Video service monitoring method, device, equipment, medium and product

Abstract

The invention provides a video service monitoring method and device, equipment, a medium and a product, and the method comprises the steps: obtaining video service data which reflects the operation condition of a video service; matching the video service data with a service quality rule, and determining a video service score; determining a dynamic index threshold based on the video service volume characteristics, the video service volume characteristics reflecting the service volume of the video service and / or the processing capability of the video service device; and when the score of the video service is lower than the score threshold, determining a quality problem positioning result of the video service based on the video service data and the dynamic index threshold. The accuracy of a video service quality problem positioning result can be improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to video service monitoring methods, devices, equipment, media and products. Background Technology

[0002] After installing a set-top box for a user, in order to better serve the user and accurately and quickly resolve user issues, a software probe is usually built into the user's set-top box. This probe collects data from the underlying player, network, and system of the set-top box and periodically reports this operational information to the software probe platform. The software probe platform processes, displays, and pushes the relevant message information to relevant personnel, enabling customer service, installation, and maintenance personnel to more proactively, accurately, and quickly locate and resolve user problems.

[0003] Based on data collected by soft probes, quickly and clearly identifying and determining video service quality issues is a crucial task. Current technologies often employ quantitative methods to pinpoint these problems; for example, if a certain indicator of a device exceeds a fixed threshold, it indicates that the device is malfunctioning. This broad-based approach to problem definition is inaccurate in locating video service quality issues. Summary of the Invention

[0004] This application provides video service monitoring methods, devices, equipment, media, and products to address the shortcomings of existing technologies in accurately locating video service quality problems, thereby improving the accuracy of video service quality problem location results.

[0005] This application provides a video service monitoring method, including: Acquire video service data, which reflects the operational status of the video service; The video service data is matched with the service quality rules to determine the video service score; Based on the characteristics of video traffic volume, dynamic indicator thresholds are determined, wherein the characteristics of video traffic volume reflect the traffic volume of video services and / or the processing capacity of video service equipment. When the video service score is lower than the score threshold, the quality problem location result of the video service is determined based on the video service data and the dynamic indicator threshold.

[0006] According to the video service monitoring method provided in this application, the step of determining dynamic indicator thresholds based on video service volume characteristics includes: The video traffic characteristics of the current time window are input into the trained threshold prediction network to obtain the threshold prediction result output by the threshold prediction network. Based on the threshold prediction results, the dynamic indicator threshold is determined.

[0007] According to the video service monitoring method provided in this application, determining the dynamic indicator threshold based on the threshold prediction result includes: Based on the dynamic indicator threshold of at least one historical time window, determine the historical indicator threshold; The historical indicator threshold and the threshold prediction result are fused to obtain the dynamic indicator threshold for the current time window.

[0008] According to the video service monitoring method provided in this application, the step of inputting the video service volume characteristics of the current time window into a trained threshold prediction network includes: When it is determined that the difference between the video traffic volume feature of the current time window and the video traffic volume feature of the historical time window exceeds the fluctuation range, the video traffic volume feature of the current time window is input into the trained threshold prediction network.

[0009] According to the video service monitoring method provided in this application, the step of determining dynamic indicator thresholds based on video service volume characteristics includes: When the video traffic characteristics correspond to a preset time period, the benchmark indicator threshold is weighted to obtain the dynamic indicator threshold. The weights in the weighted processing correspond to the preset time period.

[0010] According to the video service monitoring method provided in this application, after determining the location result of the quality problem of the video service based on the video service data and the dynamic indicator threshold, the method includes: Based on the quality problem location results, a quality problem handling plan corresponding to the quality problem location results is generated.

[0011] This application also provides a video service monitoring device, including: The data acquisition module is used to acquire video service data, which reflects the operation status of the video service; The quality scoring module is used to match the video service data with service quality rules to determine the video service score; The dynamic threshold determination module is used to determine dynamic indicator thresholds based on video traffic characteristics, wherein the video traffic characteristics reflect the traffic volume of video services and / or the processing capacity of video service equipment. The problem location module is used to determine the quality problem location result of the video service based on the video service data and the dynamic indicator threshold when the video service score is lower than the score threshold.

[0012] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the video service monitoring method described above.

[0013] This application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the video service monitoring method as described above.

[0014] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the video service monitoring method as described above.

[0015] The video service monitoring method, apparatus, equipment, medium, and product provided in this application acquire video service data, match the video service data with service quality rules, and obtain a video service score. Instead of directly locating video service quality problems based on a fixed judgment threshold, it determines a dynamic indicator threshold based on video service volume characteristics and locates video service quality problems based on this dynamic indicator threshold. In this way, the location of video service quality problems is not based on a quantitative principle, but can be dynamically adjusted based on the actual service volume and processing situation, which can improve the accuracy of the video service quality problem location results. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the video service monitoring method provided in this application.

[0018] Figure 2 This is a schematic diagram illustrating the processing of video service operation data in the video service monitoring method provided in this application.

[0019] Figure 3 This is a schematic diagram illustrating the process of determining the location of quality problems in the video service monitoring method provided in this application.

[0020] Figure 4 This is a flowchart illustrating the process of determining the location of quality problems in the video service monitoring method provided in this application.

[0021] Figure 5This is a structural schematic diagram of the video service monitoring device provided in this application.

[0022] Figure 6 This is a schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0025] It should also be understood that the terminology used in this application specification is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this application specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0026] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0027] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0028] The following is combined with Figure 1-4 Describe the video service monitoring method provided in this application. For example... Figure 1 As shown, the video service monitoring method includes the following steps: S110. Obtain video service data, which reflects the operation status of video services; S120. Match the video service data with the service quality rules to determine the video service score; S130. Based on the characteristics of video traffic volume, determine the dynamic indicator threshold. The characteristics of video traffic volume reflect the traffic volume of video services and / or the processing capacity of video service equipment. S140. When the video service score is lower than the score threshold, the quality problem location result of the video service is determined based on the video service data and dynamic indicator thresholds.

[0029] The video service monitoring method provided in this application acquires video service data, matches the video service data with service quality rules to obtain a video service score, and then does not directly locate video service quality problems based on a fixed judgment threshold. Instead, it determines a dynamic indicator threshold based on video service volume characteristics and locates video service quality problems based on this dynamic indicator threshold. In this way, the location of video service quality problems is not based on a quantitative principle, but can be dynamically adjusted based on the actual service volume and processing situation, which can improve the accuracy of the video service quality problem location results.

[0030] In the video service monitoring method provided in this application, the video service data reflects the operational status of the video service and can be collected through a soft probe built into the set-top box. This method can use video service data from a large geographical area (such as a province) as the source data for locating video service quality problems, thus providing a sufficient sample size for more accurate results. Specifically, as... Figure 2 As shown, the software probe built into the set-top box collects information from the set-top box in real time and reports it to the software probe platform. The software probe platform collects and receives various message information reported by the set-top box. The platform can centrally process the collected message information to collect video service operation indicator data. For example, the platform can use a Spark program to write the collected message information to HDFS (Hadoop Distributed File System, a distributed file system in the Hadoop ecosystem), and then use the Spark SQL engine to statistically analyze the video service operation indicator data in the message information to obtain video service data. Video service operation indicators are metrics that can determine the quality of video services, such as playback success rate, number of users playing, EPG (Electronic Program Guide) success rate, quality rate, total number of alarms, and number of buffering / alarms.

[0031] In one possible implementation, to improve the accuracy of video service quality issue localization, instead of processing and analyzing video service data at a specific moment, a time window approach is used. This involves analyzing video service operation metrics data collected by the soft probe, specifically analyzing video service data within a given time period. This approach considers changes in video service data over a given time period, leading to more accurate quality issue localization results. In this implementation, the Spark SQL engine can be triggered periodically (e.g., every 5 minutes) to statistically analyze video service operation metrics data in the message information, thus obtaining video service data within a 5-minute time window. This time window's video service data can then be sent to a Kafka platform, and the terminal executing the method provided in this application can listen to the Kafka topic in real time to acquire the video service data.

[0032] In one possible implementation, after obtaining the video service data, the video service data can be structurally transformed. For example, based on the subsequent rule matching method, the video service data can be transformed into a structure suitable for the subsequent rule matching method through an ETL (Extract, Transform, Load) architecture.

[0033] After obtaining the video service data, the video service data is matched with the pre-set service quality rules to obtain a video service score that reflects the quality of the video service. The pre-set service quality rules can be expert rules. Matching the video service data with the pre-set service quality rules can be done using existing rule matching methods. For example, the RETE algorithm can be used to implement rule matching. The RETE algorithm is an efficient pattern matching algorithm for a generative rule system. It optimizes the matching efficiency through a discrimination network composed of an Alpha network (handling single-input pattern matching) and a Beta network (handling dual-input pattern matching), achieving fact matching with a time complexity of 0 (1).

[0034] The service quality rules can include scoring rules for various video service quality indicators, as shown in Table 1.

[0035] Table 1

[0036] Based on the matching results between video service data and service quality rules, a video service score reflecting the quality of the video service can be obtained. When the video service score is lower than the set score threshold, it is determined that there is a quality problem in the video service, and the quality problem needs to be located.

[0037] In the method provided in this application, when locating quality problems, the indicators are not compared with fixed thresholds. Instead, dynamic indicator thresholds are determined based on the actual video service processing situation. Then, the various indicator data in the video service data are compared with the corresponding dynamic indicator thresholds to obtain the video service quality problem location results.

[0038] When the volume of traffic differs, or the processing capacity of the video service system differs (e.g., some devices have increased memory), it usually means that the usage of video service equipment will change. The method provided in this application determines dynamic indicator thresholds based on video traffic characteristics that reflect the traffic volume of the video service and / or the processing capacity of the video service system. This allows the indicator thresholds to quickly respond to changes in video traffic and adjust to the optimal value, thereby improving the accuracy of service quality positioning results and avoiding excessive, unnecessary, and inaccurate alarm information.

[0039] In practical applications, video traffic exhibits certain temporal characteristics. For example, traffic surges during holidays and summer / winter breaks. In some implementations, video traffic characteristics can reflect the match between the current time period and a preset time period. If the current time period matches the preset time period, it indicates a significant increase in video traffic. In this case, a simpler method can be used to determine the dynamic indicator threshold. Specifically, when the video traffic characteristics correspond to a preset time period, a weighted average is applied to the baseline indicator threshold to obtain the dynamic indicator threshold. The weights in the weighting process correspond to the preset time period.

[0040] The benchmark threshold can be obtained by summarizing experience based on historical data. For example, in one possible implementation, the benchmark threshold can be set as shown in Table 2.

[0041] Table 2

[0042] The preset time period is determined based on the time characteristics of video service volume. For example, in one possible implementation, a preset time period and corresponding weight can be set as shown in Table 3.

[0043] Table 3

[0044] By directly weighting the baseline threshold for specific time periods to determine the dynamic index threshold, the computational workload of the dynamic index threshold can be reduced, thereby improving the monitoring efficiency of video service quality.

[0045] Furthermore, in another possible implementation, video traffic volume characteristics can be obtained by processing the message information collected by the soft probe. These characteristics can be represented as feature vectors, including data across multiple dimensions, such as video playback count, number of running devices, and device processing capacity. Based on these video traffic volume characteristics, dynamic indicator thresholds are determined, including: Input the video traffic characteristics of the current time window into the trained threshold prediction network and obtain the threshold prediction result output by the threshold prediction network. Based on the threshold prediction results, the threshold for dynamic indicators is determined.

[0046] Outside of a preset time period, the video traffic volume features of the current time window can be input into a trained threshold prediction network to obtain the threshold prediction results output by the network. The threshold prediction network can be trained using supervised learning, with training data including sample video traffic volume features and the corresponding threshold labels for those features.

[0047] In one possible implementation, the calculated threshold prediction result can be directly used as the dynamic indicator threshold within the current time window. However, this may lead to occasional jumps in the indicator threshold due to changes in video traffic characteristics, potentially causing system instability. Another possible implementation of the method provided in this application determines the dynamic indicator threshold based on the threshold prediction result, including: Based on the dynamic indicator threshold of at least one historical time window, determine the historical indicator threshold. By fusing historical indicator thresholds and threshold prediction results, dynamic indicator thresholds for the current time window are obtained.

[0048] The historical time window is the time window preceding the current time window. In one possible implementation, the dynamic indicator threshold of the previous historical time window can be used as the historical indicator threshold. In another possible implementation, the average of the dynamic indicator thresholds of n consecutive historical time windows preceding the current time window can be used to obtain the historical indicator threshold. The historical indicator threshold and the threshold prediction result are then fused using a weighted fusion method to finally obtain the dynamic indicator threshold for the current time window. The process of determining the historical indicator threshold and fusing it with the threshold prediction result can be expressed by the formula: T(t) = θ·H(t) + (1-θ)·N(X(t)), where H(t) represents the historical indicator threshold, X(t) represents the video traffic characteristics, N(·) represents the threshold prediction network, and θ represents the time decay factor, which can be obtained based on experiments in real-world scenarios.

[0049] Calculating a dynamic threshold for each time window would consume significant computational resources. One possible implementation of the method provided in this application involves inputting the video traffic characteristics of the current time window into a trained threshold prediction network, including: When it is determined that the difference between the video traffic characteristics of the current time window and the video traffic characteristics of historical time windows exceeds the fluctuation range, the video traffic characteristics of the current time window are input into the trained threshold prediction network.

[0050] In this implementation, the dynamic indicator threshold is not calculated for every time window. Instead, it first checks whether there are significant fluctuations in the video traffic characteristics of the current time window. If the difference between the video traffic characteristics of the current time window and those of historical time windows exceeds the fluctuation range, the video traffic characteristics of the current time window are input into the trained threshold prediction network to calculate the dynamic indicator threshold. If the fluctuation range is not exceeded, the dynamic indicator threshold of the previous time window can be used. In this way, the dynamic indicator threshold is calculated only when it is necessary to update the indicator threshold, which reduces resource consumption.

[0051] like Figure 3 As shown, after determining the dynamic indicator thresholds, the data for each indicator in the video service data are compared with the corresponding dynamic indicator thresholds to determine the location of quality problems. For example, if multiple CDN-related indicators exceed the thresholds, it may indicate that the problem lies with the CDN service provider; if the percentage of program stuttering is high, it may be necessary to check the program source or program transmission link; if the percentage of stuttering is high for a specific terminal model, it may indicate that the terminal model has compatibility or performance issues; if the pass rate is generally lower than the threshold, it may indicate a systemic problem, such as network congestion or a general problem with the service provider.

[0052] In one possible implementation of the method provided in this application, after determining the location result of the quality problem in the video service based on video service data and dynamic indicator thresholds, the method includes: Based on the quality problem location results, a corresponding quality problem handling plan is generated.

[0053] like Figure 4 As shown, based on the results of the quality problem localization, corresponding handling plans can be specified. For example, for CDN issues, the CDN provider can be contacted to find the cause of service failure or performance degradation; for program quality issues, the program source server can be checked to ensure the quality of the content and the stability of transmission; for terminal model issues, cooperation with the terminal manufacturer can be carried out to investigate whether there are software or hardware defects; for systemic problems, network optimization or increased service capacity may be required.

[0054] The video service monitoring device provided in this application is described below. The video service monitoring device described below can be referred to in correspondence with the video service monitoring method described above. Figure 5 As shown, the video service monitoring device provided in this application includes: The data acquisition module 510 is used to acquire video service data, which reflects the operation status of the video service. The quality scoring module 520 is used to match video service data with service quality rules to determine the video service score; The dynamic threshold determination module 530 is used to determine dynamic indicator thresholds based on video traffic characteristics, where video traffic characteristics reflect the traffic volume of video services and / or the processing capacity of video service equipment. The problem location module 540 is used to determine the quality problem location result of the video service based on the video service data and dynamic indicator thresholds when the video service score is lower than the score threshold.

[0055] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6 As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640. The processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions in the memory 630 to execute a video service monitoring method. This method includes: acquiring video service data, which reflects the operation status of the video service; matching the video service data with service quality rules to determine a video service score; determining a dynamic indicator threshold based on video service volume characteristics, which reflect the service volume of the video service and / or the processing capacity of the video service equipment; and determining the location of a quality problem in the video service based on the video service data and the dynamic indicator threshold when the video service score is lower than the score threshold.

[0056] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0057] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the video service monitoring method provided by the above methods. The method includes: acquiring video service data, which reflects the operation status of video services; matching the video service data with service quality rules to determine a video service score; determining a dynamic indicator threshold based on video service volume characteristics, which reflect the service volume of video services and / or the processing capability of video service equipment; and determining the video service quality problem location result based on the video service data and the dynamic indicator threshold when the video service score is lower than the score threshold.

[0058] In another aspect, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program is implemented to perform the video service monitoring method provided by the above methods. The method includes: acquiring video service data, which reflects the operation status of video services; matching the video service data with service quality rules to determine a video service score; determining a dynamic indicator threshold based on video service volume characteristics, which reflect the service volume of video services and / or the processing capability of video service equipment; and determining the video service quality problem location result based on the video service data and the dynamic indicator threshold when the video service score is lower than the score threshold.

[0059] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0060] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0061] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A video service monitoring method, characterized in that, include: Acquire video service data, which reflects the operational status of the video service; The video service data is matched with the service quality rules to determine the video service score; Based on the characteristics of video traffic volume, dynamic indicator thresholds are determined, wherein the characteristics of video traffic volume reflect the traffic volume of video services and / or the processing capacity of video service equipment. When the video service score is lower than the score threshold, the quality problem location result of the video service is determined based on the video service data and the dynamic indicator threshold.

2. The video service monitoring method according to claim 1, characterized in that, The determination of dynamic indicator thresholds based on video traffic characteristics includes: The video traffic characteristics of the current time window are input into the trained threshold prediction network to obtain the threshold prediction result output by the threshold prediction network. Based on the threshold prediction results, the dynamic indicator threshold is determined.

3. The video service monitoring method according to claim 2, characterized in that, Determining the dynamic indicator threshold based on the threshold prediction result includes: Based on the dynamic indicator threshold of at least one historical time window, determine the historical indicator threshold; The historical indicator threshold and the threshold prediction result are fused to obtain the dynamic indicator threshold for the current time window.

4. The video service monitoring method according to claim 2, characterized in that, The step of inputting the video traffic characteristics of the current time window into the trained threshold prediction network includes: When it is determined that the difference between the video traffic volume feature of the current time window and the video traffic volume feature of the historical time window exceeds the fluctuation range, the video traffic volume feature of the current time window is input into the trained threshold prediction network.

5. The video service monitoring method according to claim 1, characterized in that, The determination of dynamic indicator thresholds based on video traffic characteristics includes: When the video traffic characteristics correspond to a preset time period, the benchmark indicator threshold is weighted to obtain the dynamic indicator threshold. The weights in the weighted processing correspond to the preset time period.

6. The video service monitoring method according to claim 1, characterized in that, After determining the location result of the quality problem in the video service based on the video service data and the dynamic indicator threshold, the process includes: Based on the quality problem location results, a quality problem handling plan corresponding to the quality problem location results is generated.

7. A video service monitoring device, characterized in that, include: The data acquisition module is used to acquire video service data, which reflects the operation status of the video service; The quality scoring module is used to match the video service data with service quality rules to determine the video service score; The dynamic threshold determination module is used to determine dynamic indicator thresholds based on video traffic volume characteristics, wherein the video traffic volume characteristics reflect the traffic volume of video services and / or the processing capability of video service equipment. The problem localization module is used to determine the quality problem localization result of the video service based on the video service data and the dynamic indicator threshold when the video service score is lower than the score threshold.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the video service monitoring method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the video service monitoring method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the video service monitoring method as described in any one of claims 1 to 6.

Images