CN120342929A

CN120342929A - Service node quality detection method, device and computing equipment

Info

Publication number: CN120342929A
Application number: CN202510575970.2A
Authority: CN
Inventors: 钱沿佐
Original assignee: Shanghai Bilibili Technology Co Ltd
Current assignee: Shanghai Bilibili Technology Co Ltd
Priority date: 2025-04-30
Filing date: 2025-04-30
Publication date: 2025-07-18

Abstract

The application discloses a service node quality detection method, a service node quality detection device and computing equipment. The method comprises the steps of identifying candidate data streams with play anomalies, calculating an original stream frame loss rate and a transcoding stream frame loss rate of the candidate data streams, determining the candidate data streams as node anomaly data streams if the original stream frame loss rate is smaller than a first threshold value and the transcoding stream frame loss rate is larger than a second threshold value, calculating a transcoding stream output/input fluctuation ratio of the node anomaly data streams, determining a plug-flow node of the node anomaly data streams as a quality anomaly node if the transcoding stream output/input fluctuation ratio is smaller than a third threshold value, and determining the transcoding node of the node anomaly data streams as the quality anomaly node if the transcoding stream output/input fluctuation ratio is larger than or equal to a third threshold value. The quality detection of the service node can be realized without relying on the service node internal monitoring data provided by a third party, the application range of the scheme is improved, and the quality abnormal node and the node abnormal data stream can be accurately and rapidly positioned.

Description

Service node quality detection method and device and computing equipment

Technical Field

The present application relates to the field of streaming media technologies, and in particular, to a service node quality detection method, apparatus, computing device, computer storage medium, and computer program product.

Background

With the continuous development of streaming media technology, various streaming media service platforms are greatly convenient for the work and life of users. In order to improve the service quality of the streaming media service platform, quality detection is generally required to be performed on service nodes in the streaming media service platform, so that service nodes with abnormal quality are discovered in time.

However, the inventor finds that in the implementation process, the existing streaming media service platform has the defect that the quality of the service node is detected through internal monitoring parameters (such as CPU utilization rate and the like) of the service node. However, in the practical implementation process, some streaming media service platforms use service nodes of a third party platform, in which case the streaming media service platform needs to rely on internal monitoring parameters of the service nodes provided by the third party platform to perform quality detection on the service nodes, however, when the third party platform cannot or is difficult to provide internal monitoring parameters of the service nodes, the streaming media service platform cannot perform quality detection on the service nodes.

Disclosure of Invention

The present application has been made in view of the above problems, and it is an object of the present application to provide a quality of service node detection method, apparatus, computing device, computer storage medium and computer program product that overcomes or at least partially solves the above problems.

According to a first aspect of the present application, there is provided a service node quality detection method, comprising:

identifying candidate data streams with abnormal playing, and calculating the original stream frame loss rate and the transcoding stream frame loss rate of the candidate data streams;

If the original stream frame loss rate is smaller than a first threshold value and the transcoding stream frame loss rate is larger than a second threshold value, determining the candidate data stream as a node abnormal data stream, and calculating the transcoding stream output and input fluctuation ratio of the node abnormal data stream;

if the output-input fluctuation ratio of the transcoding stream is smaller than a third threshold value, determining a plug-flow node of the node abnormal data stream as a quality abnormal node;

And if the output-input fluctuation ratio of the transcoding stream is greater than or equal to a third threshold value, determining that the transcoding node of the node abnormal data stream is a quality abnormal node.

In an alternative embodiment, the identifying candidate data streams for which play anomalies exist includes:

And identifying candidate data streams with abnormal playing according to the barrage data and/or the abnormal reporting data.

In an optional implementation manner, the calculating the original stream frame loss rate and the transcoding stream frame loss rate of the candidate data stream includes:

according to the monitoring data of the input end of the push node of the candidate data stream in the first historical period, calculating the original stream frame loss rate of the candidate data stream;

And/or calculating the frame loss rate of the transcoding stream of the candidate data stream according to the monitoring data of the output end of the transcoding node where the transcoding stream of the candidate data stream is located in the first historical period.

In an optional implementation manner, the calculating the original stream frame loss rate of the candidate data stream according to the input end monitoring data of the push stream node of the candidate data stream in the first historical period comprises the steps of obtaining a first original stream total frame number received by the push stream node at a first moment and a second original stream total frame number received at a second moment;

And/or, calculating the frame loss rate of the transcoding stream of the candidate data stream according to the monitoring data of the output end of the transcoding node where the transcoding stream of the candidate data stream is located in the first historical period, wherein the calculating comprises the steps of obtaining the total frame number of the first transcoding stream output by the transcoding node where the transcoding stream is located at the first moment and the total frame number of the second transcoding stream output at the second moment for any transcoding stream;

the first time is the starting time of the first history period, and the second time is the ending time of the first history period.

In an alternative embodiment, the calculating the output-to-input fluctuation ratio of the transcoding stream of the node anomaly data stream includes:

For any one of the transcoding streams of the node abnormal data stream, calculating a transcoding stream input fluctuation value corresponding to the transcoding stream according to the number of frames per second of an original stream of a receiving end of the transcoding node where the transcoding stream is located in a second history period;

And taking the ratio of the output fluctuation value of the transcoding stream and the input fluctuation value of the transcoding stream corresponding to the transcoding stream as the output fluctuation ratio of the transcoding stream.

In an alternative embodiment, the method further comprises:

Receiving false judgment feedback data of abnormal data flow of the node, and adjusting the first threshold downwards and adjusting the second threshold upwards;

and/or, receiving node abnormal data stream missed judgment feedback data, and adjusting the first threshold value upwards and adjusting the second threshold value downwards.

In an alternative embodiment, the method further comprises:

receiving the false judgment feedback data of the plug-flow node, and reducing the third threshold value;

And receiving the error judgment feedback data of the transcoding node, and up-regulating the third threshold value.

According to a second aspect of the present application, there is provided a service node quality detection apparatus comprising:

The identification module is used for identifying candidate data streams with abnormal playing;

the calculation module is used for calculating the original stream frame loss rate and the transcoding stream frame loss rate of the candidate data stream;

The first detection module is used for determining the candidate data stream as a node abnormal data stream and calculating the output and input fluctuation ratio of the transcoding stream of the node abnormal data stream if the frame loss rate of the original stream is smaller than a first threshold value and the frame loss rate of the transcoding stream is larger than a second threshold value;

And the second detection module is used for determining that the pushing node of the node abnormal data stream is a quality abnormal node if the output-input fluctuation ratio of the transcoding stream is smaller than a third threshold value, and determining that the transcoding node of the node abnormal data stream is a quality abnormal node if the output-input fluctuation ratio of the transcoding stream is larger than or equal to the third threshold value.

In an alternative embodiment, the identification module is used for identifying candidate data streams with abnormal playing according to the barrage data and/or the abnormal report data.

In an alternative embodiment, the calculating module is configured to calculate an original stream frame loss rate of the candidate data stream according to the input end monitoring data of the push node of the candidate data stream in the first history period;

In an optional implementation manner, the calculation module is used for acquiring a first original flow total frame number received by the push node at a first moment and a second original flow total frame number received at a second moment, calculating an original flow total frame number difference value between the second original flow total frame number and the first original flow total frame number, and calculating the original flow frame loss rate according to the original flow total frame number difference value and an original flow per second frame number set value;

And/or, for any transcoding stream, acquiring a total frame number of a first transcoding stream output at a first moment and a total frame number of a second transcoding stream output at a second moment of a transcoding node where the transcoding stream is located; calculating a total frame number difference value of the second transcoding stream and the total frame number of the first transcoding stream, and calculating a corresponding transcoding stream frame loss rate of the transcoding stream according to the total frame number difference value of the transcoding stream and a set value of the number of frames per second of the transcoding stream;

In an alternative implementation mode, the first detection module is used for calculating a transcoding stream input fluctuation value corresponding to a transcoding stream according to the original stream per second frame number of a receiving end of a transcoding node where the transcoding stream is located in a second history period for any transcoding stream of the node abnormal data stream;

In an alternative embodiment, the device further comprises a threshold adjustment module, a first threshold adjustment module and a second threshold adjustment module, wherein the threshold adjustment module is used for receiving the abnormal data flow misjudgment feedback data of the node, and adjusting the first threshold downwards and the second threshold upwards;

In an alternative embodiment, the threshold adjustment module is configured to receive the push node misjudgment feedback data and adjust the third threshold downward;

According to a third aspect of the present application there is provided a computing device comprising a processor, a memory, a communications interface and a communications bus, the processor, the memory and the communications interface completing communications with each other via the communications bus;

the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to execute an operation corresponding to the service node quality detection method.

According to a fourth aspect of the present application, there is provided a computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the above-described service node quality detection method.

According to a fifth aspect of the present application, there is provided a computer program product comprising at least one executable instruction for causing a processor to perform operations corresponding to the above-described service node quality detection method.

The embodiment of the application determines whether the candidate data stream is the abnormal node data stream with abnormal service nodes in the processing link according to the original stream frame loss rate and the transcoding stream frame loss rate of the abnormal node data stream with abnormal play, and positions the quality abnormal node according to the output-input fluctuation ratio of the transcoding stream aiming at the identified abnormal node data stream. The original stream frame loss rate, the transcoding stream frame loss rate and the transcoding stream output/input fluctuation ratio adopted by the scheme are not internal monitoring data of the service node, so that the quality detection of the service node by the scheme does not need to depend on the internal monitoring data of the service node provided by a third party, the application range of the scheme is improved, and the quality abnormal node and the accurate and rapid positioning of the node abnormal data stream can be realized.

According to the embodiment of the application, the candidate data stream with abnormal playing is identified through the barrage data and/or the abnormal report data at the user side, so that the candidate data stream can be determined according to the actual playing condition at the user side, and the determination accuracy of the candidate data stream is improved.

According to the embodiment of the application, the data monitoring points are arranged at the input end of the plug-flow node and the output end of the transcoding node, so that on one hand, the internal monitoring data of the service node is not needed, on the other hand, the transcoding node and the plug-flow node can be used as an integral black box system, the input end of the plug-flow node is the input port of the black box system, the output end of the transcoding node is the output port of the black box system, and therefore, whether the black box system is abnormal or not can be accurately and rapidly determined through the original stream frame loss rate of the input port and the transcoding stream frame loss rate of the output port, and the determination efficiency of the quality abnormal node is improved.

According to the embodiment of the application, the frame loss rate of the original stream can be accurately calculated according to the difference value of the total frame number of the original stream at the first moment and the second moment and the set value of the frame number of the original stream per second.

According to the embodiment of the application, the frame loss rate of the transcoding stream can be accurately calculated according to the difference value of the total frame number of the transcoding stream at the first moment and the second moment and the set value of the frame number of the transcoding stream per second.

According to the embodiment of the application, the input fluctuation value of the transcoding stream is calculated according to the number of frames per second of the original stream at the receiving end of the transcoding node in the second historical period, the output fluctuation value of the transcoding stream is calculated according to the number of frames per second of the transcoding stream at the output end of the transcoding node in the second historical period, and the output fluctuation ratio of the transcoding stream can be accurately obtained according to the output fluctuation value of the transcoding stream and the input fluctuation value of the transcoding stream.

According to the embodiment of the application, the first threshold value and the second threshold value are dynamically adjusted according to the data flow feedback data, so that the detection precision of the abnormal data flow of the node is improved.

According to the embodiment of the application, the third threshold value is dynamically adjusted according to the node feedback data, so that the detection precision of the quality abnormal node of the node abnormal data stream is improved.

The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.

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 application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:

FIG. 1 illustrates a schematic diagram of an operating environment provided for implementing at least one embodiment of the present application;

Fig. 2 is a schematic flow chart of a quality of service node detection method according to a first embodiment of the present application;

FIG. 3 is a schematic view of a monitoring point according to a first embodiment of the present application;

fig. 4 is a flow chart of a threshold adjustment method applied to a quality of service node detection method according to a second embodiment of the present application;

Fig. 5 is a schematic structural diagram of a service node quality detection device according to a third embodiment of the present application;

Fig. 6 shows a schematic structural diagram of a computing device according to a fourth embodiment of the present application.

Detailed Description

Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.

First, terms related to one or more embodiments of the present application will be briefly explained.

Transcoding, the process of converting one video or audio encoding format into another encoding format in order to accommodate different network bandwidths, different terminal processing capabilities, and/or different user requirements;

the original stream, the data stream pushed to the push node by the anchor end, may also be called as an original data stream, which is a data stream not subjected to transcoding;

transcoding the stream, and outputting the data stream after transcoding the original stream;

a pushing node, a service node which receives the data stream pushed by the anchor end in the service platform;

Transcoding node, service node executing transcoding task in service platform;

transcoding task, pulling source stream through specific address, transcoding through preset configuration to generate transcoding stream, and outputting program of transcoding stream through specific address;

A number of frames per Second, FRAMES PER seconds, FPS for short, a number of consecutive frames displayed per Second;

The frame loss rate is the ratio of the lost frame to the total frame number when the frame loss occurs due to the corresponding reasons in the data stream.

FIG. 1 illustrates a schematic diagram of an operating environment provided for implementing at least one embodiment of the present application. The application is applicable to application environments including, but not limited to, anchor end, audience end, service platform.

Wherein:

The main broadcasting end is a live broadcast resource producer and is used for producing live broadcast data such as audio and video and pushing the produced live broadcast data to the service platform. The anchor may be an electronic device running an operating system such as Windows, android (Android ^TM), or IOS, such as a smart phone, tablet device, laptop, virtual reality device, game device, set top box, vehicle terminal, or smart television. Based on the operating system described above, various application programs, such as a browser, may be run.

The audience terminal is a live resource consumer and is used for acquiring live broadcast data such as audio and video from the service platform. The spectator terminal may be an electronic device running an operating system such as Windows, android (Android ^TM) or IOS, for example, a smart phone, a tablet device, a laptop, a virtual reality device, a game device, a set top box, a vehicle terminal, or a smart television. Based on the operating system described above, various application programs, such as a browser, may be run.

The service platform is a live broadcast data processing end and is used for receiving live broadcast data produced by the main broadcasting end, processing the live broadcast data and providing the live broadcast data for audience terminals. The service platform may be formed by a single or multiple service nodes or service clusters. As shown in fig. 1, the service platform includes at least one push node and at least one transcoding node, each of which may be one or more computing devices. The computing device may include a virtualized computing instance. Virtualized computing instances may include virtual machines such as emulation of computer systems, operating systems, servers, and the like. The computing device may load the virtual machine based on a virtual image and/or other data defining particular software (e.g., operating system, dedicated application, server) for emulation. As the demand for different types of processing services changes, different virtual machines may be loaded and/or terminated on one or more computing devices. A hypervisor may be implemented to manage the use of different virtual machines on the same computing device.

The service platform may be configured to communicate with the anchor side, the audience side, etc. over a network. The network may include various network devices such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and/or the like. The network may also include physical links such as a cable link, a twisted pair cable link, a fiber optic link, combinations thereof, and the like, or wireless links such as cellular links, satellite links, wi-Fi links, and the like.

Example 1

Fig. 2 is a schematic flow chart of a quality of service node detection method according to an embodiment of the present application. The service node quality detection method provided by the embodiment of the application can be applied to a service platform, wherein the service platform can comprise a live broadcast platform and the like.

As shown in fig. 2, the method specifically includes the following steps:

Step S201, identify candidate data streams with playback anomalies.

The candidate data stream is a data stream in which play abnormality occurs in the service platform. The play exception may include play stuck, first frame timeout, play failure, asynchronous audio and video, etc.

In an alternative implementation, embodiments of the present application identify candidate data streams based on client-side (including anchor-side and/or viewer-side) data. Specifically, candidate data streams with abnormal playing can be identified according to bullet screen data and/or abnormal report data. For example, a barrage message queue and/or a katon report message queue may be monitored, when playing abnormal keywords (such as a card and a black screen) or the like of a barrage or a katon report message are monitored currently, the barrage or the katon report message is extracted, a data stream corresponding to the barrage or the katon report message is determined, and the corresponding data stream is used as a candidate data stream with playing abnormality. According to the embodiment, the candidate data stream with abnormal playing is identified through the barrage data and/or the abnormal report data at the user side, so that the candidate data stream can be determined according to the actual playing condition at the user side, and the determination accuracy of the candidate data stream is improved.

Step S202, the original stream frame loss rate and the transcoding stream frame loss rate of the candidate data stream are calculated.

The candidate data stream is a data stream with abnormal playing, and the reason for the abnormal playing may be the reason of the user side, such as the blocking of the user side equipment, the network abnormality, etc., or the quality abnormality of the service node processing the data stream, etc. After screening the candidate data stream, the original stream frame loss rate and the transcoding stream frame loss rate of the candidate data stream are further calculated, so that whether the reason for causing the play abnormality of the candidate data stream is the quality abnormality of the service node or not can be determined according to the original stream frame loss rate and the transcoding stream frame loss rate of the candidate data stream.

Specifically, the frame loss rate of the original stream of the candidate data stream in the first historical period (such as the last 1 minute) is calculated, the frame loss rate is called an original stream frame loss rate, and the original stream frame loss rate can reflect the frame loss condition of the original stream in the process of transmitting from the anchor end to the push node.

And calculating a frame loss rate of the transcoding stream of the candidate data stream during the first historical period, the frame loss rate being referred to as a transcoding stream frame loss rate. The frame loss rate of the transcoding stream can reflect the frame loss condition of the transcoding stream output by the transcoding node. Optionally, if the number of the transcoding streams of the candidate data streams is multiple, the frame loss rate of the transcoding streams of each transcoding stream is calculated respectively.

It can be seen that the original stream frame loss rate and the transcoding stream frame loss rate reflect the input and output characteristics of the service node, and can be obtained by monitoring by the streaming media service platform, that is, the original stream frame loss rate and the transcoding stream frame loss rate do not relate to the internal monitoring data of the service node, so that a third party where the service node is located does not need to rely on to provide the internal monitoring data.

In an alternative embodiment, the original stream frame loss rate of the candidate data stream is calculated according to the input end monitoring data of the push stream node of the candidate data stream in the first history period, and/or the frame loss rate of the transcoding stream of the candidate data stream is calculated according to the output end monitoring data of the transcoding node where the transcoding stream of the candidate data stream is located in the first history period. When the number of the transcoding streams of the candidate data streams is multiple, for each transcoding stream, calculating the frame loss rate of the transcoding stream corresponding to the transcoding stream according to the monitoring data of the output end of the transcoding node where the transcoding stream is located for the transcoding stream.

Referring to fig. 3, the push node receives an original stream of the candidate data stream, and the original stream can be transmitted to the transcoding node 1 and the transcoding node 2 by pushing the stream by the push node or pulling the stream by the transcoding node. Wherein the transcoding node 1 outputs a transcoding stream 1 and a transcoding stream 2 of the candidate data stream, and the transcoding node 2 outputs a transcoding stream 3 of the candidate data stream. Setting up the frame loss rate monitoring point of the transcoding stream at the output ends of the transcoding node 1 and the transcoding node 2, thus obtaining the monitoring data of the output end of the transcoding node and further obtaining the frame loss rate of the transcoding stream.

In this embodiment, data monitoring points are set at the input end of the push node and the output end of the transcoding node, so that on one hand, the internal monitoring data of the service node is not required, on the other hand, the transcoding node and the push node can be used as an integral black box system, the input end of the push node is the input port of the black box system, the output end of the transcoding node is the output port of the black box system, and therefore, whether the black box system is abnormal or not can be accurately and rapidly determined through the original stream frame loss rate of the input port and the transcoding stream frame loss rate of the output port, and thus, whether the candidate data stream is the abnormal data stream of the node can be conveniently and rapidly determined.

Further optionally, the frame loss rate of the primary stream may be specifically calculated by obtaining a total frame number of the primary stream received by the push node at the first time and a total frame number of the secondary stream received by the push node at the second time. The total frame number of the original stream of the abnormal data stream of the node received by the push node at the first moment is the total frame number of the first original stream, and the total frame number of the original stream of the abnormal data stream of the node received by the push node at the second moment is the total frame number of the second original stream. The method comprises the steps of obtaining a first historical period, calculating a first original flow total frame number difference value between a first original flow total frame number and a first original flow total frame number, namely a first original flow total frame number difference value, and finally obtaining an original flow frame loss rate according to the first original flow total frame number difference value and an original flow frame number per second set value, wherein the original flow frame number per second set value is a set parameter of original flow transmission and is also a frame number per second in the process of pushing node candidate data flows to a push node by a main broadcasting end.

Specifically, the frame loss rate of the original stream can be calculated by adopting the following formula 1:

Wherein lfr_y represents the frame loss rate of the original stream, F _a represents the total frame number of the first original stream, F _b represents the total frame number of the second original stream, t _ab represents the sampling interval between the first time and the second time, and fps_y represents the frame number per second set value of the original stream of the candidate data stream.

Further alternatively, the frame loss rate of the transcoding stream can be specifically obtained by calculating, for any transcoding stream, a total frame number of the first transcoding stream output by a transcoding node where the transcoding stream is located at a first time and a total frame number of the second transcoding stream output at a second time. The total frame number of the transcoding stream output by the transcoding node where the transcoding stream is located at the first moment is called the total frame number of the first transcoding stream, and the total frame number of the transcoding stream output by the transcoding node where the transcoding stream is located at the second moment is called the total frame number of the second transcoding stream; and finally, according to the total frame number difference of the transcoding stream and the set value of the frame number of the transcoding stream per second of the transcoding stream, calculating to obtain the frame loss rate of the transcoding stream corresponding to the transcoding stream, wherein the set value of the frame number of the transcoding stream per second is a set parameter of the transmission of the transcoding stream and is also the ideal frame number per second of the transmission of the transcoding stream.

The frame loss rate of the transcoding stream can be calculated by adopting the following formula 2:

Wherein lfr_z represents a frame loss rate of the transcoding stream, f _a represents a total frame number of the first transcoding stream, f _b represents a total frame number of the second transcoding stream, t _ab represents a sampling interval between the first time and the second time, and fps_z represents a frame number per second setting value of the transcoding stream.

Step S203, judging whether the original stream frame loss rate is smaller than a first threshold and the transcoding stream frame loss rate is larger than a second threshold, if yes, executing step S204.

If the frame loss rate of the original stream is smaller than the first threshold, the frame loss rate of the original stream is lower, and therefore the transmission link between the anchor end and the push node is not abnormal. If the frame loss rate of the original stream is greater than or equal to a first threshold, the frame loss rate of the original stream is beyond a normal range, so that the abnormal occurrence of a transmission link between the anchor end and the push node is indicated. If the frame loss rate of the transcoding stream is larger than a second threshold, the frame loss rate of the transcoding stream is higher and exceeds the normal frame loss range, and if the frame loss rate of the transcoding stream is smaller than or equal to the second threshold, the frame loss rate of the transcoding stream is lower and does not exceed the normal frame loss range.

Therefore, when the frame loss rate of the original stream is smaller than the first threshold value and the frame loss rate of the transcoding stream is larger than the second threshold value, the quality abnormality exists in the processing system formed by the pushing node and the transcoding node of the node abnormal data stream, the current candidate data stream is determined to be the node abnormal data stream, namely, the step S204 and the subsequent steps are executed to further determine which service node in the processing system has the quality abnormality. When the current frame loss rate of the original stream is not satisfied and is smaller than a first threshold value and the frame loss rate of the transcoding stream is larger than a second threshold value, the method is ended.

When a plurality of transcoding streams correspond to the candidate data streams, the method specifically judges whether the original stream frame loss rate is smaller than a first threshold value and the transcoding stream frame loss rate of each transcoding stream corresponding to the candidate data streams is larger than a second threshold value.

Step S204, determining the candidate data stream as a node abnormal data stream, and calculating the output-input fluctuation ratio of the transcoding stream of the node abnormal data stream.

If the frame loss rate of the original stream is smaller than a first threshold value and the frame loss rate of the transcoding stream is larger than a second threshold value, the quality abnormality of a processing system formed by a pushing node and a transcoding node of the node abnormal data stream is indicated, and the candidate data stream is determined to be the node abnormal data stream.

And further determining service nodes with abnormal quality in processing links of the node abnormal data stream. The method specifically comprises the step of determining a service node with abnormal quality in the processing system through the output/input fluctuation ratio of the transcoding stream.

Specifically, the transcode stream output-to-input fluctuation ratio reflects the ratio magnitude of transcode stream output fluctuation to input fluctuation. If the abnormal data stream of the node corresponds to a plurality of transcoding streams, the output-input fluctuation ratio of the transcoding stream corresponding to each transcoding stream is calculated respectively.

In an alternative embodiment, the output-to-input fluctuation ratio of the transcoded stream can be obtained specifically by:

For any transcoding stream of the node abnormal data stream, according to the number of frames per second of the original stream of the receiving end of the transcoding node where the transcoding stream is located in a second historical period (such as the last 5 minutes, etc.), the input fluctuation value of the transcoding stream corresponding to the transcoding stream is calculated. Specifically, the transcoding stream is obtained by transcoding an original stream, so that the transcoding node where the transcoding stream is located receives the original stream, the frame number of the original stream received by the transcoding node at each sampling moment in the second historical period is obtained, a fluctuation algorithm is further adopted to calculate a fluctuation value corresponding to the frame number of the original stream at each sampling moment, and the fluctuation value is the input fluctuation value of the transcoding stream corresponding to the transcoding stream. The fluctuation value includes, but is not limited to, variance, standard deviation, range, etc.

And calculating a transcoding stream output fluctuation value corresponding to the transcoding stream according to the number of frames per second of the transcoding stream of the output end of the transcoding node where the transcoding stream is located in the second historical period. Specifically, the frame number of the transcoding stream output by the transcoding node at different sampling moments of the second historical period is obtained, a fluctuation algorithm is further adopted to calculate the fluctuation value of the frame number of the transcoding stream at each sampling moment, and the fluctuation value is the output fluctuation value of the transcoding stream corresponding to the transcoding stream.

And finally, taking the ratio of the output fluctuation value of the transcoding stream and the input fluctuation value of the transcoding stream corresponding to the transcoding stream as the output fluctuation ratio of the transcoding stream.

Step S205, judging whether the fluctuation ratio of the output and the input of the transcoding stream is smaller than a third threshold value, if yes, executing step S206, and if not, executing step S207.

Step S206, determining a push node of the node abnormal data stream as a quality abnormal node.

If the output-input fluctuation ratio of the transcoding stream is smaller than a third threshold value, the difference between the output fluctuation and the input fluctuation of the transcoding node where the transcoding stream is positioned is smaller, and therefore the transcoding process of the node abnormal data stream is determined to be in a normal state, and the push stream node of the node abnormal data stream is determined to be a quality abnormal node.

Step S207, determining the transcoding node of the node abnormal data stream as a quality abnormal node.

If the output-input fluctuation ratio of the transcoding stream is greater than or equal to a third threshold value, the fact that the difference between the output fluctuation and the input fluctuation of the transcoding node where the transcoding stream is located is larger is indicated, and therefore the transcoding process of the node abnormal data stream is determined to be in an abnormal state, and the transcoding node of the node abnormal data stream is determined to be a quality abnormal node.

In an alternative embodiment, if the transcoding stream of the node abnormal data stream is multiple. And when the output-input fluctuation ratio of the transcoding stream corresponding to each transcoding stream is smaller than a third threshold value, determining a plug-flow node of the node abnormal data stream as a quality abnormal node. And if the output-input fluctuation ratio of the transcoding stream corresponding to each transcoding stream is greater than or equal to a third threshold value, determining each transcoding node of the node abnormal data stream as a quality abnormal node.

If the output-input fluctuation ratio of the transcoding stream corresponding to a part of the transcoding streams (short for first-class transcoding streams) of the node abnormal data streams is smaller than a third threshold value, and the output-input fluctuation ratio of the transcoding stream corresponding to another part of the transcoding streams (short for second-class transcoding streams) is larger than or equal to the third threshold value, determining a push node of the node abnormal data streams as a quality abnormal node, and determining the transcoding node where the second-class transcoding streams are located as the quality abnormal node. In addition, if a certain transcoding node outputs both the first type of transcoding stream and the second type of transcoding stream, the transcoding node is also used as a quality anomaly node.

Therefore, the service node quality detection method provided by the embodiment of the application determines whether the candidate data stream is the abnormal node data stream with the abnormality of the service node in the processing link according to the original stream frame loss rate and the transcoding stream frame loss rate of the abnormal node data stream with the abnormality, and positions out the abnormal quality node by outputting the input fluctuation ratio of the transcoding stream according to the identified abnormal node data stream. The original stream frame loss rate, the transcoding stream frame loss rate and the transcoding stream output/input fluctuation ratio adopted by the scheme are not internal monitoring data of the service node, so that the scheme does not need to rely on the service node internal monitoring data provided by a third party for quality detection of the service node, the application range of the scheme is improved, and accurate and rapid positioning of quality abnormal nodes and node abnormal data streams can be realized.

Example two

Fig. 4 is a flow chart illustrating a threshold adjustment method applied to a quality of service node detection method according to a second embodiment of the present application. The method and the device are used for dynamically adjusting the threshold value applied to the service node quality detection method.

As shown in fig. 4, the method specifically includes the following steps:

Step S401, acquiring feedback data.

The feedback data is feedback of a detection result of the service node quality detection method.

In an alternative embodiment, the feedback data may be derived from manual feedback, for example, when it is determined during manual inspection that the detection result obtained by the service node quality detection method does not match the actual situation, corresponding feedback data is generated.

In an alternative embodiment, the feedback data may originate from user side feedback. For example, in the implementation process, user feedback information with feedback type being abnormal in service quality may be obtained, and data flows corresponding to the user feedback information may be determined, and if the user feedback information corresponding to any one data flow exceeds a fourth threshold, the data flow is determined to be an abnormal data flow of a real node. Searching a detection result obtained by the service node quality detection method, and if the detection result that the real node abnormal data stream is judged to be the node abnormal data stream cannot be searched from the detection result, generating node abnormal data stream missed judgment feedback data corresponding to the real node abnormal data stream.

In an alternative embodiment, the feedback data may also be generated by identifying candidate data streams having abnormal play, and determining a push node and a transcoding node of each candidate data stream respectively. For any one of the pushing nodes, if the number of the candidate data streams corresponding to the pushing node exceeds a fifth threshold, determining that the pushing node is a real quality abnormal node, and for any one of the transcoding nodes, if the number of the candidate data streams corresponding to the transcoding node exceeds a sixth threshold, determining that the transcoding node is a real quality abnormal node. Comparing the generated real quality abnormal node with the quality abnormal node detection result obtained by adopting the service node quality detection method in the first embodiment, and generating corresponding node feedback data according to the comparison result.

Further optionally, the identified data stream processed by the real quality abnormal node is used as a real node abnormal data stream, the real node abnormal data stream is compared with the node abnormal data stream detection result obtained by adopting the service node quality detection method in the first embodiment, and corresponding data stream feedback data is generated according to the comparison result.

Step S402, the type of the feedback data is identified, if the feedback data is the data stream feedback data, step S403 is executed, and if the feedback data is the node feedback data, step S406 is executed.

The service node quality detection method provided by the first embodiment can generate two types of detection results, wherein the first type of detection result is a recognition result of whether the candidate data stream is a node abnormal data stream or not, and the second type of detection result is a recognition result of a quality abnormal service node of the node abnormal data stream. The feedback data aiming at the first type of detection result is data stream feedback data, the feedback data is different from the detection result of the node abnormal data stream, the feedback data aiming at the second type of detection result is node feedback data, and the feedback data is different from the detection result of the quality abnormal service node of the node abnormal data stream.

Step S403, the type of the data stream feedback data is identified, if the feedback data is misjudged by the abnormal data stream of the node, step S404 is executed, and if the feedback data is missed by the abnormal data stream of the node, step S405 is executed.

The types of data stream feedback data are divided into two types, wherein the first type is feedback data aiming at a candidate data stream which is identified as a node abnormal data stream, the candidate data stream is determined to be the node abnormal data stream by adopting a service node quality detection method, but the candidate data stream is determined to be not the node abnormal data stream in the feedback data, namely the candidate data stream is misjudged as the node abnormal data stream. The second is feedback data for a candidate data stream which is not identified as a node abnormal data stream, wherein the candidate data stream is determined to be not the node abnormal data stream by adopting a service node quality detection method, but the candidate data stream is determined to be the node abnormal data stream in the feedback data, namely the candidate data stream is missed to be judged as the node abnormal data stream.

In step S404, the first threshold is adjusted downward and the second threshold is adjusted upward.

When the abnormal data stream misjudgment feedback data of the node is received, the fact that the abnormal data stream of the non-node is misjudged as the abnormal data stream of the node is reflected, and therefore the first threshold value is adjusted downwards and the second threshold value is adjusted upwards. The first threshold value can be adjusted downwards and the second threshold value can be adjusted upwards according to a preset step length, so that the first threshold value in the subsequent detection process is reduced, the second threshold value in the subsequent detection process is improved, and the occurrence of the misjudgment phenomenon is reduced.

In step S405, the first threshold is adjusted up and the second threshold is adjusted down.

And when the missing judgment feedback data of the abnormal data stream of the node is received, reflecting that the real abnormal data stream of the node is not detected, the first threshold value is adjusted upwards and the second threshold value is adjusted downwards. The first threshold value and the second threshold value can be adjusted up and down according to a preset step length, so that the first threshold value in the subsequent detection process is improved, the second threshold value in the subsequent detection process is reduced, and the occurrence of the missing detection phenomenon is reduced.

Step S406, the type of the node feedback data is identified, if the feedback data is the push node misjudgment feedback data, step S407 is executed, and if the feedback data is the transcoding node misjudgment feedback data, step S408 is executed.

The types of the node feedback data are divided into two types, wherein the first type is the feedback data aiming at that a push node of the node abnormal data stream is identified as a quality abnormal node, the push node of the node abnormal data stream is determined to be the quality abnormal node by adopting a service node quality detection method, but the push node is determined to be not the quality abnormal node in the feedback data, namely, the push node of the node abnormal data stream is misjudged as the quality abnormal node. The second type is feedback data for identifying the transcoding node of the node abnormal data stream as a quality abnormal node, wherein the transcoding node of the node abnormal data stream is determined to be the quality abnormal node by adopting a service node quality detection method, but the transcoding node is determined not to be the quality abnormal node in the feedback data, namely the transcoding node of the node abnormal data stream is misjudged to be the quality abnormal node.

Step S407, the third threshold is adjusted down.

When the push node misjudgment feedback data is received, the push node reflecting the abnormal data flow of the node is misjudged as the quality abnormal node, so that the third threshold value is adjusted down. The third threshold value can be adjusted down according to a preset step length, so that the third threshold value in the subsequent detection process is reduced, and the occurrence of the misjudgment phenomenon is reduced.

In step S408, the third threshold is adjusted upward.

When receiving the feedback data of the misjudgment of the transcoding node, the transcoding node reflecting the abnormal data stream of the node is misjudged as the quality abnormal node, so that the third threshold value is adjusted upwards. The third threshold value can be adjusted up according to a preset step length, so that the third threshold value in the subsequent detection process is improved, and the occurrence of the misjudgment phenomenon is reduced.

Therefore, the threshold adjustment method applied to the service node quality detection method provided by the embodiment of the application can dynamically adjust the first threshold and the second threshold according to the data stream feedback data so as to improve the detection precision of the node abnormal data stream, and can dynamically adjust the third threshold according to the node feedback data so as to improve the detection precision of the quality abnormal node of the node abnormal data stream.

Example III

Fig. 5 is a schematic structural diagram of a service node quality detection device according to a third embodiment of the present application. As shown in fig. 5, the apparatus 500 includes an identification module 510, a calculation module 520, a first detection module 530, and a second detection module 540.

An identifying module 510, configured to identify candidate data streams having abnormal play;

the calculating module 520 is configured to calculate an original stream frame loss rate and a transcoding stream frame loss rate of the candidate data stream;

A first detection module 530, configured to determine that the candidate data stream is a node abnormal data stream if the frame loss rate of the original stream is less than a first threshold and the frame loss rate of the transcoding stream is greater than a second threshold, and calculate a ratio of output and input fluctuation of the transcoding stream of the node abnormal data stream;

The second detection module 540 is configured to determine that the push node of the node abnormal data stream is a quality abnormal node if the output/input fluctuation ratio of the transcoding stream is less than a third threshold, and determine that the transcoding node of the node abnormal data stream is a quality abnormal node if the output/input fluctuation ratio of the transcoding stream is greater than or equal to the third threshold.

In an alternative embodiment, the identifying module 510 is configured to identify candidate data streams with abnormal play according to the barrage data and/or the abnormal report data.

In an alternative embodiment, the calculating module 520 is configured to calculate an original stream frame loss rate of the candidate data stream according to the input monitoring data of the push node of the candidate data stream in the first history period;

In an alternative embodiment, the calculating module 520 is configured to obtain a first total frame number of the primary stream received by the push node at a first time and a second total frame number of the primary stream received at a second time, calculate a total frame number difference between the second total frame number of the primary stream and the first total frame number of the primary stream, and calculate the frame loss rate of the primary stream according to the total frame number difference of the primary stream and a set value of frames per second of the primary stream;

In an alternative embodiment, the first detection module 530 is configured to calculate, for any one of the transcoded streams of the node abnormal data stream, an input fluctuation value of the transcoded stream corresponding to the transcoded stream according to a number of frames per second of an original stream at a receiving end of a transcoded node where the transcoded stream is located in a second history period;

In an alternative embodiment, the device further comprises a threshold adjustment module (not shown in the figure) for receiving the abnormal data stream misjudgment feedback data of the node, and adjusting the first threshold downwards and the second threshold upwards;

Therefore, the service node quality detection device provided by the embodiment of the application determines whether the candidate data stream is the abnormal node data stream with the abnormality of the service node in the processing link according to the original stream frame loss rate and the transcoding stream frame loss rate of the abnormal node data stream with the abnormality, and positions out the abnormal quality node by outputting the input fluctuation ratio of the transcoding stream according to the identified abnormal node data stream. The original stream frame loss rate, the transcoding stream frame loss rate and the transcoding stream output/input fluctuation ratio adopted by the scheme are not internal monitoring data of the service node, so that the scheme does not need to rely on the service node internal monitoring data provided by a third party for quality detection of the service node, the application range of the scheme is improved, and accurate and rapid positioning of quality abnormal nodes and node abnormal data streams can be realized.

Example IV

Fig. 6 shows a schematic structural diagram of a computing device according to a fourth embodiment of the present application. The specific embodiments of the present application are not limited to a particular implementation of a computing device.

As shown in FIG. 6, the computing device may include a processor 602, a communication interface (Communications Interface) 604, a memory 606, and a communication bus 608.

Wherein the processor 602, the communication interface 604, and the memory 606 communicate with each other via a communication bus 608. Communication interface 604 is used to communicate with network elements of other devices, such as clients or other servers. The processor 602 is configured to execute the program 610, and may specifically perform relevant steps in the foregoing service node quality detection method embodiment for a computing device.

In particular, program 610 may include program code including computer-operating instructions.

The processor 602 may be a central processing unit CPU, or an Application-specific integrated Circuit ASIC (Application SPECIFIC INTEGRATED Circuit), or one or more integrated circuits configured to implement embodiments of the present application. The computing device may include one or more processors of the same type, such as one or more CPUs, or of different types, such as one or more CPUs and one or more ASICs.

A memory 606 for storing a program 610. The memory 606 may comprise high-speed RAM memory or may further comprise non-volatile memory (non-volatile memory), such as at least one disk memory. Program 610 may be specifically operative to cause processor 602 to perform operations in any of the method embodiments described above.

Example five

A fifth embodiment of the present application provides a non-volatile computer storage medium, where at least one executable instruction or a computer program is stored, where the executable instruction or the computer program may cause a processor to perform operations corresponding to the service node quality detection method in any of the foregoing method embodiments.

Example six

A sixth embodiment of the present application provides a computer program product, where the computer program product includes at least one executable instruction or a computer program, where the executable instruction or the computer program may cause a processor to perform operations corresponding to the service node quality detection method in any of the foregoing method embodiments.

In summary, according to the computing device, the computer storage medium and the computer program product provided in the present embodiment, it can be seen that the method for detecting quality of service node according to the present application determines whether the candidate data stream is a node anomaly data stream having an anomaly in a processing link according to an original stream frame loss rate and a transcode stream frame loss rate of a node anomaly data stream having an anomaly, and locates a quality anomaly node by outputting an input fluctuation ratio of the transcode stream with respect to the identified node anomaly data stream. The original stream frame loss rate, the transcoding stream frame loss rate and the transcoding stream output/input fluctuation ratio adopted by the scheme are not internal monitoring data of the service node, so that the scheme does not need to rely on the service node internal monitoring data provided by a third party for quality detection of the service node, the application range of the scheme is improved, and accurate and rapid positioning of quality abnormal nodes and node abnormal data streams can be realized.

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present application are not directed to any particular programming language. It will be appreciated that the teachings of the present application described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present application.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the above description of exemplary embodiments of the application, various features of the embodiments of the application are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the application and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

Various component embodiments of the application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components according to embodiments of the present application may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present application can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present application may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.

Claims

1. A method for detecting quality of service node, comprising:

2. The method of claim 1, wherein identifying candidate data streams for which playout anomalies exist comprises:

3. The method according to claim 1 or 2, wherein the calculating the original stream frame loss rate and the transcoding stream frame loss rate of the candidate data stream comprises:

4. The method of claim 3, wherein calculating the original stream frame loss rate of the candidate data stream based on the input monitoring data of the push node of the candidate data stream during the first history period comprises:

The method comprises the steps of obtaining a first original flow total frame number received by a push flow node at a first moment and a second original flow total frame number received at a second moment, calculating an original flow total frame number difference value between the second original flow total frame number and the first original flow total frame number, and calculating the original flow frame loss rate according to the original flow total frame number difference value and an original flow per second frame number set value;

and/or, the calculating the frame loss rate of the transcoding stream of the candidate data stream according to the monitoring data of the output end of the transcoding node where the transcoding stream of the candidate data stream is located in the first history period includes:

For any transcoding stream, acquiring the total frame number of a first transcoding stream output by a transcoding node where the transcoding stream is positioned at a first moment and the total frame number of a second transcoding stream output at a second moment; calculating a total frame number difference value of the second transcoding stream and the total frame number of the first transcoding stream, and calculating a corresponding transcoding stream frame loss rate of the transcoding stream according to the total frame number difference value of the transcoding stream and a set value of the number of frames per second of the transcoding stream;

5. The method of any of claims 1-4, wherein the calculating a transcode stream output-to-input fluctuation ratio for the node-abnormal data stream comprises:

6. The method according to any one of claims 1-5, further comprising:

7. The method according to any one of claims 1-6, further comprising:

8. A service node quality detection apparatus, comprising:

9. A computing device comprising a processor, a memory, a communication interface, and a communication bus, the processor, the memory, and the communication interface completing communication with each other over the communication bus;

the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to the quality of service node detection method according to any one of claims 1-7.

10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the quality of service node detection method according to any of claims 1-7.

11. A computer program product comprising at least one executable instruction for causing a processor to perform operations corresponding to the method of quality of service node detection according to any one of claims 1 to 7.