Method and device for determining running state of video service and electronic equipment

Abstract

The invention discloses a video service operation state determination method and device and electronic equipment. The method comprises the steps that flow data of target service network elements in the video service architecture and service data corresponding to the target service network elements are collected, the target service network elements comprise at least one of a media service network element and an upper cloud service network element, and the service data comprise running service activity state data in the target service network elements; predicting the traffic data by using the traffic prediction model to obtain a prediction result; and determining the operation state of the target service network element according to the prediction result and the service data. The technical problem that the operation state of the service network element in the GB / T 28181 protocol video service architecture cannot be accurately monitored in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of video services, and more specifically, to a method, device, and electronic device for determining the operating status of a video service. Background Art

[0002] The GB / T 28181 protocol video service architecture includes multiple service network elements. Currently, video service monitoring based on the GB / T 28181 protocol mainly relies on querying the service process status and server resource utilization. In actual production scenarios, due to the complexity of GB / T 28181 protocol video services, monitoring methods based on service process status and server resource utilization cannot fully reflect the actual operating status of the services in use. The lack of awareness of the operating status of the service network element cluster leads to the failure to timely detect system failures.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, and electronic device for determining the operating status of a video service, so as to at least solve the technical problem that the related technology cannot accurately monitor the operating status of service network elements in the GB / T 28181 protocol video service architecture.

[0005] According to one aspect of an embodiment of the present application, a method for determining the operating status of a video service is provided, comprising: collecting traffic data of a target service network element in a video service architecture and business data corresponding to the target service network element, wherein the target service network element comprises at least one of the following: a media service network element and a cloud service network element, and the business data comprises status data of business activities running in the target service network element; predicting the traffic data using a traffic prediction model to obtain a prediction result; and determining the operating status of the target service network element based on the prediction result and the business data.

[0006] In some embodiments of the present application, the prediction results include the inbound traffic prediction results and the outbound traffic prediction results of the target service network element; the operating status of the target service network element is determined based on the prediction results and the business data, including: determining a first parameter based on the inbound traffic prediction results and the outbound traffic prediction results, wherein the first parameter is used to reflect the degree of parity between the inbound traffic and the outbound traffic in the target service network element; determining a second parameter based on the outbound traffic prediction results and the business data, wherein the second parameter is used to reflect the difference between the predicted value and the actual demand value of the outbound traffic in the target service network element; determining the operating status based on the first parameter and the second parameter.

[0007] In some embodiments of the present application, the business data includes the operating parameters of the target camera in the target service network element for providing traffic data; the second parameter is determined based on the outbound traffic prediction result and the business data, including: obtaining the number of target cameras and the bit rate of each target camera; determining the average bit rate of the cameras corresponding to the number and bit rate, wherein the average bit rate and number of cameras are used to determine the data transmission requirements of the target service network element when processing the video stream; the second parameter is determined based on the outbound traffic prediction result and the average bit rate of the cameras.

[0008] In some embodiments of the present application, the operating status is determined based on the first parameter and the second parameter, including: determining the health of the target service network element based on the first parameter and the second parameter, wherein the health is used to quantitatively represent the traffic balance of the target service network element; when the health meets the preset conditions, determining that the operating status of the target service network element is an abnormal state.

[0009] In some embodiments of the present application, it also includes: obtaining first traffic data and first business data of the media service network element, and determining a first prediction result corresponding to the media service network element; obtaining second traffic data and second business data of the cloud service network element, and determining a second prediction result corresponding to the cloud service network element, wherein the cloud service network element is located in the video stream outlet direction of the media service network element; determining the operating status of the video service architecture based on the first business data, the first prediction result, the second business data, and the second prediction result.

[0010] In some embodiments of the present application, the operating status of the video service architecture is determined based on the first business data, the first prediction result and the second business data, the second prediction result, including: when the operating status of the media service network element is determined to be normal based on the first business data and the first prediction result, the operating status of the cloud service network element is determined based on the second business data and the second prediction result; when the operating status of the cloud service network element is normal, the operating status of the video service architecture is determined to be normal.

[0011] In some embodiments of the present application, the traffic prediction model includes an inbound traffic prediction model and an outbound traffic prediction model, and the traffic prediction model is trained in the following manner: obtaining historical traffic data of the target service network element, and splitting the historical traffic data into an inbound traffic data set and an outbound traffic data set; using the inbound traffic data set to train the initial inbound traffic prediction model, and obtaining the inbound traffic prediction model when the accuracy meets the first threshold; using the outbound traffic data set to train the initial outbound traffic prediction model, and obtaining the outbound traffic prediction model when the accuracy meets the second threshold.

[0012] In some embodiments of the present application, a first parameter is determined based on an inbound traffic prediction result and an outbound traffic prediction result, including: determining the ratio of the outbound traffic prediction result to the inbound traffic prediction result as the value of the first parameter; and / or, a second parameter is determined based on the outbound traffic prediction result and the service data, including: determining the ratio of the outbound traffic prediction result to the service data as the value of the second parameter, wherein the service data is used to reflect the data transmission requirements of the target service network element when processing the video stream.

[0013] According to another aspect of the embodiment of the present application, a device for determining the operating status of a video service is also provided, including: an acquisition module for collecting traffic data of a target service network element in a video service architecture and business data corresponding to the target service network element, wherein the target service network element includes at least one of the following: a media service network element, a cloud service network element, and the business data includes status data of business activities running in the target service network element; a prediction module for predicting the traffic data using a traffic prediction model to obtain a prediction result; and a determination module for determining the operating status of the target service network element based on the prediction result and the business data.

[0014] According to another aspect of the embodiments of the present application, an electronic device is provided, including: a memory and a processor, the memory being used to store program instructions; the processor being connected to the memory and being used to execute the method for determining the running status of the video service.

[0015] According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned method for determining the running status of the video service by running the computer program.

[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including computer instructions, which implement the above-mentioned method for determining the running status of the video service when executed by a processor.

[0017] In the embodiment of the present application, by collecting and analyzing traffic data and business data, combined with the traffic prediction model, it is possible to accurately judge the operating status of each service network element in the video service architecture, and detect abnormal situations in a timely manner, thereby achieving the purpose of monitoring different service network element clusters and accurately identifying the current video service operating status, thereby achieving the technical effect of improving the speed of fault discovery and accurately locating the fault section, and thus solving the technical problem that the relevant technology cannot accurately monitor the operating status of the service network elements in the GB / T 28181 protocol video service architecture. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 This is a hardware structure block diagram of a computer terminal according to a method for determining a video service running status according to an embodiment of the present application;

[0020] Figure 2 is a flow chart of a method for determining the running status of a video service according to an embodiment of the present application;

[0021] Figure 3 is a video service architecture diagram of a method for determining a video service running status according to an embodiment of the present application;

[0022] Figure 4 This is an overall flow chart of a method for determining the running status of a video service according to an embodiment of the present application;

[0023] Figure 5 This is a diagram of a media network element service health assessment model for a method for determining a video service operating status according to an embodiment of the present application;

[0024] Figure 6 This is a diagram of a cloud network element service health assessment model for a method for determining a video service operating status according to an embodiment of the present application;

[0025] Figure 7 It is a structural diagram of a device for determining the running status of a video service according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0029] GB / T 28181: A specification for the transmission, exchange, and control of public security video surveillance information. In this application, GB / T 28181 defines the communication standards for various components in the video service architecture, including signaling services, media services, and cloud services.

[0030] The Arima model (Autoregressive Integrated Moving Average Model) is a statistical model used in time series analysis for data forecasting, particularly for smoothing non-seasonal data. In this application, the Arima model is used to train a traffic forecasting model to accurately predict future traffic for media services and cloud services.

[0031] Prometheus: An open-source monitoring system and time series database that collects and stores metrics and provides data query and visualization. In this application, Prometheus can be used to collect network traffic data from the video service VM.

[0032] Network Element: In telecommunications networks, it refers to a physical or logical entity in the network, such as a router, switch, or server. In this application, network elements refer to the various components of the video service architecture, such as media services and cloud services.

[0033] The GB / T 28181 protocol video service architecture primarily includes three network elements: signaling services, media services, and cloud services. Signaling services control camera access policies, media services actually handle transcoding and streaming of accessed cameras, and cloud services upload cloud-stored files to cloud storage devices. The video service monitoring methods employed by related technologies focus on the operational status of service processes and server resource consumption. This is effective for simple service architectures, but in a complex, distributed service system like the GB / T 28181 protocol video service, focusing solely on these basic metrics is far from sufficient to fully reflect the service's true operational status. This is especially true when dealing with large volumes of service data and complex processing flows. Important performance issues may be missed, leading to an inability to promptly detect and respond to system failures.

[0034] In order to solve the above technical problems, the embodiments of the present application provide corresponding solutions, which are described in detail below.

[0035] The method for determining the running status of a video service provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG1 shows a hardware structure block diagram of a computer terminal for implementing a method for determining the running status of a video service. Figure 1 As shown, the computer terminal 10 may include one or more (illustrated by 102a, 102b, ..., 102n in the figure) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions connected via a wired and / or wireless network. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0036] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10. As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for determining the running status of a video service in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the above-mentioned method for determining the running status of a video service. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0038] The transmission module 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission module 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission module 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0039] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0040] It should be noted that, in some optional embodiments, the above Figure 1 The computer terminal shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer terminal described above.

[0041] In the above-mentioned operating environment, an embodiment of the present application provides an embodiment of a method for determining the operating status of a video service. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] Figure 2 is a flow chart of a method for determining the running status of a video service according to an embodiment of the present application, such as Figure 2 As shown, the method includes the following steps:

[0043] Step S202: Collect traffic data of the target service network element in the video service architecture and business data corresponding to the target service network element, wherein the target service network element includes at least one of the following: a media service network element and a cloud service network element, and the business data includes status data of business activities running in the target service network element.

[0044] In the above step S202, the target service network element refers to a specific component selected for monitoring in the video service architecture, such as a media service network element and a cloud service network element. The traffic data records the data traffic information input and output by the target service network element. The business data includes the status information of the business activities being carried out by the target service network element, for example, the number of cameras and bit rate in the media service network element.

[0045] The GB / T 28181 protocol video service architecture mainly includes three network elements: signaling service, media service, and cloud service. In this application:

[0046] (1) Signaling service network element: The signaling service is mainly responsible for processing and managing control signals and messages in the video surveillance system. Its core function is to control and coordinate the access authentication of cameras and the establishment and removal of video streams. For example, when a camera needs to access the video surveillance platform, it sends a registration request to the signaling server. The signaling server verifies its identity and allows it to access, thus ensuring that only authorized cameras can send video streams to the platform, improving the security of the system.

[0047] (2) Media Services: Media services are the primary processors of video data. They receive the raw video stream from the camera, perform decoding, transcoding, and compression, and then transmit the processed video stream to the client (e.g., mobile device, PC client) or to a cloud server for storage. For example, when a user watches surveillance video on a mobile phone, the media server optimizes the video stream to suit the phone's playback capabilities and network conditions.

[0048] (3) Cloud services: Cloud services focus on cloud storage and management of video data. They receive processed video streams from media servers, cut these video streams into cloud storage files, and upload them to cloud storage services or other cloud storage platforms for long-term preservation and subsequent retrieval. For example, when video surveillance captures an important event, the cloud service can automatically slice the video of the relevant time period and upload it to the cloud. This way, even if the local server fails, the data can be restored from the cloud, ensuring the security of the video data.

[0049] In some embodiments of the present application, the Prometheus monitoring tool can be used to continuously monitor the network interface of the target service network element (media service network element or cloud service network element) in the video service architecture, and collect inbound and outbound traffic data. For example, based on the Prometheus pull mechanism, traffic indicators are obtained from the target service network element according to a preset period.

[0050] To overcome the limitations of relying solely on system logs and resource usage for monitoring and provide more direct service quality feedback, a business data collection module for video services can be developed to collect business activity status data (i.e., business data) running in the target service network element, such as the number and bit rate of cameras in the media service network element, and file upload delay in the cloud service network element.

[0051] Traffic data collection may encounter data noise or outliers, which may affect the accuracy of the prediction model. To address this issue, feature engineering can be used to extract key indicators from traffic data before modeling, such as traffic peaks, average traffic, and traffic fluctuations. These features can better reflect the periodicity and patterns of the business and reduce the impact of noise on the model.

[0052] It should be noted that, considering that network traffic may be affected by sudden events (such as large-scale video conferencing), dynamic thresholds can be set for the prediction model. This means automatically adjusting the anomaly detection threshold based on historical traffic data, making the model more robust and adaptable. Specifically, statistical features that help identify normal and abnormal traffic, such as traffic peaks, average traffic, and traffic fluctuations, are extracted from historical traffic data. Anomaly detection algorithms suitable for dynamic thresholds, such as statistical-based methods, are selected. Statistical features of historical data (such as the mean and median) are used as the baseline or normal range for traffic. The initial anomaly detection threshold is based on the standard deviation or interquartile range (IQR) of the baseline traffic plus a certain multiple. During model operation, the threshold is updated using the latest data within a rolling window (such as the data from the past week) to ensure that the threshold reflects recent traffic behavior and adapts to traffic changes caused by sudden events. The new dynamic threshold is used to detect anomalies in real-time monitored traffic data. Based on the effectiveness of anomaly detection, the threshold generation parameters and other parameters that may affect model performance are adjusted.

[0053] Step S204: Use the traffic prediction model to predict the traffic data and obtain a prediction result.

[0054] In step S204, the traffic prediction model is a statistical or machine learning model developed based on historical traffic data to predict future traffic. In this application, traffic prediction can be achieved using the Arima model to foresee traffic trends within a service network element, thereby providing early warning of potential network or service anomalies. The prediction result is an estimated value of future traffic output by the traffic prediction model, which is used to assess the operational status and future behavior of the service network element.

[0055] The Arima model (autoregressive sum moving average model) is a time series forecasting model that uses three main components: autoregression, differencing, and moving average to model and predict traffic data.

[0056] Due to the mixed indication problem that may be caused by simultaneously predicting inbound and outbound traffic, in order to make the model focus on traffic in a single direction and improve the prediction accuracy, the traffic prediction model may include an inbound traffic prediction model and an outbound traffic prediction model. In some embodiments of the present application, the traffic prediction model is trained in the following manner: obtaining historical traffic data of the target service network element, and splitting the historical traffic data into an inbound traffic data set and an outbound traffic data set; using the inbound traffic data set to train the initial inbound traffic prediction model, and obtaining the inbound traffic prediction model when the accuracy meets the first threshold; using the outbound traffic data set to train the initial outbound traffic prediction model, and obtaining the outbound traffic prediction model when the accuracy meets the second threshold.

[0057] The inbound traffic prediction model predicts the traffic arriving at the target service NE within a certain period of time based on the historical data of the inbound traffic of the target service NE. It is used to help understand the input pressure of the service NE and prepare resources in advance to cope with high traffic input.

[0058] The outbound traffic prediction model predicts the outbound traffic from the target service NE within a certain period of time based on the historical data of the outbound traffic of the target service NE. It is used to evaluate the output capacity of the service NE and ensure that the network bandwidth and server resources can meet the expected traffic demand.

[0059] In some embodiments of the present application, the historical traffic data of the target service network element can be segmented into an inbound traffic data set and an outbound traffic data set according to the traffic direction based on the characteristics of time series data, ensuring that the segmented data sets maintain the time series characteristics of traffic changes; the inbound traffic data set is used to train the initial inbound traffic prediction model by adjusting the model parameters, such as the p, d, and q parameters of the Arima model, until the prediction accuracy of the model meets the first threshold; similarly, the outbound traffic data set is used to train the initial outbound traffic prediction model until the model prediction accuracy reaches the second threshold.

[0060] In the development and deployment of traffic prediction models, traditional threshold setting is often based on fixed-value empirical rules or simple statistical analysis. This approach may be inflexible and unable to fully reflect the dynamic characteristics and complex environment of service network element traffic. To address this problem, a dynamic threshold determination strategy based on the historical traffic data distribution of service network elements and service demand analysis can be adopted. By quantifying the traffic tolerance of service network elements and their impact on service continuity and service quality, a more refined and adaptable first threshold (for inbound traffic prediction models) and second threshold (for outbound traffic prediction models) can be defined.

[0061] Step 1: Collect and analyze historical traffic data of target service network elements (such as media service network elements and cloud service network elements) under normal operation. By drawing traffic distribution curves (such as histograms) and calculating statistical indicators (mean, standard deviation, percentiles, etc.), understand the normal range and extreme cases of traffic data.

[0062] Step 2: Based on the traffic distribution curve and statistical indicators, identify the abnormal threshold of the traffic data, that is, the traffic change that exceeds the normal range. For example, it can be set based on the standard deviation or percentile.

[0063] Step 3: Based on abnormal thresholds and business activity data, analyze the impact of abnormal traffic on business activities such as live video streaming, real-time recording, and file uploads. By establishing a business impact model, quantify the potential decline in service quality and user experience associated with traffic fluctuations.

[0064] Step 4: Based on the output of the service impact model, analyze the maximum service interruption time and frequency that the service network element can withstand under different traffic conditions, as well as the minimum resource adjustment required for recovery, to determine the minimum accuracy requirement that the traffic prediction model must achieve.

[0065] Step 5: According to the minimum accuracy requirement determined in step 4, set a first threshold (for the inbound traffic prediction model) and a second threshold (for the outbound traffic prediction model).

[0066] Step S206: Determine the operating status of the target service network element based on the prediction result and the service data.

[0067] In step S206, the traffic forecast results can be compared with real-time service data to check whether the service data matches the forecast results or whether there are unexpected large fluctuations. For example, the consistency between the forecasted and measured values can be evaluated by calculating the difference or correlation coefficient between the two. By combining the forecast results with service data, potential operational anomalies can be identified before actual traffic changes occur, thereby improving the system's response speed and troubleshooting capabilities.

[0068] It should be noted that in addition to the data output by the traffic prediction model and business data, data from multiple other sources, such as network logs and server performance indicators, can also be integrated to provide a more comprehensive perspective on the operating status.

[0069] In some embodiments of the present application, the prediction results include the inbound traffic prediction results and the outbound traffic prediction results of the target service network element, and the operating status of the target service network element can be determined by the following steps: determining a first parameter based on the inbound traffic prediction results and the outbound traffic prediction results, wherein the first parameter is used to reflect the degree of equivalence between the inbound traffic and the outbound traffic in the target service network element; determining a second parameter based on the outbound traffic prediction results and the business data, wherein the second parameter is used to reflect the difference between the predicted value and the actual demand value of the outbound traffic in the target service network element; and determining the operating status based on the first parameter and the second parameter.

[0070] The inbound traffic prediction result is generated by the inbound traffic prediction model and is the traffic data expected to arrive at the target service network element. The outbound traffic prediction result is generated by the outbound traffic prediction model and is the traffic data expected to be sent out from the target service network element.

[0071] The first parameter reflects the degree of parity between inbound and outbound traffic and is used to assess the traffic balance of a service network element. Due to the limitations of relying on unidirectional traffic data, which cannot fully assess the traffic processing capabilities of a service network element, this application examines the parity of bidirectional traffic to more accurately understand the traffic management status of the service network element and promptly identify potential network congestion or imbalanced resource allocation.

[0072] It's important to note that in the context of video service monitoring, parity primarily refers to the balance between inbound and outbound traffic at the target service NE. Inbound traffic refers to the amount of data flowing into the service NE, while outbound traffic refers to the amount of data flowing out of the service NE. Ideally, inbound and outbound traffic should remain relatively stable and well-matched to ensure the service NE can efficiently process video streams and avoid wasted resources or network congestion.

[0073] The second parameter reflects the difference between the predicted outbound traffic and the actual service demand. It is used to evaluate the service network element's output capacity and service adaptability. To avoid over- or under-allocation of resources due to inaccurate predictions, the second parameter measures the accuracy of the prediction model and the service network element's traffic output capacity to handle service demands.

[0074] In some embodiments of the present application, the first parameter may be the ratio of the outgoing traffic prediction result to the incoming traffic prediction result, and the second parameter may be the ratio of the outgoing traffic prediction result to the service data, wherein the service data is used to reflect the data transmission requirements of the target service network element when processing the video stream.

[0075] The business data may include the operating parameters of the target camera in the target service network element used to provide traffic data. In this case, the second parameter can be determined by the following steps: obtaining the number of target cameras and the bit rate of each target camera; determining the average bit rate of the cameras corresponding to the number and bit rate, wherein the average bit rate and number of cameras are used to determine the data transmission requirements of the target service network element when processing video streams; and determining the second parameter based on the outbound traffic prediction results and the average bit rate of the cameras.

[0076] Specifically, through the video service business acquisition module, the number of active cameras in the current service network element and the real-time bit rate of each camera are obtained and recorded in real time. The statistical averaging method is used to calculate the average bit rate of all target cameras. Based on the outbound traffic prediction results and the average bit rate of the cameras, combined with the number of cameras, the second parameter is calculated.

[0077] By combining the first parameter and the second parameter, the operating status of the target service network element can be determined by setting a threshold or establishing a comprehensive evaluation model. For example, if the first parameter deviates from the normal range (such as the incoming traffic is significantly greater than the outgoing traffic), or the second parameter exceeds the allowable error limit, it may indicate that the service network element is in an abnormal or high-risk state.

[0078] It should be noted that in addition to the first parameter and the second parameter, other indicators can also be combined to determine the operating status of the target service network element, such as the server's CPU and memory usage, network delay, packet loss rate, etc., to obtain a more comprehensive evaluation of the service network element's operating status.

[0079] Determining the operating status based on the first parameter and the second parameter includes: determining the health of the target service network element based on the first parameter and the second parameter, wherein the health is used to quantitatively represent the traffic balance of the target service network element; when the health meets the preset conditions, determining that the operating status of the target service network element is an abnormal state.

[0080] Health is a quantitative indicator used to comprehensively evaluate the traffic balance and business processing capabilities of the target service network element, where traffic balance refers to the degree of balance between incoming traffic and outgoing traffic. Good traffic balance means that the service network element can effectively process input and output traffic to avoid network congestion or waste of resources. In some embodiments of the present application, the health value is calculated through a comprehensive evaluation algorithm in combination with a first parameter (reflecting the degree of parity between incoming and outgoing traffic) and a second parameter (reflecting the difference between predicted traffic and business data requirements). For example, in the comprehensive evaluation algorithm, a first adjustment coefficient and a second adjustment coefficient are introduced to adjust the weights of the first parameter and the second parameter in the health calculation. This is because the balance of traffic processing and the satisfaction of business needs may have different degrees of influence on the overall health of the service. The adjustment coefficient can more accurately reflect the operating status of the service network element.

[0081] The first adjustment coefficient and the second adjustment coefficient can be determined according to the business scenario requirements of the target service network element. For example, in some cases, such as during large-scale real-time video stream processing, traffic parity is the key to ensuring service quality, and the first adjustment coefficient can be determined to be greater than the second adjustment coefficient.

[0082] Preset conditions refer to thresholds or standards used to determine whether health meets normal operation requirements.

[0083] In some embodiments of the present application, the operating status of different service network elements can be monitored simultaneously, specifically: first traffic data and first business data of the media service network element are obtained, and a first prediction result corresponding to the media service network element is determined; second traffic data and second business data of the cloud service network element are obtained, and a second prediction result corresponding to the cloud service network element is determined, wherein the cloud service network element is located in the video stream outlet direction of the media service network element; the operating status of the video service architecture is determined based on the first business data, the first prediction result, the second business data, and the second prediction result.

[0084] The determination of the first / second traffic data, the first / second service data and the first / second prediction results can refer to the specific solutions in the above embodiments, which will not be repeated here.

[0085] The operating status of the video service architecture is determined based on the first business data, the first prediction result and the second business data, the second prediction result. Specifically: when the operating status of the media service network element is determined to be normal based on the first business data and the first prediction result, the operating status of the cloud service network element is determined based on the second business data and the second prediction result; when the operating status of the cloud service network element is normal, the operating status of the video service architecture is determined to be normal.

[0086] In the video service architecture, the media service network element (NE) serves as the "transfer station" for video streams. It receives video data from cameras, performs preliminary processing such as transcoding, and then transmits the data to the cloud service NE for cloud storage. Because of its central position in the video stream path, the normal operation of the media service is the cornerstone of the stability of the video service architecture. Problems with the media service not only affect the reception and processing of video data, but also prevent subsequent cloud services from receiving data properly, thus affecting the continuity and quality of the entire video service.

[0087] The operational status of cloud services, including the processing speed and storage efficiency of cloud-stored data, depends on the media service providing video data accurately and promptly. Therefore, evaluating cloud services is meaningful only after confirming that the media service is operating normally, as abnormal media service status may directly lead to chain reactions of abnormalities in cloud services.

[0088] It should be noted that in addition to monitoring media service network elements and cloud service network elements, any network element in the architecture can also be monitored. The evaluation can start from the traffic entry end of the architecture (media service), that is, to determine the dependency relationship between the service network elements in the architecture. For example, it can be determined by the flow direction of video data, and the operating status of multiple service network elements can be determined in turn based on the dependency relationship.

[0089] Through the above steps S202 to S206, by collecting and analyzing traffic data and business data, combined with the traffic prediction model, it is possible to accurately judge the operating status of each service network element in the video service architecture, and timely discover abnormal situations, thereby achieving the purpose of monitoring different service network element clusters and accurately identifying the current video service operating status, thereby achieving the technical effect of improving the fault discovery speed and accurately locating the fault section, and thus solving the technical problem that related technologies cannot accurately monitor the operating status of service network elements in the GB / T28181 protocol video service architecture.

[0090] Figure 3 FIG. 1 is a diagram of a video service architecture according to a method for determining a video service running state according to an embodiment of the present application. Figure 3 Shown, including:

[0091] Camera 302: Camera 302 is the source of video data, typically installed at a surveillance location to record live images or video. It communicates with other components of the video service using the GB / T 28181 protocol, sending real-time video stream data. Camera 302 first connects to signaling server 304 for registration. Once registration is successful, it begins sending video stream data to media server 306.

[0092] Signaling Server 304: Signaling Server 304 is primarily responsible for access management and registration of camera 302. It authenticates cameras according to the GB / T28181 protocol, ensuring that only authorized devices can access the video service system. Signaling Server 304 establishes a connection with camera 302 and processes its registration request. It also connects to Media Server 306, transmitting the camera's registration information so that the media server can prepare to receive the video stream based on the signaling information.

[0093] Media Server 306: As the primary processing node for video streams, media server 306 receives video data streams from camera 302 and performs tasks such as video encoding and transcoding to adapt the video streams to the playback requirements of different terminals. It also monitors and predicts traffic flow to ensure the proper allocation of resources and the smooth transmission of video streams. Media server 306 receives the video stream from camera 302 and also receives camera registration information from signaling server 304. The processed video streams are then sent to client 310 and cloud server 308.

[0094] Cloud Upload Server 308: Cloud Upload Server 308 uploads video clips processed by Media Server 306 to Cloud Storage 312 for long-term storage. Cloud Upload Server 308 performs operations such as video slicing, compression, and encryption to optimize storage space and ensure data security. Cloud Upload Server 308 receives video stream data from Media Server 306 and uploads it to Cloud Storage 312. Cloud Upload Server 308 also maintains communication with Client 310 and Media Server 306 to obtain real-time service data and traffic forecasts, ensuring a smooth upload process and efficient resource utilization.

[0095] Client 310: Client 310 is the user interface for accessing video services. It can be a computer, mobile phone, or any other terminal. The client receives video streams from media server 306 via video streaming protocols (such as RTSP and HLS), enabling functions such as video playback and live viewing. Client 310 directly connects to media server 306 to obtain video streams in real time. It can also indirectly access video files stored in cloud storage device 312 through cloud servers to provide on-demand services.

[0096] Cloud storage device 312: Cloud storage device 312 is responsible for long-term storage of video files. It utilizes a high-availability and redundant design to ensure data security and persistence. It supports multiple storage formats and protocols, facilitating data upload and retrieval from cloud server 308. Cloud storage device 312's primary data source is cloud server 308, receiving and storing video files. It also maintains certain interactions with cloud server 308 and client 310 for data retrieval and backup management.

[0097] To facilitate understanding of the specific implementation of the above embodiments, an explanation is provided below in conjunction with a specific embodiment. It should be noted that the relevant explanations involved in this embodiment are applicable to the above method for determining the running status of a video service.

[0098] The technical solution involved in this embodiment is mainly divided into six steps. The first is to collect the traffic of the video service virtual machine based on the Promethus traffic collection module; the second is to collect the current service in-use business data based on the video service business collection module; the third is to train the media service Arima traffic prediction model and the cloud service Arima traffic prediction model respectively; the fourth is to perform traffic prediction based on the trained media service Arima traffic prediction model and the cloud service Arima traffic prediction model; the fifth is to build a media network element service health assessment model based on the inbound and outbound traffic and business data of the media service network element, and detect the media service status; the sixth is to build a cloud network element service health assessment model based on the inbound and outbound traffic and business data of the cloud service network element, and detect the cloud service status.

[0099] (1) Based on the Promethus traffic collection module described in the first part, the video service virtual machine traffic is collected. The specific steps are as follows: install Prometheus on the server used by the video service; edit the Prometheus configuration file to collect the inbound and outbound traffic of the network element network cards of the media service and the cloud service; and output the collected traffic data through the interface.

[0100] (2) The video service business acquisition module described in the second part collects the business data of the current service. The specific operation steps are as follows:

[0101] Collect the number of cameras in use for media services. The cameras in use include those watching live broadcasts, real-time recording of cloud-stored videos, and other situations involving pulling streams. This number is denoted as N M ; Calculate the average bitrate of cameras in use in media services The calculation formula is as follows:

[0102]

[0103] in, Represents the camera bit rate used by the media service, i∈[1, N M ];

[0104] The number of online cameras that record and store videos in the cloud in real time, denoted as N C ; Calculate the average bit rate of cameras in use on the cloud service The calculation formula is as follows:

[0105]

[0106] in, Represents the camera bit rate used by the cloud service, j∈[1, N C ];

[0107] The above video service business data is output through the interface.

[0108] (3) The specific steps for training the media service Arima traffic prediction model and the cloud service Arima traffic prediction model described in the third part are as follows: Based on the media / cloud service inbound and outbound traffic collected in the first part, perform data cleaning to create a media inbound traffic dataset, a media outbound traffic dataset, a cloud service inbound traffic dataset, and a cloud service outbound traffic dataset. Use the labeled data to train the model and test it with the test set. If the accuracy rate reaches 80% or above, the parameter adjustment and training of the media service Arima inbound traffic prediction model, the media service Arima outbound traffic prediction model, the cloud service Arima inbound traffic prediction model, and the cloud service Arima outbound traffic prediction model are completed. If it does not reach the target, return to the first part and continue to collect data sets to re-adjust parameters and train until the accuracy rate reaches the target.

[0109] (4) Traffic prediction is performed based on the trained media service Arima traffic prediction model and cloud service Arima traffic prediction model described in Section 4. The specific steps are as follows:

[0110] Based on the trained media service Arima inbound traffic prediction model, the media service inbound traffic is predicted, and the traffic prediction result is recorded as T M_in Based on the trained media service Arima outbound traffic prediction model, the outbound traffic of the media service is predicted, and the traffic prediction result is recorded as T M_out ;

[0111] Based on the trained Arima inbound traffic prediction model for cloud services, the inbound traffic of cloud services is predicted, and the traffic prediction result is recorded as T C_in Based on the trained Arima inbound traffic prediction model for cloud services, the outbound traffic of cloud services is predicted, and the traffic prediction result is recorded as T C_out .

[0112] (5) The media network element service health assessment model described in Section 5 detects the media service status. The specific steps are as follows:

[0113] According to the media service inbound and outbound traffic prediction data obtained in Section 4, in general, due to the best-effort nature of the UDP protocol, the media service inbound traffic is greater than the media service outbound traffic. Based on this characteristic, the degree of parity between the media service inbound and outbound traffic is defined. The calculation is as follows:

[0114]

[0115] in, is the first parameter corresponding to the media service network element.

[0116] Based on the media service business data obtained in Part 2 and Part 4 and the outbound traffic forecast data, calculate the media service outbound traffic difference γ M , the calculation formula is as follows:

[0117]

[0118] Among them, γ M is the second parameter corresponding to the media service network element.

[0119] Based on the parity of inbound and outbound traffic of media services Difference between outbound traffic of media service and γ M , calculate the media network element service health H M , the calculation formula is as follows:

[0120]

[0121] Among them, H M is health, if H M <0.5, the media service is judged to be abnormal.

[0122] (6) The cloud-based network element service health assessment model described in Section 6 detects the cloud-based service status. The specific steps are as follows:

[0123] According to the cloud service inbound and outbound traffic forecast data obtained in the fourth part, in general, due to the service bandwidth limitation, there is a certain delay in uploading cloud storage slice files. Specifically, the inbound traffic of the cloud service is greater than the outbound traffic of the cloud service. Based on this characteristic, the degree of parity of the inbound and outbound traffic of the cloud service is defined. The calculation is as follows:

[0124]

[0125] in, It is the first parameter corresponding to the cloud service network element.

[0126] Based on the cloud service business data and inbound and outbound traffic forecast data obtained in Part 2 and Part 4, calculate the difference in outbound traffic of cloud services γ C , the calculation formula is as follows:

[0127]

[0128] Among them, γ CIt is the second parameter corresponding to the cloud service network element.

[0129] According to the degree of parity of inbound and outbound traffic of cloud services Difference in outbound traffic from cloud services γ C , calculate the health of cloud network element services H C , the calculation formula is as follows:

[0130]

[0131] Among them, H M is health, if H C If the value is less than 0.5, the cloud service is considered abnormal.

[0132] Figure 4 This is an overall flow chart of a method for determining the running status of a video service according to an embodiment of the present application. Figure 4 As shown, the following steps are included:

[0133] Step S402: Start the Prometheus traffic collection module. Deploy the Prometheus monitoring system in the server environment of the video service architecture and use its traffic collection module to monitor network traffic data for media services and cloud services. This includes both inbound and outbound traffic, which serves as the basis for subsequent traffic prediction and health assessment.

[0134] Step S404: Start the video service traffic collection module. This specially designed traffic collection module monitors the traffic load of media services and cloud services in real time. For example, for media services, this includes information such as the number of cameras in use and the average bitrate. For cloud services, this includes information such as the number of cameras recording online videos to cloud storage and the average bitrate, providing a comprehensive understanding of the real-time traffic status of the services.

[0135] Step S406a: Obtain inbound and outbound traffic of the media service. The Prometheus traffic collection module regularly collects and provides inbound traffic (i.e., traffic received from the camera) and outbound traffic (i.e., traffic sent to the client and cloud server) of the media service to ensure data continuity and integrity.

[0136] Step S408a: Acquire media service business data. The video service business acquisition module synchronously collects the media service business data in use, including but not limited to key information such as the number of cameras and average bit rate, to provide reference for subsequent evaluation.

[0137] Step S410a: The media service Arima traffic prediction model performs traffic prediction. Using the pre-trained Arima traffic prediction model, based on the collected historical traffic data, the future inbound and outbound traffic trends of the media service are predicted to prepare for resource allocation and optimization in advance.

[0138] Step S412a: The media network element service health assessment model performs an assessment. Based on traffic forecast results and real-time service data, the assessment model measures the parity of inbound and outbound traffic and the difference in outbound traffic of the media service network element. Combining these two indicators, the model calculates the health score of the media network element service.

[0139] Step S414a: Determine whether the media NE service health score is less than 0.5. Compare the health score calculated in step S412a with the preset threshold of 0.5 to determine whether the media service NE is operating normally. If the score is less than 0.5, an abnormality is present. If it is greater than or equal to 0.5, proceed to the next step to evaluate the operating status of the cloud service NE.

[0140] Step S416a: Determine if the media service network element service is abnormal. When the health score of the media service network element is lower than 0.5, the system will trigger an abnormality warning and may initiate automatic or manual troubleshooting and resource adjustment processes to restore normal service as soon as possible.

[0141] Step S406b: Obtaining the inbound and outbound traffic of the cloud service. After the media service is evaluated as normal, the Prometheus traffic collection module continues to run, collecting the inbound and outbound traffic data of the cloud service, in preparation for traffic prediction and health assessment of the cloud service.

[0142] Step S408b: Obtaining cloud service business data. The video service business collection module collects real-time business data of cloud services, such as the number of cameras recording online videos and the average bit rate, to provide a basis for health assessment of cloud services.

[0143] Step S410b: Perform traffic forecasting using the Arima traffic forecasting model of the cloud service. Using the Arima traffic forecasting model of the cloud service, future traffic trends are predicted based on historical traffic data, helping the system respond in advance and avoid performance bottlenecks caused by sudden traffic increases.

[0144] Step S412b: The cloud-based NE service health assessment model is used to evaluate the service. Based on the traffic forecast results and real-time service data of the cloud-based service, the assessment model calculates the parity of inbound and outbound traffic and the difference in outbound traffic, and derives a health score for the cloud-based NE to monitor its operational status.

[0145] Step S414b: Determine whether the cloud-based NE service health score is less than 0.5. Compare the cloud-based NE health score with a preset threshold of 0.5 to determine whether its operating status is normal. If the score is less than 0.5, it indicates an anomaly in the cloud-based service. If it is greater than or equal to 0.5, the overall video service architecture is considered to be operating normally.

[0146] Step S416b: Determine if the cloud-based NE service is abnormal. When the health score of the cloud-based NE falls below 0.5, the system will mark it as abnormal and may take measures, such as increasing storage resources and optimizing data transmission paths, to improve the efficiency and stability of the cloud-based service.

[0147] Step S418: Determine that the service is normal. If the health scores of the media service and the cloud service are both greater than or equal to 0.5, the system ultimately determines that the operation status of the entire video service architecture is normal, indicating that traffic processing and business needs are stable and efficient.

[0148] Figure 5 This is a media network element service health evaluation model diagram of a method for determining the running status of a video service according to an embodiment of the present application, such as Figure 5 As shown, the execution of the media network element service health assessment model includes the following steps:

[0149] Step S502: Obtain the predicted inbound traffic of the media service.

[0150] Using the pre-trained Arima traffic prediction model for media services, we predict incoming traffic for media services over the next period of time based on the trends and periodicity of historical traffic data. This prediction takes into account various factors that may affect traffic, such as time period and specific events, to improve prediction accuracy.

[0151] Step S504: Obtain the predicted outbound traffic of the media service.

[0152] Similarly, using the same or corresponding Arima traffic prediction model, we can predict the outbound traffic that the media service will send to the outside world (clients and cloud servers) in the future. This prediction also needs to take into account the periodic changes in the service and the impact of possible external events, such as traffic growth during peak hours.

[0153] Step S506: Acquire media service business data.

[0154] The video service business collection module collects real-time information about the current business load of the media service, including but not limited to the number of cameras in use and the average bit rate of cameras in use, to reflect the actual business pressure and resource usage of the media service.

[0155] Step S508: Determine the parity of inbound and outbound traffic of the media service according to S502 and S504.

[0156] Compare the predicted inbound traffic in step S502 with the predicted outbound traffic in step S504 and calculate the ratio between the two. Since inbound traffic is usually slightly larger than outbound traffic (taking into account data processing and conversion losses) when the media service processes video streams, this ratio can reflect the traffic processing balance and efficiency of the media service network element.

[0157] Step S510: Determine the difference in outbound traffic of the media service according to S506 and S504.

[0158] After obtaining media service business data (such as the number of cameras and average bit rate), it is compared with the predicted outbound traffic to evaluate the match between actual business needs and predicted outbound traffic, so as to identify whether there is sufficient outbound traffic capacity to cope with the current business load and prevent overload or resource waste.

[0159] Step S512: Determine the health of the media service network element according to S508 and S510.

[0160] Combined with the degree of parity of inbound and outbound traffic obtained in step S508 and the degree of difference in outbound traffic obtained in step S510, a health score of the media service network element is determined through comprehensive calculation and analysis. The health score reflects the overall operating status of the media service network element, including the rationality of resource allocation and the matching degree of traffic processing capacity with business needs.

[0161] Figure 6 This is a diagram of a cloud network element service health assessment model for a method for determining the running status of a video service according to an embodiment of the present application, such as Figure 6 As shown, the execution of the network element service health evaluation model includes steps S602 to S612, and the specific implementation of each step is as follows: Figure 5 The execution steps shown are similar, please refer to Figure 5 The explanation of each step is omitted here.

[0162] Figure 7 is a structural diagram of a device for determining the running status of a video service according to an embodiment of the present application, such as Figure 7 As shown, the device includes:

[0163] A collection module 702 is configured to collect traffic data of a target service network element in the video service architecture and service data corresponding to the target service network element, wherein the target service network element includes at least one of the following: a media service network element and a cloud service network element, and the service data includes status data of service activities running in the target service network element;

[0164] The prediction module 704 is used to predict the traffic data using the traffic prediction model to obtain a prediction result;

[0165] The determination module 706 is configured to determine the operating status of the target service network element based on the prediction result and the service data.

[0166] It should be noted that Figure 7 The apparatus for determining the running state of the video service is used to execute Figure 2 The method for determining the running status of the video service shown, therefore Figure 2 The explanations in the video service operation status determination method also apply to Figure 7 The apparatus for determining the running status of the video service shown will not be described in detail here.

[0167] An embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory and is used to execute the steps of the method for determining the running status of the video service in each embodiment of the present application.

[0168] For example, the processor performs the following functions by executing program instructions stored in the memory: collecting traffic data of the target service network element in the video service architecture and business data corresponding to the target service network element, wherein the target service network element includes at least one of the following: media service network element, cloud service network element, and the business data includes the status data of business activities running in the target service network element; using a traffic prediction model to predict the traffic data to obtain a prediction result; determining the operating status of the target service network element based on the prediction result and the business data.

[0169] An embodiment of the present application further provides a non-volatile storage medium, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the steps of the method for determining the running status of the video service in each embodiment of the present application by running the computer program.

[0170] An embodiment of the present application further provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the method for determining the running status of a video service in each embodiment of the present application.

[0171] The embodiments of the present application further provide a computer program, which, when executed by a processor, implements the steps of the method for determining the running status of a video service in each embodiment of the present application.

[0172] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0173] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0174] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0175] The units described as separate components may or may not be physically separate, and 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0176] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0177] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0178] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining the running status of a video service, characterized in that: include: Collecting traffic data of a target service network element in a video service architecture and service data corresponding to the target service network element, wherein the target service network element includes at least one of the following: a media service network element and a cloud service network element, and the service data includes status data of service activities running in the target service network element; Using a traffic prediction model to predict the traffic data to obtain a prediction result; The operating status of the target service network element is determined based on the prediction result and the service data.

2. The method according to claim 1, characterized in that The prediction result includes an inbound traffic prediction result and an outbound traffic prediction result of the target service network element; and determining an operating state of the target service network element based on the prediction result and the service data includes: Determining a first parameter based on the inbound traffic prediction result and the outbound traffic prediction result, wherein the first parameter is used to reflect the degree of parity between the inbound traffic and the outbound traffic in the target serving network element; Determining a second parameter based on the outbound traffic prediction result and the service data, wherein the second parameter is used to reflect the difference between the predicted value and the actual demand value of the outbound traffic in the target service network element; The operating state is determined according to the first parameter and the second parameter.

3. The method according to claim 2, characterized in that The service data includes operating parameters of a target camera in the target service network element for providing the traffic data; and determining a second parameter based on the outbound traffic prediction result and the service data includes: Obtain the number of target cameras and the bit rate of each target camera; Determining an average bit rate of the cameras corresponding to the number and the bit rate, wherein the average bit rate of the cameras and the number are used to determine a data transmission requirement of the target service network element when processing the video stream; The second parameter is determined according to the outbound traffic prediction result and the average bit rate of the camera.

4. The method according to claim 2, characterized in that Determining the operating state according to the first parameter and the second parameter includes: Determining a healthiness of the target service network element based on the first parameter and the second parameter, wherein the healthiness is used to quantitatively represent traffic balance of the target service network element; When the health level meets a preset condition, it is determined that the operating state of the target service network element is an abnormal state.

5. The method according to claim 1, wherein The method further comprises: Obtaining first traffic data and first service data of the media service network element, and determining a first prediction result corresponding to the media service network element; Obtaining second traffic data and second service data of the cloud service network element, and determining a second prediction result corresponding to the cloud service network element, wherein the cloud service network element is located in the video stream egress direction of the media service network element; The operating state of the video service architecture is determined based on the first business data and the first prediction result and the second business data and the second prediction result.

6. The method according to claim 5, characterized in that Determining an operating state of the video service architecture according to the first service data, the first prediction result, and the second service data, the second prediction result includes: When it is determined that the operating state of the media service network element is normal according to the first service data and the first prediction result, the operating state of the cloud service network element is determined according to the second service data and the second prediction result; When the operation status of the cloud service network element is normal, it is determined that the operation status of the video service architecture is normal.

7. The method according to claim 1, characterized in that The traffic prediction model includes an inbound traffic prediction model and an outbound traffic prediction model, and the traffic prediction model is trained in the following manner: Acquire historical traffic data of the target service network element, and split the historical traffic data into an inbound traffic data set and an outbound traffic data set; Training an initial inbound traffic prediction model using the inbound traffic data set, and obtaining the inbound traffic prediction model when an accuracy rate satisfies a first threshold; The outbound traffic data set is used to train an initial outbound traffic prediction model, and when the accuracy rate meets a second threshold, the outbound traffic prediction model is obtained.

8. The method according to claim 2, characterized in that Determining a first parameter according to the inbound traffic prediction result and the outbound traffic prediction result includes: determining the ratio of the outbound flow prediction result to the inbound flow prediction result as the value of the first parameter; and / or, Determining a second parameter based on the outbound traffic prediction result and the business data, including: determining the ratio of the outbound traffic prediction result to the business data as the value of the second parameter, wherein the business data is used to reflect the data transmission requirements of the target service network element when processing the video stream.

9. A device for determining the running status of a video service, characterized in that: include: A collection module, configured to collect traffic data of a target service network element in a video service architecture and service data corresponding to the target service network element, wherein the target service network element includes at least one of the following: a media service network element and a cloud service network element, and the service data includes status data of service activities running in the target service network element; A prediction module, configured to predict the flow data using a flow prediction model to obtain a prediction result; A determination module is used to determine the operating status of the target service network element based on the prediction result and the business data.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory and is used to execute the method for determining the running status of the video service according to any one of claims 1 to 8.

11. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the method for determining the running status of a video service according to any one of claims 1 to 8 by running the computer program.

12. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the method for determining the running status of a video service according to any one of claims 1 to 8 is implemented.

Images