Method, device, equipment, medium and program product for evaluating quality of service

Abstract

The application discloses a service quality evaluation method and device, equipment, medium and program product, and relates to the technical field of artificial intelligence. The service quality evaluation method comprises the following steps: obtaining a target performance parameter of a target service in a target link of a target terminal, the target performance parameter comprising at least one of a target packet loss parameter, a target delay parameter, a target jitter parameter and a target bandwidth utilization rate, and the target link comprising at least one of a primary link and a backup link; comparing the target performance parameter with a corresponding performance parameter threshold to obtain a comparison result, wherein the performance parameter threshold comprises at least one of a packet loss threshold, a delay threshold, a jitter threshold and a bandwidth utilization rate threshold; and determining a quality evaluation result of the target service according to the comparison result. According to the embodiment of the application, the accuracy of the operation quality determination can be improved.

Description

Technical Field

[0001] This application belongs to the field of artificial intelligence technology, and in particular relates to a business quality assessment method, apparatus, equipment, medium and program product. Background Technology

[0002] The government and enterprise market, as a new driving force for revenue growth and a major force for transformation and upgrading for telecom operators, is an important component of their revenue structure. In customer satisfaction surveys among government and enterprise users, the operational quality of services provided by telecom operators is a key concern for users.

[0003] However, the accuracy of determining operational quality in related technologies is low. Summary of the Invention

[0004] This application provides a business quality assessment method, apparatus, equipment, medium, and program product that can improve the accuracy of business quality determination.

[0005] In a first aspect, embodiments of this application provide a service quality assessment method, the method comprising:

[0006] Obtain the target performance parameters of the target service in the target link of the target terminal. The target performance parameters include at least one of the target packet loss parameters, target latency parameters, target jitter parameters, and target bandwidth utilization. The target link includes at least one of the primary link and the backup link.

[0007] The target performance parameters are compared with the corresponding performance parameter thresholds to obtain the comparison results. The performance parameter thresholds include at least one of the following: packet loss threshold, latency threshold, jitter threshold, and bandwidth utilization threshold.

[0008] Based on the comparison results, the quality assessment results of the target business are determined.

[0009] In some alternative implementations of the first aspect, determining the quality assessment result of the target service based on the comparison results includes:

[0010] If all target performance parameters in the comparison results are greater than or equal to their corresponding performance parameter thresholds, the quality assessment result of the target service is determined to be passed.

[0011] If the comparison results show that the target performance parameter is lower than its corresponding performance parameter threshold, the quality assessment result of the target service is determined to be unsuccessful.

[0012] In some alternative implementations of the first aspect, before obtaining the target performance parameters of the target service, the method further includes:

[0013] Obtain historical busy time information, which includes historical busy time data, a first quantity of historical busy time data, a first weight corresponding to the historical busy time data, a first random fluctuation data at the first target time, a second quantity of the first random fluctuation data, a second weight corresponding to the first random fluctuation data, a third quantity of the first calibration data, and a first calibration coefficient corresponding to the first calibration data.

[0014] Determine peak hours based on historical peak hour information;

[0015] Determine the acquisition frequency based on peak hours;

[0016] Obtain the target performance parameters of the target service in the target link of the target terminal, including:

[0017] Based on the acquisition frequency, obtain the target performance parameters of the target service in the target link of the target terminal.

[0018] In some alternative implementations of the first aspect, the busy period includes a busy start time and a busy end time;

[0019] Based on historical peak hour information, determine peak hour periods, including:

[0020] Based on historical busy time information, determine the start and end times of busy times;

[0021] Among them, the i-th historical busy time data α i First quantity p, first weight y (t-i) The first random fluctuation data ε at the first target time (t-i) Second quantity q, second weight β i Third quantity n, first calibration coefficient μ i And the busy start time y1 or busy end time y1 satisfy formula (1):

[0022]

[0023] In some alternative implementations of the first aspect, before obtaining historical busy time information, the method includes:

[0024] Acquire historical power outage information, which includes historical power outage data, the fourth quantity of historical power outage data, the third weight corresponding to the historical power outage data, the second random fluctuation data at the second target time, the fifth quantity of the second random fluctuation data, the fourth weight corresponding to the second random fluctuation data, the sixth quantity of the second calibration data, and the second calibration coefficient corresponding to the second calibration data.

[0025] Based on historical power outage information, determine whether the target terminal is in a non-power outage state;

[0026] Retrieve historical busy time information, including:

[0027] Obtain historical busy time information when the target terminal is not powered off.

[0028] In some optional implementations of the first aspect, determining whether the target terminal is in a non-power-off state based on historical power outage information includes:

[0029] Based on historical power outage information, determine the start and end times of the power outage;

[0030] Determine whether the target terminal is in a non-power-off state based on the start and end times of the power outage;

[0031] Among them, the j-th historical power outage data α j The fourth quantity b, and the third weight y corresponding to historical power outage data. (t-j) The second random fluctuation data ε at the second target time (t-j) Fifth quantity d, fourth weight β j The sixth quantity m, the second calibration coefficient μ j And the time between the start time y2 of the power outage and the end time y2 of the power outage satisfies formula (2):

[0032]

[0033] In some alternative implementations of the first aspect, the target link includes a primary link and a backup link;

[0034] If the quality assessment results of the target service are both unsuccessful in both the primary link and the backup link, obtain the current quality parameters of the target terminal. The current quality parameters include at least one of the current interruption alarm frequency and the current terminal network access time.

[0035] Determine the current quality score of the target terminal based on the current quality parameters.

[0036] In some optional implementations of the first aspect, determining the current quality score of the target terminal based on current quality parameters includes:

[0037] Input the current quality parameters into the quality identification model, use the quality identification model to identify the target terminal, and obtain the current quality score of the target terminal.

[0038] The quality identification model is trained using historical quality parameters, which include at least one of the following: historical interruption alarm frequency and historical terminal network access time. The historical quality parameters correspond to the current quality parameters.

[0039] Secondly, embodiments of this application provide a business quality assessment apparatus, the apparatus comprising:

[0040] The first acquisition module is used to acquire the target performance parameters of the target service in the target link of the target terminal. The target performance parameters include at least one of the target packet loss parameters, target latency parameters, target jitter parameters and target bandwidth utilization. The target link includes at least one of the primary link and the backup link.

[0041] The comparison module is used to compare the target performance parameters with the corresponding performance parameter thresholds to obtain the comparison results. The performance parameter thresholds include at least one of the following: packet loss threshold, latency threshold, jitter threshold, and bandwidth utilization threshold.

[0042] The first determination module is used to determine the quality assessment result of the target business based on the comparison results.

[0043] Thirdly, embodiments of this application provide an electronic device, the device comprising:

[0044] Processor and memory storing computer program instructions;

[0045] When the processor executes computer program instructions, it implements the service quality assessment method as described in the first aspect.

[0046] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the service quality assessment method as described in the first aspect.

[0047] Fifthly, embodiments of this application provide a computer program product, which includes computer program instructions that, when executed by a processor, implement the service quality assessment method as described in the first aspect.

[0048] According to the service quality assessment method, apparatus, device, medium, and program product provided in the embodiments of this application, the target performance parameters of the target service in the target link of the target terminal are first obtained. Then, the target performance parameters are compared with the corresponding performance parameter thresholds to obtain the comparison results. Based on the comparison results, the quality assessment result of the target service is determined. Thus, by comparing at least one of the target packet loss parameters, target latency parameters, target jitter parameters, and target bandwidth utilization with the corresponding performance parameter thresholds, the quality of the target service in the primary link and / or backup link can be accurately determined. Compared with the device-level determination of operational quality in related technologies, the embodiments of this application can determine operational quality at the service level, thereby improving the accuracy of operational quality determination. Attached Figure Description

[0049] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This paper illustrates a flowchart of a business quality assessment method provided in an embodiment of this application.

[0051] Figure 2 This illustration shows a schematic diagram of a service quality assessment device provided in an embodiment of this application;

[0052] Figure 3 A schematic diagram of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0053] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0054] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0055] Before describing the technical solutions provided in the embodiments of this application, in order to facilitate understanding of the embodiments of this application, this application first specifically explains the problems existing in the related technologies:

[0056] The inventors discovered that the evaluation mechanisms for operational quality in related technologies are all at the equipment level, resulting in low accuracy in determining operational quality.

[0057] To address the aforementioned issues, embodiments of this application provide a service quality assessment method, apparatus, device, medium, and program product. The service quality assessment method provided in this application embodiment will be described first below.

[0058] Figure 1 A flowchart illustrating a business quality assessment method provided in an embodiment of this application is shown.

[0059] The service quality assessment method provided in this application can be executed by a server, a service quality assessment device, or an electronic device. This application embodiment uses an electronic device as the executing entity for illustration. For example, the electronic device may include a Packet Transport Network (PTN) device, a Synchronous Packet Network (SPN) device, and a miniaturized PTN, etc.

[0060] like Figure 1 As shown, the business quality assessment method may include the following S110 to S130.

[0061] S110. Obtain the target performance parameters of the target service in the target link of the target terminal. The target performance parameters include at least one of the target packet loss parameters, target latency parameters, target jitter parameters and target bandwidth utilization. The target link includes at least one of the primary link and the backup link.

[0062] S120. Compare the target performance parameters with the corresponding performance parameter thresholds to obtain the comparison results. The performance parameter thresholds include at least one of the following: packet loss threshold, latency threshold, jitter threshold, and bandwidth utilization threshold.

[0063] S130. Based on the comparison results, determine the quality assessment results of the target business.

[0064] According to the service quality assessment method provided in this application embodiment, the target performance parameters of the target service in the target link of the target terminal are first obtained. Then, the target performance parameters are compared with the corresponding performance parameter thresholds to obtain the comparison results. Based on the comparison results, the quality assessment result of the target service is determined. Thus, by comparing at least one of the target packet loss parameters, target latency parameters, target jitter parameters, and target bandwidth utilization with the corresponding performance parameter thresholds, the quality of the target service in the primary link and / or backup link can be accurately determined. Compared with the device-level determination of operational quality in related technologies, this application embodiment can determine operational quality at the service level, thereby improving the accuracy of operational quality determination.

[0065] The specific implementation methods for each of the above steps are described below.

[0066] In S110, the target terminal can be a telecommunications operator terminal connected to the user terminal via the target link.

[0067] The target link includes at least one of the primary link and the backup link.

[0068] The target service can be any service provided by a telecommunications operator to a user terminal.

[0069] The target packet loss parameter can be used to characterize the proportion of data packets lost during data transmission.

[0070] The target delay parameter can be used to characterize the time required for data to travel from the sender to the receiver.

[0071] The target jitter parameter can be used to characterize the delay variation of data packets during transmission.

[0072] Target bandwidth utilization can be used to characterize the utilization rate of network bandwidth.

[0073] For example, the electronic device may include a Tunnel Quality Test Module (TQTM). The TQTM can be used to transmit target packet loss parameters, target delay parameters, and target jitter parameters between the A-end network element (i.e., the sender of data transmission) and the Z-end network element (i.e., the receiver of data transmission) of the tunnel. The TQTM may include a low-level protocol based on the Internet Control Message Protocol (ICMP) to enable the detection of end-to-end network connectivity, i.e., the detection of target packet loss parameters, target delay parameters, and target jitter parameters.

[0074] For example, the electronic device may also include a Pseudowire Data Statistics Module (PDSM), which can be used to count the number and size of data packets sent and received on the pseudowire, and calculate the instantaneous traffic and the cumulative traffic over a period of time. By comparing with the configured bandwidth, the instantaneous bandwidth utilization and the bandwidth utilization over a period of time can be automatically output. For example, the ratio of instantaneous traffic to available bandwidth can be determined as the instantaneous bandwidth utilization. As another example, the ratio of cumulative traffic over a period of time to the available bandwidth during that period can be determined as the bandwidth utilization over that period of time.

[0075] In some implementations, the method further includes, before obtaining the target performance parameters of the target service:

[0076] Obtain historical busy time information, which includes historical busy time data, a first quantity of historical busy time data, a first weight corresponding to the historical busy time data, a first random fluctuation data at the first target time, a second quantity of the first random fluctuation data, a second weight corresponding to the first random fluctuation data, a third quantity of the first calibration data, and a first calibration coefficient corresponding to the first calibration data.

[0077] Determine peak hours based on historical peak hour information;

[0078] Determine the acquisition frequency based on peak hours;

[0079] Obtain the target performance parameters of the target service in the target link of the target terminal, including:

[0080] Based on the acquisition frequency, obtain the target performance parameters of the target service in the target link of the target terminal.

[0081] In this embodiment, determining the busy time period through historical busy time information can improve the accuracy of busy time period determination; determining the acquisition frequency through the busy time period, and then acquiring the target performance parameters of the target service in the target link of the target terminal based on the acquisition frequency, can improve the efficiency of service quality determination and also alleviate the problem of bandwidth contention with users.

[0082] For example, historical busy time data may include the start time and end time of historical busy times. Correspondingly, the first quantity may include the number of historical busy time start times and the number of historical busy time end times. It is understood that the number of historical busy time start times is the same as the number of historical busy time end times.

[0083] For example, the first random fluctuation data may include busy-hour data of random fluctuations at a first target time. The first random fluctuation data includes a white noise sequence.

[0084] For example, the first calibration data may be historical busy-hour data for calibration.

[0085] In some examples, the busy period includes the start time and the end time of the busy period;

[0086] Based on historical peak hour information, determine peak hour periods, including:

[0087] Based on historical busy time information, determine the start and end times of busy times;

[0088] Among them, the i-th historical busy time data α i First quantity p, first weight y (t-i) The first random fluctuation data ε at the first target time (t-i) Second quantity q, second weight β iThird quantity n, first calibration coefficient μ i And the busy start time y1 or busy end time y1 satisfy formula (1):

[0089]

[0090] In this example, the start and end times of the busy period can be quickly determined using formula (1) and historical busy period information.

[0091] Formula (1) can be called the AWCIMA (Autoregressive Weight-based Correct Integrated Moving Average) algorithm, or the busy hour prediction model. p, q and n can all represent the order of the busy hour prediction model. Specifically, p can be the number of historical busy hour data, q can be the number of white noise sequences related to busy hours, and n can be the number of calibrated historical busy hour data.

[0092] In some examples, the training data for the busy-hour prediction model can be divided into three parts. The first part can be the basic data used to train user busy-hour predictions; the second part can be the data to verify the accuracy of the prediction structure; and the third part can be the basic prediction data for comprehensive application. For training the busy-hour prediction model, the first part should have as much data as possible to improve the reliability of the training; the second part should have less data so that the application can continuously calibrate the accuracy of the busy-hour prediction model's prediction results; and the third part should have as much comprehensive data as possible to cover the prediction needs of more users.

[0093] Understandably, as business volume changes, users’ recent business usage is more meaningful. Therefore, different weights (i.e., first weight and second weight) are assigned to data from different periods. Using formula (1), the historical busy time data that is closer to the current time period is assigned a larger weight, and the historical busy time data that is further away from the current time period is assigned a smaller weight. This can better reflect the user’s actual situation, effectively strengthen the weight of recent historical busy time data, and improve the usability of historical busy time data.

[0094] When the historical busy time data is the start time of a historical busy time, the first quantity is the number of historical busy time start times, the first weight is the weight corresponding to the historical busy time start time, the first random fluctuation data is the historical busy time start time with random fluctuations, the second quantity is the number of historical busy time start times with random fluctuations, and the first calibration data is the historical busy time start time with manual calibration, the busy time start time y1 can be obtained using formula (1). This busy time start time is the current busy time start time predicted based on the historical busy time start time. Similarly, when the historical busy time data is the end time of a historical busy time, the first random fluctuation data is the historical busy time end time with random fluctuations, and the first calibration data is the historical busy time end time with calibration, the busy time end time y1 can be obtained using formula (1). This busy time end time is the current busy time end time predicted based on the historical busy time end time.

[0095] ti can represent the i-th moment on day t, which is also the first target moment.

[0096] Historical busy time information can be pre-stored in electronic devices and can be directly retrieved later.

[0097] In some examples, if the current time period is within a busy period, the acquisition frequency is determined as the first frequency; if the current time period is not within a busy period, the acquisition frequency is determined as the second frequency, with the first frequency being less than the second frequency.

[0098] For example, if the current time period falls within a busy time frame, the first frequency could be once every 15 minutes. This prioritizes meeting user needs, obtains target performance parameters, and thus determines the quality of the target service. If the current time period does not fall within a busy time frame, the second frequency could be once every 500 milliseconds. This allows for timely acquisition of target performance parameters without affecting user experience, enabling timely determination of the target service quality and rapid, effective problem detection. The above values ​​are for illustrative purposes only and are not intended to limit this application. The first and second frequencies can be set according to actual circumstances and are not limited here.

[0099] For example, the code for a user busy-hour prediction model can be as follows:

[0100] y_hat_avg = test.copy()

[0101] fitl=sm.tsa.statespace.AMCIMA(train.Count, order=(2,1,4), seasonal_order=(0,1,1,7)).fit()

[0102] y_hat_avg['AWCIMA']=fit1.predict(start="09:01:01", end="16:01:01", dynamic=True)

[0103] plt.figure(figsize=(16,8))

[0104] plt.plot(train['Count'], label="Train')

[0105] plt.plot(test['Count'], label='Test')

[0106] plt.plot(y_hat_avg['AWCIMA'], label='AWCIMA')

[0107] plt.legend(loc='best')

[0108] plt.show()

[0109] In some implementations, the method further includes, before obtaining historical busy time information:

[0110] Acquire historical power outage information, which includes historical power outage data, the fourth quantity of historical power outage data, the third weight corresponding to the historical power outage data, the second random fluctuation data at the second target time, the fifth quantity of the second random fluctuation data, the fourth weight corresponding to the second random fluctuation data, the sixth quantity of the second calibration data, and the second calibration coefficient corresponding to the second calibration data.

[0111] Based on historical power outage information, determine whether the target terminal is in a non-power outage state;

[0112] Retrieve historical busy time information, including:

[0113] Obtain historical busy time information when the target terminal is not powered off.

[0114] In this embodiment, based on historical power outage information, it is possible to accurately determine whether the target terminal is in a non-power-out state. When the target terminal is in a non-power-out state, obtaining historical busy time information can reduce the number of times historical busy time information is obtained, thereby reducing the power consumption of electronic devices.

[0115] For example, historical power outage data may include the start time and end time of historical power outages. Correspondingly, the first quantity may include the number of historical power outage start times and the number of historical power outage end times. It is understood that the number of historical power outage start times is the same as the number of historical power outage end times.

[0116] For example, the second random fluctuation data may include power outage data of random fluctuations at the second target time. The second random fluctuation data may form a white noise sequence.

[0117] For example, the second calibration data may be historical power outage data for calibration.

[0118] For example, the non-power-off state can include the powered-on state, that is, the state connected to the power source. The power-off state can be the state disconnected from the power source.

[0119] In some examples, determining whether a target terminal is in a non-power-off state is based on historical power outage information, including:

[0120] Based on historical power outage information, determine the start and end times of the power outage;

[0121] Determine whether the target terminal is in a non-power-off state based on the start and end times of the power outage;

[0122] Among them, the j-th historical power outage data α j The fourth quantity b, and the third weight y corresponding to historical power outage data. (t-j) The second random fluctuation data ε at the second target time (t-j) Fifth quantity d, fourth weight β j The sixth quantity m, the second calibration coefficient μ j And the time between the start time y2 of the power outage and the end time y2 of the power outage satisfies formula (2):

[0123]

[0124] In this example, the start and end times of the power outage can be quickly determined using formula (2) and historical power outage information.

[0125] Formula (2) can be called the ACIMA (Autoregressive Correct Integrated Moving Average) algorithm, or the power outage prediction model. b, d and m can all represent the order of the power outage prediction model. Specifically, p can be the number of historical power outage data, q can be the number of white noise sequences related to the power outage, and n can be the number of calibrated historical power outage data.

[0126] In some examples, the training data for a power outage prediction model can be divided into three parts. The first part can be the basic data used to train user-busy power outage predictions; the second part can be the data to verify the accuracy of the prediction structure; and the third part can be the basic prediction data for comprehensive application. For training the power outage prediction model, the first part should have as much data as possible to improve the reliability of the training; the second part should have less data so that the accuracy of the prediction results can be continuously calibrated; and the third part should have as much comprehensive data as possible to cover the prediction needs of more users.

[0127] Understandably, the ACIMA algorithm is used to perform trend analysis on users' daily power-on and power-off behaviors (i.e., power outages and power-offs), modeling them as a linear function of the difference observations and residuals of previous time steps. At the same time, it takes into account time series that can be calibrated as needed. After installation and maintenance personnel report the deviation between the actual power-on and power-off times of users and the prediction, it can also be effectively calibrated, which can improve the consistency between the prediction results and the actual situation.

[0128] When the historical power outage data represents the start time of a historical power outage, the fourth quantity represents the number of historical power outage start times, the third weight represents the weight corresponding to the historical power outage start time, the second random fluctuation data represents the start time of a randomly fluctuating historical power outage, the fifth quantity represents the number of randomly fluctuating historical power outage start times, and the second calibration data represents the start time of a manually calibrated historical power outage, the power outage start time y2 can be obtained using formula (2). This power outage start time is the current power outage start time predicted based on the historical power outage start times. Similarly, when the historical power outage data represents the end time of a historical power outage, the second random fluctuation data represents the end time of a randomly fluctuating historical power outage, and the second calibration data represents the end time of a calibrated historical power outage, the power outage end time y2 can be obtained using formula (2). This power outage end time is the current power outage end time predicted based on the historical power outage end times.

[0129] tj can represent the j-th moment of day t, which is the second target moment. The values ​​of i and j can be set according to the actual situation; they can be equal or unequal, and there is no restriction here.

[0130] It should be noted that the first to fourth weights and the first to sixth quantities in this embodiment can be pre-stored in the electronic device and can be directly called later. The values ​​of each weight and each quantity can be set according to the actual situation and are not limited here.

[0131] Historical power outage information can be pre-stored in electronic devices and can be directly retrieved later.

[0132] For example, if the current time period or the current moment is between the start and end of the power outage, the target terminal is determined to be in a power outage state; if the current time period or the current moment is not between the start and end of the power outage, the target terminal is determined to be in a non-power outage state.

[0133] Understandably, if it is determined that the target terminal is in a power-off state, the steps from "obtaining historical power outage information" to "determining whether the target terminal is in a non-power-off state based on historical power outage information" can be repeated until it is determined that the target terminal is in a non-power-off state, and then subsequent steps such as "obtaining historical busy time information" can be executed.

[0134] For example, the code for a user power outage prediction model can be as follows:

[0135] from statsmodels.tsa.arima.model import ACIMA

[0136] from randominport random

[0137] time=[x+random()for x in range(1,1000)]

[0138] model=ACIMA(time,order=(1,1,1))

[0139] model_fit = model.fit()

[0140] yhat=model_fit.predict(len(time), len(time), typ='levels')

[0141] print(yhat)

[0142] In S120, after acquiring the target performance parameters, the electronic device can also compare the target performance parameters with the corresponding performance parameter thresholds to obtain the comparison results.

[0143] When the target performance parameter includes a target packet loss parameter, the corresponding performance parameter threshold includes a packet loss threshold; when the target performance parameter includes a target latency parameter, the corresponding performance parameter threshold includes a latency packet threshold; when the target performance parameter includes a packet loss threshold, the corresponding performance parameter threshold includes a packet loss threshold; when the target performance parameter includes a target jitter parameter, the corresponding performance parameter threshold includes a jitter threshold; when the target performance parameter includes a target bandwidth utilization, the corresponding performance parameter threshold includes a bandwidth utilization threshold.

[0144] In S130, after comparing the target performance parameters with the corresponding performance parameter thresholds, the electronic device can also determine the quality assessment result of the target service based on the comparison results.

[0145] In some implementations, the quality assessment result of the target service is determined based on the comparison results, including:

[0146] If all target performance parameters in the comparison results are greater than or equal to their corresponding performance parameter thresholds, the quality assessment result of the target service is determined to be passed.

[0147] If the comparison results show that the target performance parameter is lower than its corresponding performance parameter threshold, the quality assessment result of the target service is determined to be unsuccessful.

[0148] In this embodiment, by comparing the target performance parameters with their corresponding performance parameter thresholds, the quality assessment result of the target service can be quickly determined.

[0149] As an example, when the target performance parameters include target packet loss parameters, target latency parameters, target jitter parameters, and target bandwidth utilization, the performance parameter thresholds include packet loss thresholds, latency thresholds, jitter thresholds, and bandwidth utilization thresholds. If the target packet loss parameter is greater than or equal to the packet loss threshold, the target latency parameter is greater than or equal to the latency threshold, the target jitter parameter is greater than or equal to the jitter threshold, and the target bandwidth utilization is greater than or equal to the bandwidth utilization threshold, the quality assessment result for the target service is determined to be "pass".

[0150] As another example, when the target performance parameters include target packet loss parameters, target latency parameters, target jitter parameters, and target bandwidth utilization, the performance parameter thresholds include packet loss thresholds, latency thresholds, jitter thresholds, and bandwidth utilization thresholds. If the target packet loss parameter is less than the packet loss threshold, and / or the target latency parameter is less than the latency threshold, and / or the target jitter parameter is less than the jitter threshold, and / or the target bandwidth utilization is less than the bandwidth utilization threshold, the quality assessment result for the target service is determined to be unsuccessful.

[0151] Performance parameters such as packet loss threshold, latency threshold, jitter threshold, and bandwidth utilization threshold can be stored in the electronic device for later direct retrieval. Each threshold can be set according to actual conditions and is not limited here. The thresholds can be equal or unequal. For example, all thresholds can be 70%.

[0152] In some examples, after the target link is the primary link and the quality assessment result of the target service is unsuccessful, the electronic device can also simulate the switching mechanism between the primary link and the backup link, start the backup link tunnel, send the target performance parameters of the target service to the backup link, and repeat S110 to S130 to perform a quality assessment of the target service on the backup link.

[0153] In other words, this application embodiment utilizes an end-to-end operational quality assessment mechanism. In electronic devices such as PTN / SPN / miniaturized PTN, a TUNNEL quality assessment module (TQTM) and a PW data statistics module (PDSM) are designed. Based on the above two modules, the quality of the primary link is assessed. To address the pain point that the poor quality of the backup link cannot be effectively assessed, a primary and backup link switching mechanism is simulated to activate the backup link TUNNEL and send the assessment data to the backup link. Based on the quality assessment of the backup link through the TQTM module and the PDSM module, the assessment of the poor-quality terminal is initiated according to the assessment results of the primary and backup links, thus achieving a comprehensive assessment from the link to the terminal node.

[0154] In some examples, after determining that the quality assessment result for the target business is unsatisfactory, the method also includes:

[0155] Output poor quality warning information, which is used to indicate the poor quality of the target service in the target link.

[0156] For example, poor quality prompts can be output in the form of voice, text, or other means.

[0157] The specific content of the poor quality warning message can be set according to the actual situation, and is not limited here.

[0158] As an example, if the target link is the primary link and the quality assessment result of the target service is determined to be unsatisfactory, the quality improvement message can be the Active Link Quality Degradation (ALQD) message.

[0159] As another example, if the target link is a backup link and the quality assessment result of the target service is determined to be unsatisfactory, the quality defect warning message can be the Standby Link Quality Degradation (SLQD) warning message.

[0160] In this embodiment of the application, a quality defect warning can be output in a timely manner, which can then guide installation and maintenance personnel to handle potential problems in the backup link and / or the primary link.

[0161] In some implementations, the target link includes a primary link and a backup link;

[0162] If the quality assessment results of the target service are both unsuccessful in both the primary link and the backup link, obtain the current quality parameters of the target terminal. The current quality parameters include at least one of the current interruption alarm frequency and the current terminal network access time.

[0163] Determine the current quality score of the target terminal based on the current quality parameters.

[0164] In this embodiment, when the quality assessment results of the target service in both the primary link and the backup link are unsuccessful, obtaining the current quality parameters of the target terminal can reduce the number of times the current quality parameters are obtained and reduce the power consumption of the electronic device; based on the current quality parameters, the current quality score of the target terminal can be accurately determined.

[0165] Current quality parameters, such as the current interruption alarm frequency and the current terminal network access time, can be pre-stored in the electronic device for direct retrieval later.

[0166] In some implementations, the current quality score of the target terminal is determined based on the current quality parameters, including:

[0167] Input the current quality parameters into the quality identification model, use the quality identification model to identify the target terminal, and obtain the current quality score of the target terminal.

[0168] The quality identification model is trained using historical quality parameters, which include at least one of the following: historical interruption alarm frequency and historical terminal network access time. The historical quality parameters correspond to the current quality parameters.

[0169] In this embodiment, the current quality parameters are input into the quality identification model, and the model is used for identification, which can quickly and accurately determine the current quality score of the target terminal.

[0170] The correspondence between historical quality parameters and current quality parameters can be as follows: if the current quality parameters include the frequency of interruption alarms, then the historical quality parameters include the historical frequency of interruption alarms; if the current quality parameters include the terminal's network access time, then the historical quality parameters include the historical terminal's network access time.

[0171] For example, a quality identification model can be obtained by training a neural network model based on the regression principle of discrete data, using historical quality parameters and the historical quality scores corresponding to the historical quality parameters.

[0172] Historical quality parameters, such as the frequency of historical interruption alarms and the historical terminal network access time, as well as their corresponding historical quality scores, can also be pre-stored in electronic devices.

[0173] In some implementations, after determining the current quality score of the target terminal based on the current quality parameters, the following may also be included:

[0174] Based on the current quality score, determine whether a poor quality warning is triggered. The poor quality warning is used to instruct installation and maintenance personnel to repair or replace the target terminal.

[0175] For example, if the current quality score is less than or equal to the scoring threshold, a poor quality warning is triggered. If the current quality score is greater than the scoring threshold, a poor quality warning is not triggered, and the business quality assessment for the next cycle can be initiated. The scoring threshold can be set according to actual circumstances and is not limited here.

[0176] In some implementations, after determining that the quality assessment result of the target service is unsatisfactory, the method further includes:

[0177] Data can be transmitted via wired and / or wireless means.

[0178] As an example, in related technologies, data transmission cannot be achieved if the access segment optical cable fails. However, in this embodiment, when the wired channel is normal, the end-to-end network connectivity indicators (i.e., target packet loss parameters, target delay parameters, and target jitter parameters) of the Tunnel Quality Assessment Module (TQTM) and the target bandwidth utilization assessed by the Pseudo-wire Data Statistics Module (PDSM) can be transmitted via the network management service channel in a wired manner.

[0179] As another example, when the wired channel is abnormal, data transmission based on the mobile network can be achieved through the mobile wireless communication module within the target terminal, coupled with a mobile SIM card. For instance, the mobile wireless communication module may include a 5G wireless communication module that is compatible with 4G, enabling the 4G network when 5G signal is insufficient. Since the network connectivity evaluation results (i.e., quality assessment results) at either end A or Z of the leased line are consistent, when encountering services with a head-to-branch network structure, the head point can handle data transmission alone; the branch points do not need to configure wireless communication modules and mobile SIM cards, saving equipment and maintenance costs. Specifically, data transmission may include data backhaul.

[0180] For example, the embodiments of this application involve the following three emergency intervention mechanisms, which can effectively improve the accuracy of end-to-end service quality assessment and improve the bandwidth contention problem of user services.

[0181] Mechanism 1: Network Anomaly Intervention. When the target terminal is in an engineering state or has reported an emergency or critical warning, and installation and maintenance personnel are currently performing network operations or troubleshooting, quality assessment is not very meaningful at this time. TQTM and PDSM will stop working until the engineering state ends or the alarm is cleared. TQTM and PDSM will then automatically perform a quality assessment. Alternatively, a quality assessment activation command can be sent to the electronic device via a terminal to manually initiate the TQTM and PDSM quality assessment task. The engineering state can refer to the target terminal being under maintenance or during installation.

[0182] Mechanism Two: Intervention for Service Anomalies. When an electronic device determines that the current time period is not a busy period and the number of data packets on the PW (Power Controller) counted by the PDSM (Power Controller System) is less than the data threshold, a quality assessment of the target service is performed; this is called an off-peak assessment. When an electronic device determines that the current time period is a busy period or the number of data packets on the PW counted by the PDSM is greater than or equal to the data threshold, it indicates that the user is sending and receiving a large amount of data. If an off-peak assessment is performed, there may be bandwidth contention with the user, affecting the user experience. In this case, a busy-peak assessment of the target service is performed. The acquisition frequencies for off-peak and busy-peak assessments differ. The off-peak assessment is acquired at the second frequency; the busy-peak assessment is acquired at the first frequency.

[0183] Mechanism 3: Target Terminal Anomaly Intervention. When the target terminal is in a power-off state, it can no longer function normally. Electronic devices can suspend the scheduling and data acquisition of TQTM and PDSM until the target terminal switches to a non-power-off state.

[0184] For example, when an electronic device initiates an evaluation task, it first uses the ACIMA algorithm to analyze the user's daily power-on and power-off behavior to evaluate the power outage status. If a power outage is determined, the evaluation stops. If a non-power outage is determined, the ACIMA algorithm is used to simulate the user's actual situation to evaluate the busy time. If the busy time evaluation result is a busy time (i.e., the current time period is within a busy time period), busy time evaluation is initiated. If the busy time evaluation result is an idle time (i.e., the current time period is not within a busy time period), idle time evaluation is initiated. The busy time evaluation result or idle time evaluation result is compared with a pre-set threshold. If the busy time evaluation result or idle time evaluation result is worse than the threshold, a primary link quality poor ALQD alarm is reported. If the busy time evaluation result or idle time evaluation result is better than the threshold, the backup link is evaluated. The backup link evaluation result is then compared with a pre-set threshold. If the evaluation result is worse than the threshold, a backup link quality poor SLQD alarm is reported. If the evaluation result is better than the threshold, no alarm is reported, and the evaluation task for the next cycle begins. If both the primary and backup links report alarms simultaneously, the Artificial Intelligence (AI) capability for discrete data is invoked to perform an AI-based assessment of the terminal with poor quality. If the assessment identifies a poor quality terminal, the installation and maintenance personnel are guided to replace the terminal on-site. If no poor quality terminal is identified, no action is required, and the assessment task for the next cycle is initiated.

[0185] Based on the same inventive concept as the service quality assessment method provided in the above embodiments, this application also provides a service quality assessment apparatus. The above-mentioned service quality assessment generation apparatus will be described in detail below.

[0186] Figure 2This is a schematic diagram of a business quality assessment device provided in an embodiment of this application.

[0187] like Figure 2 As shown, the business quality assessment device provided in this application embodiment may include a first acquisition module 210, a comparison module 220, and a first determination module 230.

[0188] The first acquisition module 210 is used to acquire the target performance parameters of the target service in the target link of the target terminal. The target performance parameters include at least one of the target packet loss parameters, target latency parameters, target jitter parameters and target bandwidth utilization. The target link includes at least one of the primary link and the backup link.

[0189] The comparison module 220 is used to compare the target performance parameters with the corresponding performance parameter thresholds to obtain the comparison results. The performance parameter thresholds include at least one of the following: packet loss threshold, latency threshold, jitter threshold, and bandwidth utilization threshold.

[0190] The first determining module 230 is used to determine the quality assessment result of the target business based on the comparison results.

[0191] According to the service quality assessment apparatus provided in this application embodiment, the target performance parameters of the target service in the target link of the target terminal are first obtained, then the target performance parameters are compared with the corresponding performance parameter thresholds to obtain the comparison results, and then the quality assessment result of the target service is determined based on the comparison results. Thus, by comparing at least one of the target packet loss parameters, target latency parameters, target jitter parameters, and target bandwidth utilization with the corresponding performance parameter thresholds, the quality of the target service in the primary link and / or backup link can be accurately determined. Compared with the device-level determination of operational quality in related technologies, this application embodiment can determine operational quality at the service level, thereby improving the accuracy of operational quality determination.

[0192] In some alternative implementations, the first determining module 230 may be specifically used for:

[0193] If all target performance parameters in the comparison results are greater than or equal to their corresponding performance parameter thresholds, the quality assessment result of the target service is determined to be passed.

[0194] If the comparison results show that the target performance parameter is lower than its corresponding performance parameter threshold, the quality assessment result of the target service is determined to be unsuccessful.

[0195] In some alternative implementations, the business quality assessment apparatus may further include:

[0196] The second acquisition module is used to acquire historical busy time information, which includes historical busy time data, a first quantity of historical busy time data, a first weight corresponding to the historical busy time data, a first random fluctuation data at the first target time, a second quantity of the first random fluctuation data, a second weight corresponding to the first random fluctuation data, a third quantity of the first calibration data, and a first calibration coefficient corresponding to the first calibration data.

[0197] The second determination module is used to determine the peak time period based on historical peak time information;

[0198] The third module is used to determine the acquisition frequency based on the busy time period;

[0199] The first acquisition module 210 can also be specifically used for:

[0200] Based on the acquisition frequency, obtain the target performance parameters of the target service in the target link of the target terminal.

[0201] In some alternative implementations, the second determining module may specifically be used for:

[0202] Based on historical busy time information, determine the start and end times of busy times;

[0203] Among them, the i-th historical busy time data α i First quantity p, first weight y (t-i) The first random fluctuation data ε at the first target time (t-i) Second quantity q, second weight β i Third quantity n, first calibration coefficient μ i And the busy start time y1 or busy end time y1 satisfy formula (1):

[0204]

[0205] In some alternative implementations, the business quality assessment apparatus may further include:

[0206] The third acquisition module is used to acquire historical power outage information, which includes historical power outage data, the fourth quantity of historical power outage data, the third weight corresponding to the historical power outage data, the second random fluctuation data at the second target time, the fifth quantity of the second random fluctuation data, the fourth weight corresponding to the second random fluctuation data, the sixth quantity of the second calibration data, and the second calibration coefficient corresponding to the second calibration data.

[0207] The fourth determination module is used to determine whether the target terminal is in a non-power-off state based on historical power outage information;

[0208] The second acquisition module can be specifically used for:

[0209] Obtain historical busy time information when the target terminal is not powered off.

[0210] In some alternative implementations, the fourth determining module may specifically be used for:

[0211] Based on historical power outage information, determine the start and end times of the power outage;

[0212] Determine whether the target terminal is in a non-power-off state based on the start and end times of the power outage;

[0213] Among them, the j-th historical power outage data α j The fourth quantity b, and the third weight y corresponding to historical power outage data. (t-j) The second random fluctuation data ε at the second target time (t-j) Fifth quantity d, fourth weight β j The sixth quantity m, the second calibration coefficient μ j And the time between the start time y2 of the power outage and the end time y2 of the power outage satisfies formula (2):

[0214]

[0215] In some alternative implementations, the target link includes a primary link and a backup link;

[0216] Business quality assessment devices may also include:

[0217] The fourth acquisition module is used to acquire the current quality parameters of the target terminal when the quality assessment results of the target service in both the primary link and the backup link are unsuccessful. The current quality parameters include at least one of the current interruption alarm frequency and the current terminal network access time.

[0218] The fifth determination module is used to determine the current quality score of the target terminal based on the current quality parameters.

[0219] In some alternative implementations, the fifth determining module may be specifically used for:

[0220] Input the current quality parameters into the quality identification model, use the quality identification model to identify the target terminal, and obtain the current quality score of the target terminal.

[0221] The quality identification model is trained using historical quality parameters, which include at least one of the following: historical interruption alarm frequency and historical terminal network access time. The historical quality parameters correspond to the current quality parameters.

[0222] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation and the beneficial effects have been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0223] Based on the service quality assessment method and apparatus provided in the above embodiments, this application also provides an electronic device. The electronic device will be described in detail below.

[0224] Figure 3 A schematic diagram illustrating an embodiment of the electronic device provided in this application is shown.

[0225] An electronic device may include a processor 301 and a memory 302 storing computer program instructions.

[0226] Specifically, the processor 301 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0227] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 302 is non-volatile solid-state memory.

[0228] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0229] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any of the service quality assessment methods in the above embodiments.

[0230] In one example, the electronic device may also include a communication interface 303 and a bus 310. For example, Figure 3As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.

[0231] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0232] Bus 310 includes hardware, software, or both, that couples components of a service quality assessment device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0233] Furthermore, in conjunction with the service quality assessment methods in the above embodiments, this application embodiment can provide a computer-readable storage medium for implementation. This computer-readable storage medium stores computer program instructions; when executed by a processor, these computer program instructions implement any of the service quality assessment methods in the above embodiments.

[0234] Furthermore, in conjunction with the service quality assessment methods in the above embodiments, this application embodiment can provide a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, they implement any of the service quality assessment methods in the above embodiments.

[0235] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0236] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0237] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0238] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0239] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A business quality assessment method, characterized in that, include: Obtain the target performance parameters of the target service in the target link of the target terminal. The target performance parameters include at least one of the target packet loss parameters, target latency parameters, target jitter parameters, and target bandwidth utilization. The target link includes at least one of the primary link and the backup link. The target performance parameter is compared with the corresponding performance parameter threshold to obtain the comparison result. The performance parameter threshold includes at least one of packet loss threshold, latency threshold, jitter threshold and bandwidth utilization threshold. Based on the comparison results, the quality assessment result of the target service is determined; Before obtaining the target performance parameters of the target service in the target link of the target terminal, the method further includes: Historical busy time information is obtained, which includes historical busy time data, a first quantity of historical busy time data, a first weight corresponding to the historical busy time data, a first random fluctuation data of a first target time, a second quantity of the first random fluctuation data, a second weight corresponding to the first random fluctuation data, a third quantity of first calibration data, and a first calibration coefficient corresponding to the first calibration data. The first weight corresponding to the historical busy time data that is closer to the current time period is larger, and the first weight corresponding to the historical busy time data that is further away from the current time period is smaller. Based on the historical busy time information, determine the busy time period; The acquisition frequency is determined based on the busy time period. The acquisition of target performance parameters of the target service in the target link of the target terminal includes: Based on the acquisition frequency, the target performance parameters of the target service in the target link of the target terminal are obtained; The busy period includes a start time and an end time; determining the busy period based on the historical busy information includes: Based on the historical busy time information, determine the start time and end time of the busy time; Among them, the i-th historical busy time data The first quantity p, the first weight The first random fluctuation data at the first target time The second quantity q, the second weight The third quantity n, the first calibration coefficient And the busy start time y1 or the busy end time y1 satisfy formula (1): Official (1) Wherein, when y1 is the busy time start time, the Where p is the number of historical busy time start times, and p is the number of historical busy time start times. The weight corresponding to the start time of the historical busy time, where ti is the first target time. The q represents the number of historical busy time start times with random fluctuations. The weight corresponding to the start time of the historical busy time with random fluctuations, the The n represents the number of historical busy time start times for manual calibration. Alternatively, when y1 is the busy time end time, the The p represents the number of historical busy time end times. The weight corresponding to the end time of the historical busy time, where ti is the first target time, and the The q represents the number of historical busy time end times with random fluctuations. The weight corresponding to the end time of the historical busy time with random fluctuations, the The n represents the number of historical busy time ends during manual calibration.

2. The method according to claim 1, characterized in that, The step of determining the quality assessment result of the target service based on the comparison result includes: If all the target performance parameters in the comparison results are greater than or equal to their corresponding performance parameter thresholds, the quality assessment result of the target service is determined to be passed. If the target performance parameter is found to be less than its corresponding performance parameter threshold in the comparison results, the quality assessment result of the target service is determined to be unsuccessful.

3. The method according to claim 1, characterized in that, Before obtaining historical busy time information, the method includes: Acquire historical power outage information, which includes historical power outage data, a fourth quantity of the historical power outage data, a third weight corresponding to the historical power outage data, second random fluctuation data at the second target time, a fifth quantity of the second random fluctuation data, a fourth weight corresponding to the second random fluctuation data, a sixth quantity of the second calibration data, and a second calibration coefficient corresponding to the second calibration data. Based on the historical power outage information, determine whether the target terminal is in a non-power-out state; The acquisition of historical busy time information includes: If the target terminal is not powered off, obtain historical busy time information.

4. The method according to claim 3, characterized in that, The step of determining whether the target terminal is in a non-power-off state based on the historical power outage information includes: Based on the historical power outage information, determine the start and end times of the power outage; Based on the power outage start time and the power outage end time, determine whether the target terminal is in a non-power-out state; Among them, the j-th historical power outage data The fourth quantity b, and the third weight corresponding to the historical power outage data. Second random fluctuation data at the second target time The fifth quantity d, the fourth weight The sixth quantity m, the second calibration coefficient And the power outage start time y2 or the power outage end time y2 satisfy formula (2): Official (2).

5. The method according to claim 1, characterized in that, The target link includes the primary link and the backup link; If the quality assessment result of the target service fails in both the primary link and the backup link, the current quality parameters of the target terminal are obtained. The current quality parameters include at least one of the current interruption alarm frequency and the current terminal network access time. Based on the current quality parameters, determine the current quality score of the target terminal.

6. The method according to claim 5, characterized in that, Determining the current quality score of the target terminal based on the current quality parameters includes: The current quality parameters are input into the quality identification model, and the quality identification model is used for identification to obtain the current quality score of the target terminal. The quality identification model is trained using historical quality parameters, which include at least one of historical interruption alarm frequency and historical terminal network access time. The historical quality parameters correspond to the current quality parameters.

7. A business quality assessment device, characterized in that, include: The first acquisition module is used to acquire the target performance parameters of the target service in the target link of the target terminal. The target performance parameters include at least one of the target packet loss parameters, target latency parameters, target jitter parameters and target bandwidth utilization. The target link includes at least one of the primary link and the backup link. The comparison module is used to compare the target performance parameter with the corresponding performance parameter threshold to obtain the comparison result. The performance parameter threshold includes at least one of packet loss threshold, latency threshold, jitter threshold and bandwidth utilization threshold. The first determining module is used to determine the quality assessment result of the target service based on the comparison result; Before the first acquisition module acquires the target performance parameters of the target service in the target link of the target terminal, the device further includes: The second acquisition module is used to acquire historical busy time information, which includes historical busy time data, a first quantity of historical busy time data, a first weight corresponding to the historical busy time data, a first random fluctuation data of a first target time, a second quantity of the first random fluctuation data, a second weight corresponding to the first random fluctuation data, a third quantity of first calibration data, and a first calibration coefficient corresponding to the first calibration data. The first weight corresponding to the historical busy time data that is closer to the current time period is larger, and the first weight corresponding to the historical busy time data that is further away from the current time period is smaller. The second determining module is used to determine the busy time period based on the historical busy time information; The third determining module is used to determine the acquisition frequency based on the busy time period; The first acquisition module is used to acquire the target performance parameters of the target service in the target link of the target terminal, specifically for: Based on the acquisition frequency, the target performance parameters of the target service in the target link of the target terminal are obtained; The busy period includes a busy start time and a busy end time; the second determining module is used to determine the busy period based on the historical busy information, specifically for: Based on the historical busy time information, determine the start time and end time of the busy time; Among them, the i-th historical busy time data The first quantity p, the first weight The first random fluctuation data at the first target time The second quantity q, the second weight The third quantity n, the first calibration coefficient And the busy start time y1 or the busy end time y1 satisfy formula (1): Official (1) Wherein, when y1 is the busy time start time, the Where p is the number of historical busy time start times, and p is the number of historical busy time start times. The weight corresponding to the start time of the historical busy time, where ti is the first target time. The q represents the number of historical busy time start times with random fluctuations. The weight corresponding to the start time of the historical busy time with random fluctuations, the The n represents the number of historical busy time start times for manual calibration. Alternatively, when y1 is the busy time end time, the The p represents the number of historical busy time end times. The weight corresponding to the end time of the historical busy time, where ti is the first target time, and the The q represents the number of historical busy time end times with random fluctuations. The weight corresponding to the end time of the historical busy time with random fluctuations, the The n represents the number of historical busy time ends during manual calibration.

8. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the service quality assessment method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the service quality assessment method as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes computer program instructions that, when executed by a processor, implement the business quality assessment method as described in any one of claims 1 to 6.

Images