Method and device for determining operation state of network

Abstract

The invention discloses a method and device for determining the running state of a network. The method comprises the following steps: acquiring historical performance data of a target network in a detection period, the target network being a network running a netmeeting process, and the detection period being a time period when the target network runs the netmeeting process; a linear dependency relationship of the multiple pieces of historical performance data is determined, an objective function is constructed according to the linear dependency relationship, the objective function is used for describing dynamic characteristics of the historical performance data, and the dynamic characteristics are used for indicating a time-varying rule of the historical performance data; actual performance data of the target network at the current moment are obtained, the operation state of the target network at the current moment is determined according to the actual performance data and the target function, and the operation state comprises normal operation and abnormal operation. According to the invention, the technical problem of low detection result accuracy of a method for detecting whether a network conference has a fault in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for determining the operating status of a network. Background Art

[0002] In the information age, the Internet has become an important way for people to obtain information. Network failures can cause users to be unable to access the Internet or internal network resources, making it difficult to obtain the required information and knowledge. In addition, network failures can reduce the work efficiency of users. Due to the inability to access emails, shared files or online collaboration tools normally, users may not be able to complete their work tasks in time, thus affecting the overall work progress. Especially when conducting online meetings, if the network fails, it will have a huge impact on the overall work process. Therefore, when a network failure occurs in an online meeting, it is necessary to be able to discover the failure so that it can be repaired in time to ensure that the meeting can continue in the shortest time. In the related art, whether a network failure occurs is determined by detecting the survival time value of the encapsulated packet. However, if the survival time value of the encapsulated packet does not decrease as expected, it only means that there is a possibility of a network failure, and it cannot be determined that it is definitely caused by a network failure. In addition, the noise of normal network operation is relatively high, and occasional data packet loss or delay may be mistakenly regarded as a failure. Therefore, when using this method to detect the status of the online meeting, there is a low accuracy rate of the detection result, which further leads to the inability to repair the failure of the online meeting in time.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method and device for determining the operating status of a network, so as to at least solve the technical problem of low accuracy of detection results of methods for detecting whether a network conference is faulty in related technologies.

[0005] According to one aspect of an embodiment of the present application, a method for determining the operating status of a network is provided, including: obtaining historical performance data of a target network within a detection period, wherein the target network is a network running a network conference process, the detection period is a time period in which the target network runs the network conference process, and the historical performance data is used to describe the network performance of the target network within the detection period; determining a linear dependency relationship among multiple historical performance data, and constructing an objective function based on the linear dependency relationship, wherein the objective function is used to describe the dynamic characteristics of the historical performance data, and the dynamic characteristics are used to indicate the law of change of the historical performance data over time; obtaining actual performance data of the target network at the current moment, and determining the operating status of the target network at the current moment based on the actual performance data and the objective function, wherein the operating status includes: normal operation and abnormal operation.

[0006] Optionally, the linear dependency includes: autocorrelation, partial autocorrelation, and determining the linear dependency of multiple historical performance data includes: determining multiple lag time intervals, wherein the lag time interval contains multiple generation moments of multiple historical performance data; for each lag time interval, determining multiple first generation moments contained in the lag time interval, and determining a first type of historical performance data whose generation moment is the first generation moment; determining the autocorrelation coefficient corresponding to each lag time interval based on the first type of historical performance data, wherein the autocorrelation coefficient is used to indicate the autocorrelation; and determining the second generation moment with the earliest indication time and the third generation moment with the latest indication time in the lag time interval; determining the second type of historical performance data with the generation moment being the second generation moment, and determining the third type of historical performance data with the generation moment being the third generation moment; determining the partial autocorrelation coefficient corresponding to each lag time interval based on the second type of historical performance data and the third type of historical performance data, wherein the partial autocorrelation coefficient is used to indicate the partial autocorrelation.

[0007] Optionally, constructing an objective function according to a linear dependency relationship includes: determining a first lag parameter value corresponding to each autocorrelation coefficient, wherein the first lag parameter value is used to indicate the number of generation moments included in the lag time interval corresponding to the autocorrelation coefficient; determining a target first lag parameter value whose corresponding autocorrelation coefficient is 0 and whose value is the smallest among multiple first lag parameter values; determining a second lag parameter value corresponding to each partial autocorrelation coefficient, wherein the second lag parameter value is used to indicate the number of generation moments included in the lag time interval corresponding to the partial autocorrelation coefficient; determining a target second lag parameter value whose corresponding partial autocorrelation coefficient is 0 and whose value is the smallest among multiple second lag parameter values; screening target historical performance data for constructing the objective function in the historical performance data according to the target first lag parameter value and the target second lag parameter value; and constructing the objective function according to the target historical performance data.

[0008] Optionally, determining the operating state of the target network at the current moment according to actual performance data and the objective function includes: determining a plurality of first prediction results according to historical performance data and the objective function, wherein the first prediction result is used to indicate the performance of the target network at the current moment; determining a first difference between the first prediction result and the actual performance data, and comparing the first difference with a reference difference to obtain a comparison result, wherein the reference difference is determined in the process of iteratively updating the objective function using historical performance data; when the comparison result indicates that the absolute value of the first difference is greater than the reference difference, determining that the operating state of the target network at the current moment is abnormal operation; when the comparison result indicates that the absolute value of the first difference is less than or equal to the reference difference, determining that the operating state of the target network at the current moment is normal operation.

[0009] Optionally, the reference difference is determined by the following method: during each iterative update, multiple second prediction results are determined based on the objective function and historical performance data, wherein the second prediction results are used to indicate the performance of the target network at historical moments, and the historical moments are multiple moments included in the detection cycle; for each historical moment, a second difference between the historical performance data corresponding to the historical moment and the second prediction result is determined; the reference difference is determined based on the multiple second differences, the number of second prediction results, and the parameters of the objective function, wherein the parameters are used to indicate the sum of the parameters of the objective function, and the parameters of the objective function include: autocorrelation coefficient and partial autocorrelation coefficient.

[0010] Optionally, the method for determining the operating status of a network also includes: when it is determined that the operating status of the target network at the current moment is abnormal operation, determining a third difference between the first difference and the reference difference, and determining an abnormality level of the target network based on the third difference, wherein the abnormality level is positively correlated with the third difference; determining a maintenance level associated with the abnormality level in a preset list, wherein the preset list is used to record the association between the abnormality level and the maintenance level; and sending a maintenance alarm to a terminal associated with the maintenance level, wherein the maintenance alarm is used to prompt a user corresponding to the terminal to perform maintenance on the target network.

[0011] Optionally, the maintenance level is determined by the following method: obtaining maintenance information associated with the terminal, wherein the maintenance information includes at least: number of maintenance times, after-sales satisfaction, and current maintenance score; determining the weight corresponding to the maintenance information, wherein the weight corresponding to the first maintenance is different from the weight corresponding to the number of repairs; and determining the maintenance level based on the maintenance information and the weight.

[0012] According to another aspect of an embodiment of the present application, a device for determining the operating status of a network is also provided, including: an acquisition module, used to obtain historical performance data of a target network within a detection period, wherein the target network is a network running a network conference process, the detection period is a time period when the target network runs the network conference process, and the historical performance data is used to describe the network performance of the target network within the detection period; a first determination module, used to determine a linear dependency of multiple historical performance data, and construct an objective function based on the linear dependency, wherein the objective function is used to describe the dynamic characteristics of the historical performance data, and the dynamic characteristics are used to indicate the law of change of the historical performance data over time; a second determination module, used to obtain actual performance data of the target network at the current moment, and determine the operating status of the target network at the current moment based on the actual performance data and the objective function, wherein the operating status includes: normal operation and abnormal operation.

[0013] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, in which a computer program is stored, wherein the method for determining the operating status of a network is executed by running the computer program on a device where the non-volatile storage medium is located.

[0014] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned method for determining the operating status of a network through the computer program.

[0015] According to another aspect of an embodiment of the present application, a computer program product is also provided, including computer instructions, which implement the steps of the above-mentioned method for determining the operating status of a network when the computer instructions are executed by a processor.

[0016] In an embodiment of the present application, the historical performance data of the target network within a detection period is obtained, wherein the target network is a network running a network conference process, the detection period is a period of time when the target network runs the network conference process, and the historical performance data is used to describe the network performance of the target network within the detection period; a linear dependency relationship of multiple historical performance data is determined, and an objective function is constructed according to the linear dependency relationship, wherein the objective function is used to describe the dynamic characteristics of the historical performance data, and the dynamic characteristics are used to indicate the law of change of the historical performance data over time; the actual performance data of the target network at the current moment is obtained, and the operating state of the target network at the current moment is determined according to the actual performance data and the objective function, wherein the operating state includes: normal operation and abnormal operation. The historical performance data of the network supporting the network conference is comprehensively analyzed to determine the dynamic characteristics of the network (i.e., the relationship between network performance and time), and the actual performance data of the network used for the current network conference is analyzed based on the dynamic characteristics of the network to determine whether the network is operating normally. The historical performance data of the network is combined to achieve the purpose of improving the accuracy of the judgment of the network state, thereby achieving the technical effect of timely and accurate identification of network faults, effectively avoiding conference interruptions, and thus solving the technical problem of low accuracy of detection results of the method for detecting whether a network conference is faulty in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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:

[0018] Figure 1 is a hardware structure block diagram of a computer terminal for implementing a method for determining an operating status of a network according to an embodiment of the present application;

[0019] Figure 2is a flow chart of a method for determining an operating status of a network according to an embodiment of the present application;

[0020] Figure 3 It is a structural diagram of a device for determining the operating status of a network according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0022] 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 sequence. 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 an order 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.

[0023] 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:

[0024] Autocorrelation: The correlation between observations at different points in time in a time series.

[0025] Partial autocorrelation: The correlation between two variables after controlling for other variables.

[0026] In the related art, a method of detecting multiple encapsulated packets transmitted over the network is used to determine whether a network failure occurs. Specifically, whether a network failure occurs is determined based on the survival time value of the encapsulated packet. Under normal circumstances, the survival time value of a data packet should be decreasing, because each time it is forwarded by a router, the value will be reduced by one. If it is found that the survival time value of a packet does not decrease as expected, it may be caused by a network failure. However, the fact that the survival time value of the encapsulated packet does not decrease as expected is only a possibility of network failure, and it cannot be determined that it is definitely caused by a network failure. First, the survival time value does not decrease as expected for certain specific network paths or protocol behaviors; second, if the network is in a low-traffic environment, the number of encapsulated packets transmitted in the network itself is small, and it is impossible to collect enough data for analysis. In addition, in a traffic environment, the noise of normal network operation is relatively high. If this method is used to detect whether the network is faulty, occasional data packet loss or delay will also be mistakenly regarded as a fault; therefore, there is a problem of low accuracy in detecting network failures. In order to solve this problem, a relevant solution is provided in the embodiment of the present application, which is described in detail below.

[0027] According to an embodiment of the present application, a method embodiment for determining the operating status of a network is provided. 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.

[0028] The method embodiments 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 The hardware structure block diagram of a computer terminal for implementing a method for determining the operating status of a network is shown. Figure 1 As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 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 device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can 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 as shown, or with Figure 1 Different configurations are shown.

[0029] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0030] 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 operating status of the network in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned method for determining the operating status of the network is realized. 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 examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, 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.

[0031] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] 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 .

[0033] The embodiment of the present application provides a method for determining the operating status of a network that can be operated in the above operating environment. Figure 2 is a flow chart of a method for determining the operating status of a network provided in an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0034] Step S202, obtaining historical performance data of the target network within a detection period, wherein the target network is a network running a network conference process, the detection period is a period of time when the target network runs the network conference process, and the historical performance data is used to describe the network performance of the target network within the detection period.

[0035] The embodiment of the present application provides a method for detecting whether a network is faulty in real time. Each time it is determined whether a network is faulty, the dynamic characteristics of the network are determined based on the historical performance data of the network, and then whether the network is faulty is determined based on the dynamic characteristics of the network and the actual performance data of the network at the current moment. The method provided by the embodiment of the present application is applied to any network that supports network conferencing; when detecting any network running a network conferencing process (i.e., the target network), first execute the method in step S202 to obtain the performance data (i.e., historical performance data) of the target network before the detection moment and when the network conferencing process is running, wherein the (historical) performance data of the network includes network delay, packet loss rate, central processing unit (CPU) utilization, memory occupancy rate, etc., which are used to describe network performance. These historical performance data can be arranged as a time series according to the time when they are generated (determined by the timestamp they carry). Usually, these performance data are collected at continuous and equally spaced time points; the detection period can be set to 1 minute, or 30 seconds, to ensure that the technical effect of real-time detection of the target network can be achieved.

[0036] In the embodiment of the present application, after the historical performance data of the target network is obtained in step S202, the linear dependency between the historical performance data can be directly determined, or the linear dependency between the historical performance data can be determined after preprocessing the historical performance data. Preprocessing the historical performance data can improve the accuracy of the processing result. If the historical performance data is preprocessed, the following method can be adopted: Arrange the historical performance data into a time series Y according to their corresponding generation time t , and then perform differential processing on it. The differential processing process can be expressed by the following formula: t ‘ =Y t -Y{t-1}, where Y t ‘ is the first-order difference value of the historical performance data generated at time t. If the first-order difference is obtained, Y t ‘ If there is still large fluctuation in the data, the second-order difference can be continued until the fluctuation of the data in the obtained sequence tends to be stable, and the preprocessing is completed.

[0037] Step S204, determining the linear dependency of the plurality of historical performance data, and constructing an objective function according to the linear dependency, wherein the objective function is used to describe the dynamic characteristics of the historical performance data, and the dynamic characteristics are used to indicate the law of change of the historical performance data over time.

[0038] After obtaining the historical performance data of the target network in the detection cycle in step S202, further, in step S204, the dynamic characteristics of the network (i.e., the target network) running the network conference process are determined by analyzing these historical performance data. The dynamic characteristics of the network in the embodiment of the present application refer to the law of the performance of the network changing over time. Specifically, in step S204, the linear dependency between the historical performance data is first analyzed, and then a function model (i.e., the target function) that can describe the law of the historical performance data changing over time is constructed based on the obtained linear dependency. For example, an autoregressive moving average model (Autoregressive MovingAverage model, ARMA) can be constructed based on the linear dependency of the historical performance data. The ARMA model is a time series model. The ARMA model can predict the value of future data points, and can be combined with the network performance data at the historical moment to predict the current operating state of the network, and can also be combined with the network performance data at the current moment to predict the operating state of the network at the next detection cycle at the current moment. Since the object analyzed in step S204 is the historical performance data of the target network, the dynamic characteristics analyzed in step S204 are the laws of the historical performance data changing over time.

[0039] Optionally, the linear dependency includes: autocorrelation, partial autocorrelation, and determining the linear dependency of multiple historical performance data includes: determining multiple lag time intervals, wherein the lag time interval contains multiple generation moments of multiple historical performance data; for each lag time interval, determining multiple first generation moments contained in the lag time interval, and determining a first type of historical performance data whose generation moment is the first generation moment; determining the autocorrelation coefficient corresponding to each lag time interval based on the first type of historical performance data, wherein the autocorrelation coefficient is used to indicate the autocorrelation; and determining the second generation moment with the earliest indication time and the third generation moment with the latest indication time in the lag time interval; determining the second type of historical performance data with the generation moment being the second generation moment, and determining the third type of historical performance data with the generation moment being the third generation moment; determining the partial autocorrelation coefficient corresponding to each lag time interval based on the second type of historical performance data and the third type of historical performance data, wherein the partial autocorrelation coefficient is used to indicate the partial autocorrelation.

[0040] In this embodiment, the linear dependency relationship between historical performance data includes two categories: autocorrelation and partial autocorrelation. Among them, autocorrelation is the correlation between two categories of historical performance data corresponding to two detection moments, and the correlation between them is affected by the historical performance data at other detection moments between the two detection moments; partial autocorrelation also refers to the correlation between two categories of historical performance data corresponding to two detection moments. However, when determining the partial autocorrelation, the historical performance data at other detection moments between the two detection moments are not considered. Therefore, the partial autocorrelation of the two categories of historical performance data corresponding to the two detection moments is not affected by the historical performance data at other detection moments between the two detection moments. In this embodiment, an autocorrelation function (ACF) is introduced to determine the autocorrelation between historical performance data, and at the same time, a partial autocorrelation function (PACF) is introduced to determine the partial autocorrelation between historical performance data; wherein, the autocorrelation function (ACF) is used to describe the correlation between a time series and itself at different lag periods, and the partial autocorrelation function (PACF) is used to describe the correlation between a time series and itself at different lag periods on the basis of controlling the influence of the lag period. In this embodiment, each historical performance data carries its corresponding generation time, and a series generated by arranging multiple historical performance data according to their corresponding generation times is a time series, and the lag period (i.e., the lag time interval) refers to the difference in the generation times corresponding to the two historical performance data to be analyzed, which is given by From the above, it can be seen that when using ACF and PACF to analyze the linear dependence between historical performance data, setting the lag period (i.e., the lag time interval) is a necessary step. Therefore, when determining the linear dependence between historical performance data, the following steps are mainly involved: First, multiple lag time intervals are determined according to multiple historical generation moments corresponding to multiple historical performance data. When the lag time interval is 1 time unit (such as 1 second), it means analyzing the autocorrelation between multiple historical performance data with a generation moment interval of 1 second. When the lag time interval is 2 time units (such as 2 seconds), it means analyzing the autocorrelation between multiple historical performance data with a generation moment interval of 2 seconds. It can be seen that when the lag time interval is set to different time spans, the number of generation moments it covers is different.Next, the autocorrelation between the historical performance data is determined. Since the multiple generation moments (i.e., the first generation moment) covered by each lag time interval must include the two generation moments corresponding to the two historical performance data to be analyzed, as well as the generation moment between these two generation moments, therefore, by analyzing the historical performance data (i.e., the first type of historical performance data) whose generation moment is the same as the generation moment (i.e., the first generation moment) included in each lag time interval, a quantitative value (i.e., the autocorrelation coefficient) used to indicate the autocorrelation between the historical performance data can be determined; for example, when the lag time interval is 2 generation moments, the generation moments covered in each lag time interval are generation moment A, generation moment B, and generation moment C, wherein generation moment A is one generation moment away from generation moment B, and generation moment B is one generation moment away from generation moment C. Since the influence of other data is not considered when determining the partial autocorrelation, when determining the partial autocorrelation between historical performance data, only the historical performance data corresponding to the two generation moments to be analyzed are considered, and the data corresponding to other generation moments between the two generation moments are ignored, or the influence of the data corresponding to other generation moments between the two generation moments is set to a preset value; then, when determining the partial autocorrelation, only the historical performance data (i.e., the second type of historical performance data) whose generation moment is the earliest generation moment (i.e., the second generation moment) contained in the lag time interval and the historical performance data whose generation moment is the latest generation moment (i.e., the third generation moment) contained in the lag time interval are considered; by analyzing the above second type of historical performance data and the third type of historical performance data, a quantitative value (i.e., partial autocorrelation coefficient) indicating the partial autocorrelation between historical performance data can be determined. The above-mentioned scheme for determining the linear dependency between historical performance data can be implemented by software with data statistics function and code execution function, and such software can be used to analyze the historical performance data and draw charts to show the linear dependency between historical performance data; for example, it can be implemented by the following code:.

[0041] fig,(ax1,ax2)=plt.subplots(2,1);#Create a subplot layout with 2 rows and 1 column, and get the axis objects ax1 and ax2 of the subplot#;

[0042] sm.graphics.tsa.plot_acf(data,lags=40,ax=ax1);#Use tsa module of statsmodels to draw autocorrelation function (ACF) graph, lags=40 means the number of lags calculated is 40, and the result is drawn on ax1 axis#

[0043] ax1.set_title('ACF'); #Set the title of the first subgraph to 'ACF'#

[0044] sm.graphics.tsa.plot_pacf(data,lags=40,ax=ax2);#Use the tsa module of statsmodels to draw the partial autocorrelation function (PACF) graph. lags=40 means that the number of lags calculated is 40. The result is plotted on the ax2 axis. #ax2.set_title('PACF').#Set the title of the second subgraph to 'PACF'#.

[0045] According to some optional embodiments of the present application, constructing an objective function according to a linear dependency relationship includes: determining a first lag parameter value corresponding to each autocorrelation coefficient, wherein the first lag parameter value is used to indicate the number of generation moments included in the lag time interval corresponding to the autocorrelation coefficient; determining a target first lag parameter value whose corresponding autocorrelation coefficient is 0 and whose value is the smallest among multiple first lag parameter values; determining a second lag parameter value corresponding to each partial autocorrelation coefficient, wherein the second lag parameter value is used to indicate the number of generation moments included in the lag time interval corresponding to the partial autocorrelation coefficient; determining a target second lag parameter value whose corresponding partial autocorrelation coefficient is 0 and whose value is the smallest among multiple second lag parameter values; screening target historical performance data for constructing the objective function in the historical performance data according to the target first lag parameter value and the target second lag parameter value; and constructing the objective function according to the target historical performance data.

[0046] As mentioned in step S204, after the linear dependency between the historical performance data is determined, it is necessary to construct a function model ARMA (i.e., the objective function) based on the linear dependency of the historical performance data. The function model ARMA (i.e., the objective function) can be expressed as the following formula: Among them, X t represents the historical performance data at the generation time t, u represents the average value of the historical performance data, P is the order at which the autocorrelation coefficient first drops to 0 determined based on the autocorrelation of the historical performance data (i.e., the target first lag parameter value), q is the order at which the partial autocorrelation coefficient first drops to 0 determined based on the partial autocorrelation of the historical performance data (i.e., the target second lag parameter value), φ i represents the autoregressive coefficient, which is used to indicate the linear dependence between the historical performance data generated at time t and the multiple historical performance data generated before time t, θ j Represents the moving average coefficient, which is used to indicate the relationship between the forecast results output by ARMA at the generation time t and the multiple error values ​​before time t, φ i and θ j It can be determined by processing historical performance data through statistical methods such as maximum likelihood or least squares method; ti is the historical performance data corresponding to the generation time (ti), and is the historical performance data generated before the generation time t; ∈t-j It represents the error value corresponding to the generation time (ti), which is determined based on the historical performance data at the generation time (ti) and the performance data at the time (ti) predicted by the ARMA function; ∈ t represents the error value corresponding to the generation time t, in, It is determined by the performance data at time t obtained by ARMA prediction. It can be seen from the above formula that when the function model ARMA (i.e., the target function) is used for prediction, the historical performance data used are the historical performance data generated in the interval (1~p), and the error data (i.e., the error term) used are the error terms generated in the interval (1~q), that is, the historical performance data (i.e., the target historical performance data) used to construct the function model ARMA (i.e., the target function) are obtained by screening all the historical performance data with p (i.e., the first target lag parameter value) and q (i.e., the second target lag parameter value) as screening conditions after determining the order at which the autocorrelation coefficient first drops to 0 (i.e., the target first lag parameter value) and the order at which the partial autocorrelation coefficient first drops to 0 (i.e., the target second lag parameter value). The above method for constructing the function model ARMA (i.e., the target function) can be implemented by software with data statistics function and code execution function, for example, it can be implemented by the following code, which takes 100 historical performance data as an example:

[0047] np.random.seed(123); #Set the random number seed to ensure the repeatability of the results#

[0048] data = np.random.randn(100); #Generate 100 random numbers that follow the standard normal distribution as sample data #model = ARMA(data,order = (1,1)); #Fit the ARMA(1,1) model, setting the order to (1,1) means that the AR order (P) is 1 and the MA order (q) is 1#

[0049] model_fit = model.fit(); #Fit the model#

[0050] print(model_fit.summary()).#Print summary information of model fitting results, including estimated parameters, standard errors, confidence intervals, etc.#.

[0051] Step S206, obtaining actual performance data of the target network at the current moment, and determining the operating state of the target network at the current moment according to the actual performance data and the target function, wherein the operating state includes: normal operation and abnormal operation.

[0052] After the dynamic characteristics of the target network are determined in step S204, the dynamic characteristics of the target network can be used to analyze the performance data of the target network at the current moment (i.e., actual performance data) in step S206 to predict the operating state of the target network at the current moment; specifically, in step S206, the function model (i.e., target function) describing the dynamic characteristics of the target network is used to analyze the performance data (i.e., historical performance data) generated by the target network in the last detection cycle closest to the current moment to obtain the prediction result output by the function model, the prediction result is the performance data of the target network at the current moment predicted by the function model, and the operating state of the target network at the current moment is jointly determined based on the prediction result output by the function model and the performance data (i.e., actual performance data) actually generated by the target network at the current moment. Whether it is abnormal operation due to a fault or normal operation without a fault. In order to ensure timeliness and accuracy, the method provided in the embodiment of the present application can set the detection period to 1 minute, or 30 seconds or a shorter duration.

[0053] Optionally, determining the operating state of the target network at the current moment according to actual performance data and the objective function includes: determining a plurality of first prediction results according to historical performance data and the objective function, wherein the first prediction result is used to indicate the performance of the target network at the current moment; determining a first difference between the first prediction result and the actual performance data, and comparing the first difference with a reference difference to obtain a comparison result, wherein the reference difference is determined in the process of iteratively updating the objective function using historical performance data; when the comparison result indicates that the absolute value of the first difference is greater than the reference difference, determining that the operating state of the target network at the current moment is abnormal operation; when the comparison result indicates that the absolute value of the first difference is less than or equal to the reference difference, determining that the operating state of the target network at the current moment is normal operation.

[0054] After the function model ARMA (i.e., the target function) is constructed in step S204, the target function is used to analyze the performance data X of the target network at the current moment in step S206. new (i.e., actual performance data); at the same time, the target function is used to analyze the performance data (i.e., historical performance data) generated in the previous detection cycle of the target network at the current moment, and a (first) prediction result indicating the performance of the target network at the current moment is obtained. And further according to the formula Determine the error value ∈ between the predicted result output by the model and the actual performance data new (i.e., the first difference) is used to determine the current operating state of the target network. In this embodiment, determining the operating state of the target network at the current moment by using the error value is to convert the error value (i.e., the first difference)∈ newCompare with the reference difference determined in the iterative update process of the function model ARMA (i.e., the target function), and judge whether the operating state of the target network is normal operation or abnormal operation according to the comparison result; wherein, the reference difference is the maximum allowable error value. The historical performance data (i.e., the target historical performance data) used when constructing the function model ARMA is screened, and are all performance data generated when the target network is in a normal operating state. Then, the result (i.e., the first prediction result) predicted by the function model ARMA (i.e., the target function) is actually the performance data generated at the current moment when the target network is running in a normal operating state. If the difference between the actual performance data currently generated by the target network and the (first) prediction result output by the function model ARM is greater than the above-mentioned reference difference, it means that the allowable error value has been exceeded, and the current operating state of the target network is abnormal operation; otherwise, if the difference between the actual performance data currently generated by the target network and the (first) prediction result output by the function model ARM is less than or equal to the above-mentioned reference difference, it means that the fluctuation of network performance is within the allowable error range, and the current operating state of the target network is normal operation.

[0055] According to some optional embodiments of the present application, the reference difference is determined by the following method: during each iterative update, multiple second prediction results are determined based on the objective function and historical performance data, wherein the second prediction results are used to indicate the performance of the target network at a historical moment, and the historical moment is a plurality of moments included in the detection cycle; for each historical moment, a second difference between the historical performance data corresponding to the historical moment and the second prediction result is determined; the reference difference is determined based on the multiple second differences, the number of second prediction results, and the parameters of the objective function, wherein the parameters are used to indicate the sum of the parameters of the objective function, and the parameters of the objective function include: autocorrelation coefficient and partial autocorrelation coefficient.

[0056] As mentioned in the previous embodiment, the reference difference is determined in the iterative update process of the function model ARMA (ie, the objective function). Specifically, the process of determining the reference difference in this embodiment can be described as a formula: Among them, σ ∈ is the reference difference, t represents the generation time, X t It is the performance data actually generated by the target network at the time of generation (i.e. historical performance data). is the performance data of the target network at time t predicted by the function model ARMA (i.e., the target function) (i.e., the second prediction result), n is the number of generated time t, and is also the residual (i.e., X t and The number of differences, that is, the second difference), P is the parameter sum of the function model. For example, in the embodiment of the present application, the parameters of the function model ARMA (that is, the target function) are the autocorrelation coefficient p (that is, the target first lag parameter value) and the partial autocorrelation coefficient q (that is, the target second lag parameter value), then the parameter sum P = p + q. After each iterative update is completed, the reference difference σ is determined using the above formula ∈ , until the iteration is updated to the current moment, where the reference difference σ is used when updating to the current moment ∈ It is determined based on the historical performance data generated in the previous detection cycle at the current detection time and its corresponding prediction results, that is, the reference difference used to judge the operating status of the target network at the time to be detected is determined based on the historical performance data generated in the previous detection cycle at the time to be detected and the prediction results corresponding to the historical performance data. In addition, the reference difference can also be set to kσ ∈ , where k is a preset value. By setting k to different values, the reference difference value for judging the network operation status can be flexibly adjusted to meet the requirements of the target network in different scenarios. For example, when the network conference supported by the target network has a higher requirement for synchronization, the value of k can be set to a smaller value; when the network conference supported by the target network has a higher requirement for synchronization, the value of k can be set to a larger value. In addition, in this embodiment, the actual error value at the current moment ∈ new (i.e. the first difference) and the reference difference kσ ∈ (or σ ∈ ) is taken as the anomaly index (EAI) of the target network.

[0057] According to some other optional embodiments of the present application, the method for determining the operating status of a network also includes: when it is determined that the operating status of the target network at the current moment is abnormal operation, determining a third difference between the first difference and the reference difference, and determining the abnormality level of the target network based on the third difference, wherein the abnormality level is positively correlated with the third difference; determining a maintenance level associated with the abnormality level in a preset list, wherein the preset list is used to record the association between the abnormality level and the maintenance level; and sending a maintenance alarm to a terminal associated with the maintenance level, wherein the maintenance alarm is used to prompt a user corresponding to the terminal to repair the target network.

[0058] In some embodiments, when the network state is determined to be abnormal, the residual ∈ new (ie, the first difference) and the threshold value (ie, the reference difference) kσ ∈ The (third) difference of determines the equipment anomaly index EAI, which is used to determine the degree of abnormality of the target network (i.e., the abnormality level), where ∈ new Difference kσ from the reference ∈The larger the difference (i.e., the third difference) is, the higher the abnormality level is. Further, the maintenance level of the target network is determined according to the abnormality level of the target network, so as to match the target network with more / larger faults (i.e., higher abnormality level) to maintenance personnel with stronger maintenance skills for maintenance, thereby improving the probability of successful repair. In this embodiment, the association between the abnormality level and the maintenance level is recorded in a mapping table (i.e., a preset list), and each abnormality level in the mapping table is simultaneously associated with the numerical range and maintenance level of the abnormality index EAI. Therefore, after determining the abnormality index EAI of the target network, its associated abnormality level can be determined in the preset list, and the maintenance level associated with this abnormality level is determined as the abnormality level of the target network. In this embodiment, after determining the maintenance level, the target network is notified to be repaired by sending an alarm message (i.e., a maintenance alarm) to the terminal associated with the maintenance level, wherein each terminal is bound to a maintenance personnel (i.e., a user), and the maintenance level corresponding to the terminal is the maintenance level of the maintenance personnel bound to the terminal.

[0059] Optionally, the maintenance level is determined by the following method: obtaining maintenance information associated with the terminal, wherein the maintenance information includes at least: number of maintenance times, after-sales satisfaction, and current maintenance score; determining the weight corresponding to the maintenance information, wherein the weight corresponding to the first maintenance is different from the weight corresponding to the number of repairs; and determining the maintenance level based on the maintenance information and the weight.

[0060] As mentioned in the above embodiment, the maintenance level associated with each terminal is the maintenance level of the maintenance personnel (i.e., the user) bound to the terminal. In this embodiment, the maintenance level is determined by the following method. First, the maintenance information associated with the terminal is obtained, that is, the maintenance information of the maintenance personnel bound to the terminal, such as the number of maintenance times, after-sales satisfaction and other basic maintenance information, and the maintenance information may also include: the average maintenance price, the current maintenance score of the maintenance personnel bound to the terminal, and the maintenance level is determined based on the above multiple maintenance information. The method for determining the maintenance level can be expressed as the following formula: MLI = WC × W wc +SH×W sh +WJ×W wj , where MLI represents the maintenance level, WC represents the number of maintenance times, and the score W wc represents the weight of the number of repairs, SH represents the score of after-sales satisfaction, and W sh represents the weight corresponding to after-sales satisfaction, WJ represents the current maintenance score of the maintenance personnel, which is determined based on the average maintenance price, and W wj Represents the weight of the current maintenance score, where W wc +W sh +W wj=1. Since the number of repairs (WC) reflects the workload and experience of the maintenance personnel. Therefore, a threshold can be set based on the distribution of the number of repairs to convert the number of repairs into a score. For example, if the threshold of the number of repairs is set to 25 times, the scoring standard for the number of repairs is: less than 25 times: 50 points (less experience); 25 to 50 times: 70 points (moderate experience); 51 to 75 times: 90 points (rich experience); more than 75 times: 100 points (extremely rich experience). After-sales satisfaction directly reflects the customer's satisfaction with the maintenance service, so it is usually expressed in percentage. The scoring criteria are as follows: satisfaction below 60%: 50 points (unsatisfied); 60% to 79%: 70 points (generally satisfied); 80% to 89%: 90 points (satisfied); more than 90%: 100 points (very satisfied). The average price of maintenance reflects the cost efficiency of the maintenance service, and the score can be set based on the comparison with the industry average price. Assume that the industry average price is X. The scoring standard for the average repair price is: 20% or more above the industry average price: 50 points (expensive); 10% to 20% above the industry average price: 70 points (high price); 10% to 10% below the industry average price: 90 points (reasonable price); 20% or less below the industry average price: 100 points (affordable price). It is worth mentioning that the scoring standard here is proportional to the degree of price discount, that is, this scoring standard tends to take into account the price that consumers need to spend. However, in reality, for companies, the higher the average price, the more profit they make. Therefore, if we consider the company's perspective, the scoring standard for the average maintenance price can be set to the opposite of the above-mentioned situation considering consumers, that is, higher than the industry average price X20% or more: 100 points (expensive, maximum profit); higher than the industry average price X10% to 20%: 90 points (high price, more profit); lower than the industry average price X10% to 10% higher than the industry average price: 70 points (reasonable price, normal profit); lower than the industry average price X20% or less: 50 points (favorable price, little profit). In addition, if only the number of repairs (WC) is considered for scoring, it cannot represent the quality of the repairs, because the more repairs the same customer has, the lower the quality of each repair. For this reason, the score of the number of repairs WC can include the score based on the first repair (CW) and the score based on the number of returns (FX), as follows: obtain the number of repairs performed by the maintenance personnel on new customers and the number of returns for the customer through the maintenance company system, and perform a weighted average of the number of first repairs and the number of returns to obtain the score based on the number of repairs (WC) while considering both the number of first repairs and the number of returns. That is, the score of the number of repairs (WC) can be calculated by the following formula: WC = (CW × WC) cw +FX×W fx ), where CW represents the number of initial repairs by maintenance personnel, FX represents the number of return repairs by maintenance personnel, and Wcw represents the weight of the initial maintenance, W fx Represents the weight of the repair. The number of initial repairs mainly reflects the workload and service scope of the maintenance personnel. A higher number of initial repairs indicates that the maintenance personnel has extensive service experience. Therefore, the scoring standard can be referred to as follows: less than 20 times: 50 points (less experience); 20 to 40 times: 70 points (moderate experience); 41 to 60 times: 90 points (rich experience); more than 60 times: 100 points (extremely rich experience). The number of repairs reflects the problem of maintenance quality. The lower the number of repairs, the higher the maintenance quality. Therefore, the scoring standard can be referred to as follows: 0 times: 100 points (no repair, the highest quality); 1 to 2 times: 90 points (occasionally repair, high quality); 3 to 5 times: 70 points (frequent repairs, need for improvement); more than 5 times: 50 points (frequent repairs, serious quality problems). After determining the maintenance level (MLI) of each maintenance personnel through the above method, the maintenance level is associated with the terminal of the maintenance personnel.

[0061] Through the above steps, real-time monitoring and anomaly detection of the network operation status can be achieved, and the accuracy of the detection results can be improved, thereby ensuring the smooth progress of the network conference and timely fault response.

[0062] Figure 3 is a structural diagram of a device for determining the operating status of a network provided in an embodiment of the present application, such as Figure 3 As shown, the device includes: an acquisition module 30, which is used to acquire historical performance data of the target network within a detection period, wherein the target network is a network running a network conference process, the detection period is a time period when the target network runs the network conference process, and the historical performance data is used to describe the network performance of the target network within the detection period; a first determination module 32, which is used to determine the linear dependency of multiple historical performance data, and construct an objective function based on the linear dependency, wherein the objective function is used to describe the dynamic characteristics of the historical performance data, and the dynamic characteristics are used to indicate the law of change of the historical performance data over time; a second determination module 34, which is used to acquire the actual performance data of the target network at the current moment, and determine the operating status of the target network at the current moment based on the actual performance data and the objective function, wherein the operating status includes: normal operation and abnormal operation.

[0063] The device for determining the operation state of the network can be a network device such as a router, a switch, and a server. When these network devices determine the operation state of the network, the acquisition module 30 collects the historical performance data such as the network delay, packet loss rate, and bandwidth usage of the target network within the detection period (for example, 1 minute); the acquisition module 30 transmits the above historical performance data to the first determination module 32, and the first determination module 32 constructs a function model ARMA (i.e., the target function) by analyzing the linear dependency (autocorrelation, partial correlation) between the historical performance data; and transmits ARMA to the second determination module 34. When the network conference is in progress, the second determination module 34 obtains the current performance data (i.e., the actual performance data) of the network (i.e., the target network) used in the network conference, and determines whether the operation state of the target network is normal operation or abnormal operation according to ARMA and the actual performance data; for example, the second determination module 34 obtains the current network delay data of 500 milliseconds (ms), the packet loss rate is 3%, and the bandwidth usage rate is 85% in real time. The ARMA (3 (p), 2 (q)) model is used to predict that the network delay at the current moment should be 400ms, the packet loss rate is 1%, and the bandwidth usage rate is 75%. The residuals between the actual and predicted values ​​are 100ms, 2%, and 10%, respectively. Assume that the reference difference is set to the mean of the historical residuals. If the absolute value of the residual (i.e., the first difference) is less than the reference difference, the network is determined to be in normal operation. If the absolute value of the residual exceeds the reference difference, for example, the absolute value of the residual of the network delay of 100ms is greater than the reference difference, the network delay part is determined to be in an abnormal operation state and requires further diagnosis and maintenance. In addition, the second determination module 34 will also determine the abnormality level based on the abnormal difference, and send a maintenance alarm to the corresponding maintenance personnel or team by matching the maintenance level list, so as to quickly respond to and solve the problem and ensure the continuity of the meeting and the user experience.

[0064] It should be noted that Figure 3 The preferred implementation of the illustrated embodiment can be found in Figure 2 The relevant description of the illustrated embodiment will not be repeated here.

[0065] An embodiment of the present application further provides a non-volatile storage medium, in which a computer program is stored, wherein the above method for determining the operating status of a network is executed by running the computer program on a device where the non-volatile storage medium is located.

[0066] The above-mentioned non-volatile storage medium is used to store programs that perform the following functions: obtain historical performance data of the target network within a detection period, wherein the target network is a network running a network conference process, the detection period is a period of time when the target network runs the network conference process, and the historical performance data is used to describe the network performance of the target network within the detection period; determine the linear dependency of multiple historical performance data, and construct an objective function based on the linear dependency, wherein the objective function is used to describe the dynamic characteristics of the historical performance data, and the dynamic characteristics are used to indicate the law of change of the historical performance data over time; obtain the actual performance data of the target network at the current moment, and determine the operating status of the target network at the current moment based on the actual performance data and the objective function, wherein the operating status includes: normal operation and abnormal operation.

[0067] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above method for determining the operating status of a network through the computer program.

[0068] The processor in the above-mentioned electronic device is used to run a program that performs the following functions: obtaining historical performance data of the target network within a detection period, wherein the target network is a network running a network conference process, the detection period is a period of time when the target network runs the network conference process, and the historical performance data is used to describe the network performance of the target network within the detection period; determining the linear dependency of multiple historical performance data, and constructing an objective function based on the linear dependency, wherein the objective function is used to describe the dynamic characteristics of the historical performance data, and the dynamic characteristics are used to indicate the law of change of the historical performance data over time; obtaining the actual performance data of the target network at the current moment, and determining the operating status of the target network at the current moment based on the actual performance data and the objective function, wherein the operating status includes: normal operation and abnormal operation.

[0069] According to another aspect of an embodiment of the present application, a computer program product is also provided, including computer instructions, which implement the steps of the above-mentioned method for determining the operating status of a network when the computer instructions are executed by a processor.

[0070] It should be noted that the various modules in the above-mentioned device for determining the state of the network can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0071] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0072] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0073] 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 schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, 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.

[0074] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0075] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0076] 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, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0077] The above is only a preferred implementation 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 operating status of a network, characterized in that: include: Acquire historical performance data of a target network within a detection period, wherein the target network is a network running a network conference process, the detection period is a period of time during which the target network runs the network conference process, and the historical performance data is used to describe the network performance of the target network within the detection period; Determine a linear dependency relationship among a plurality of the historical performance data, and construct an objective function according to the linear dependency relationship, wherein the objective function is used to describe the dynamic characteristics of the historical performance data, and the dynamic characteristics are used to indicate a law of change of the historical performance data over time; Acquire actual performance data of the target network at the current moment, and determine the operating state of the target network at the current moment according to the actual performance data and the objective function, wherein the operating state includes: normal operation and abnormal operation.

2. The method according to claim 1, characterized in that The linear dependency relationship includes: autocorrelation and partial autocorrelation. Determining the linear dependency relationship of the plurality of historical performance data includes: Determine a plurality of hysteresis time intervals, wherein the hysteresis time intervals include a plurality of generation moments of the plurality of historical performance data; For each of the lag time intervals, determining a plurality of first generation moments included in the lag time interval, and determining a first type of historical performance data whose generation moment is the first generation moment; determining an autocorrelation coefficient corresponding to each of the lag time intervals according to the first type of historical performance data, wherein the autocorrelation coefficient is used to indicate the autocorrelation; and, Determine a second generation moment with the earliest indication time and a third generation moment with the latest indication time in the lag time interval; determine the second type of historical performance data with the generation time being the second generation moment, and determine the third type of historical performance data with the generation time being the third generation moment; determine the partial autocorrelation coefficient corresponding to each of the lag time intervals based on the second type of historical performance data and the third type of historical performance data, wherein the partial autocorrelation coefficient is used to indicate the partial autocorrelation.

3. The method according to claim 2, characterized in that Constructing an objective function according to the linear dependency relationship includes: Determine a first lag parameter value corresponding to each of the autocorrelation coefficients, wherein the first lag parameter value is used to indicate the number of the generation moments contained in the lag time interval corresponding to the autocorrelation coefficient; determine a target first lag parameter value having a minimum value and a corresponding autocorrelation coefficient of 0 among the plurality of first lag parameter values; Determine a second lag parameter value corresponding to each of the partial autocorrelation coefficients, wherein the second lag parameter value is used to indicate the number of the generation moments contained in the lag time interval corresponding to the partial autocorrelation coefficient; determine a target second lag parameter value having a corresponding partial autocorrelation coefficient of 0 and a minimum value among the plurality of the second lag parameter values; Filter target historical performance data for constructing the objective function from the historical performance data according to the target first lag parameter value and the target second lag parameter value; and construct the objective function according to the target historical performance data.

4. The method according to claim 1, characterized in that: Determining the operating state of the target network at the current moment according to the actual performance data and the objective function includes: A plurality of first prediction results according to the historical performance data and the objective function, wherein the first prediction results are used to indicate the performance of the target network at a current moment; Determining a first difference between the first prediction result and the actual performance data, and comparing the first difference with a reference difference to obtain a comparison result, wherein the reference difference is determined in a process of iteratively updating the objective function using the historical performance data; When the comparison result indicates that the absolute value of the first difference is greater than the reference difference, determining that the operation state of the target network at the current moment is the abnormal operation; When the comparison result indicates that the absolute value of the first difference is less than or equal to the reference difference, it is determined that the operating state of the target network at the current moment is the normal operation.

5. The method according to claim 4, characterized in that The reference difference is determined by the following method: During each iteration update, a plurality of second prediction results are determined according to the objective function and the historical performance data, wherein the second prediction results are used to indicate the performance of the target network at a historical moment, and the historical moment is a plurality of moments included in the detection period; For each of the historical moments, determining a second difference between the historical performance data corresponding to the historical moment and the second prediction result; The reference difference is determined based on multiple second differences, the number of second prediction results and the parameter sum of the objective function, wherein the parameter sum is used to indicate the sum of the parameters of the objective function, and the parameters of the objective function include: autocorrelation coefficient and partial autocorrelation coefficient.

6. The method according to claim 4, characterized in that The method further comprises: In the case where it is determined that the operation state of the target network at the current moment is the abnormal operation, determining a third difference between the first difference and the reference difference, and determining an abnormality level of the target network according to the third difference, wherein there is a positive correlation between the abnormality level and the third difference; Determining a maintenance level associated with the abnormality level in a preset list, wherein the preset list is used to record the association relationship between the abnormality level and the maintenance level; A maintenance alarm is sent to a terminal associated with the maintenance level, wherein the maintenance alarm is used to prompt a user corresponding to the terminal to perform maintenance on the target network.

7. The method according to claim 6, characterized in that The maintenance level is determined by the following method: Acquire maintenance information associated with the terminal, wherein the maintenance information includes at least: number of maintenance times, after-sales satisfaction, and current maintenance score; Determine the weight corresponding to the maintenance information, wherein the weight corresponding to the first maintenance is different from the weight corresponding to the number of repairs; The maintenance level is determined according to the maintenance information and the weight.

8. A device for determining the operating status of a network, characterized in that include: An acquisition module, used to acquire historical performance data of a target network within a detection period, wherein the target network is a network running a network conference process, the detection period is a period of time during which the target network runs the network conference process, and the historical performance data is used to describe the network performance of the target network within the detection period; A first determination module is used to determine a linear dependency relationship between a plurality of the historical performance data, and to construct an objective function according to the linear dependency relationship, wherein the objective function is used to describe a dynamic characteristic of the historical performance data, and the dynamic characteristic is used to indicate a law of change of the historical performance data over time; The second determination module is used to obtain actual performance data of the target network at the current moment, and determine the operating state of the target network at the current moment according to the actual performance data and the objective function, wherein the operating state includes: normal operation and abnormal operation.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a computer program, wherein the method for determining the operating status of a network as described in any one of claims 1 to 7 is executed by running the computer program on the device where the non-volatile storage medium is located.

10. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to execute the method for determining the operating status of a network according to any one of claims 1 to 7 through the computer program.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method for determining the operating status of a network as described in any one of claims 1 to 7 are implemented.

Images