient of the first video may specifically include: Based on the following formula: alPriority=f1(Bt)*f2(Pr)*f3(Qs), Calculate and obtain the service priority coefficient of the first video, where alPriority represents the service priority coefficient, and its value range is [0,1), Bt represents the network bearer type, Pr represents the ARP level, and Qs represents the network service quality identifier configuration value; The processor is further configured to: Based on the formula Calculate and obtain a quality assessment value of the first video; Among them, nvMOS represents the quality assessment value, alPriority represents the service priority coefficient, sInteraction represents the video interaction score, sView represents the video viewing score, α represents the weight ratio of the video interaction score in the quality assessment, and β represents the weight ratio of the video viewing score in the quality assessment.

8. The network device according to claim 7, characterized in that: The processor is further configured to: Obtaining a service experience indicator corresponding to the first video according to the network transmission information; Based on the service experience index, the video interaction score and the video viewing score are calculated.

9. The network device according to claim 8, characterized in that: The processor is further configured to: The network transmission information is used through a preset neural network, a preset machine learning algorithm or a preset calculation strategy to obtain a service experience indicator corresponding to the first video.

10. The network device according to claim 8, characterized in that: The service experience index includes: the number of drags, initial buffering delay, average playback request delay, number of freezes, freeze duration and viewing duration during the user's viewing of the first video; the processor is further configured to: Calculating the video interaction score according to the number of dragging times, the initial buffering delay, the average playback request delay, and the viewing time; The video viewing score is calculated according to the number of freezes, the freeze duration, and the viewing duration.

11. The network device according to claim 7, characterized in that: The processor is further configured to: When the quality assessment value of the first video is lower than a first assessment threshold and the service priority coefficient is higher than a first preset threshold, adjusting the network slice where the first video is located; When the quality evaluation value of the first video is lower than a second evaluation threshold, and the video interaction score is lower than a second preset threshold, and / or the video viewing score is lower than a second preset threshold, the network configuration parameters are adjusted.

12. A network device comprising a memory, a processor, and a program stored in the memory and executable on the processor; characterized in that: When the processor executes the program, the video quality assessment method according to any one of claims 1 to 5 is implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the video quality assessment method according to any one of claims 1 to 5 are implemented.

Images