CN116132330A

Movatterモバイル変換

Info

Publication number: CN116132330A
Application number: CN202210817220.8A
Authority: CN
Inventors: 骆林; 唐蠡; 郭剑霓; 吴海英; 曾琳铖曦; 蒋宁
Original assignee: Mashang Consumer Finance Co Ltd
Current assignee: Mashang Consumer Finance Co Ltd
Priority date: 2022-07-12
Filing date: 2022-07-12
Publication date: 2023-05-16

Abstract

Translated fromChinese

本公开实施例公开了一种网络检测方法、网络检测模型训练方法及装置。所述网络检测方法包括：获取网络拓扑结构中包括的网络链路的链路信息，所述链路信息包括网络链路上的设备的指标信息；将链路信息输入至预先训练的网络检测模型中进行网络状况检测，得到网络状况检测结果；所述网络状况检测结果包括以下至少一项：所述网络链路是否异常的检测结果、所述网络链路上的设备是否异常的检测结果。本技术方案能够提高网络检测的效率和准确度。

The embodiment of the present disclosure discloses a network detection method, a network detection model training method and a device. The network detection method includes: obtaining link information of network links included in the network topology, the link information including index information of devices on the network links; inputting the link information into a pre-trained network detection model The network condition detection is carried out to obtain the network condition detection result; the network condition detection result includes at least one of the following: the detection result of whether the network link is abnormal, and the detection result of whether the equipment on the network link is abnormal. The technical solution can improve the efficiency and accuracy of network detection.

Description

Translated fromChinese

网络检测方法、网络检测模型训练方法及装置Network detection method, network detection model training method and device

技术领域Technical Field

本公开涉及人工智能技术领域，尤其涉及一种网络检测方法、网络检测模型训练方法及装置。The present disclosure relates to the field of artificial intelligence technology, and in particular to a network detection method, a network detection model training method and a device.

背景技术Background Art

相关技术中，通常是通过监测应用或宿主机的网络指标来检测网络质量，如APM(Application Performance Management，应用性能监控工具)监控服务，通过汇聚业务系统各处理环节的实时数据，分析业务系统各事务处理的交易路径和处理时间，从而实现对应用的全链路性能监测。但是，这种监控方式往往仅涉及宿主机的网络指标，例如对宿主机进行流量、带宽和数据包数量的监控，即，仅能对网络指标进行采集、整理以及可视化展示。在网络发生故障时，仅能从应用层面定位到服务之间的网络异常，而难以准确定位故障原因及发生故障的网络链路。若要定位故障原因及发生故障的网络链路，则还需结合其他监控设备或者结合人力，比如，为每条网络链路均配置一台监测设备，以监测每条网络链路的网络指标；或者，在网络收发出现问题时，通过人力来排查发生故障的网络链路。显然，这两种故障定位方式不仅效率低、且准确度低。In the related technology, the network quality is usually detected by monitoring the network indicators of the application or the host machine, such as the APM (Application Performance Management, application performance monitoring tool) monitoring service, which aggregates the real-time data of each processing link of the business system and analyzes the transaction path and processing time of each transaction processing of the business system, thereby realizing the full-link performance monitoring of the application. However, this monitoring method often only involves the network indicators of the host machine, such as monitoring the traffic, bandwidth and number of data packets of the host machine, that is, only the network indicators can be collected, sorted and visualized. When a network failure occurs, only the network anomaly between services can be located from the application level, and it is difficult to accurately locate the cause of the failure and the network link where the failure occurs. If the cause of the failure and the network link where the failure occurs are to be located, other monitoring equipment or manpower must be combined, for example, a monitoring device is configured for each network link to monitor the network indicators of each network link; or, when there is a problem with the network transmission and reception, the network link where the failure occurs is checked by manpower. Obviously, these two fault location methods are not only inefficient, but also inaccurate.

发明内容Summary of the invention

本公开实施例的目的是提供一种网络检测方法、网络检测模型训练方法及装置，提高网络检测的效率以及精确度。The purpose of the embodiments of the present disclosure is to provide a network detection method, a network detection model training method and a device to improve the efficiency and accuracy of network detection.

为解决上述技术问题，本公开实施例是这样实现的：To solve the above technical problems, the embodiments of the present disclosure are implemented as follows:

一方面，本公开实施例提供一种网络检测方法，包括：On the one hand, an embodiment of the present disclosure provides a network detection method, including:

获取网络拓扑结构中包括的网络链路的链路信息，所述链路信息包括所述网络链路上的设备的指标信息；Acquire link information of a network link included in the network topology structure, wherein the link information includes indicator information of a device on the network link;

将所述链路信息输入至预先训练的网络检测模型中进行网络状况检测，得到网络状况检测结果；其中，所述网络状况检测结果包括以下至少一项：所述网络链路是否异常的检测结果、所述网络链路上的设备是否异常的检测结果。The link information is input into a pre-trained network detection model to perform network status detection to obtain a network status detection result; wherein the network status detection result includes at least one of the following: a detection result of whether the network link is abnormal, and a detection result of whether the device on the network link is abnormal.

采用本公开实施例的技术方案，通过将网络拓扑结构中包括的网络链路的链路信息输入至预先训练的网络检测模型中，利用网络检测模型对网络链路进行网络状况检测，得到网络状况检测结果，包括网络链路是否异常的检测结果和/或网络链路上的设备是否异常的检测结果。可见，本技术方案提供了应用层以下的链路监控及设备监控机制，能够在网络出现异常时，准确定位到发生异常的网络链路和/或网络链路上发生异常的设备，从而准确检测出整个网络链路上可能潜在的异常情况，为网络异常排查和网络维护提供有力的数据支撑。进一步地，相较于现有技术中需要依赖人力来检测异常网络的方案而言，本技术方案能够自动化地定位到发生异常的网络链路和/或网络链路上发生异常的设备，无需用户参与，因此避免了人力因素可能带来的定位不准确情况，提升了网络异常定位的准确度。并且，通过预先训练网络检测模型，并通过网络检测模型来实现网络异常定位，使得网络异常定位的效率大大提升，节省了网络异常定位时间。By adopting the technical solution of the embodiment of the present disclosure, the link information of the network link included in the network topology structure is input into the pre-trained network detection model, and the network status detection result of the network link is performed using the network detection model to obtain the network status detection result, including the detection result of whether the network link is abnormal and/or the detection result of whether the device on the network link is abnormal. It can be seen that the technical solution provides a link monitoring and device monitoring mechanism below the application layer, which can accurately locate the abnormal network link and/or the abnormal device on the network link when the network is abnormal, so as to accurately detect the potential abnormal situation on the entire network link, and provide strong data support for network abnormality troubleshooting and network maintenance. Further, compared with the solution in the prior art that needs to rely on manpower to detect abnormal networks, the technical solution can automatically locate the abnormal network link and/or the abnormal device on the network link without user participation, thereby avoiding the inaccurate positioning situation that may be caused by human factors and improving the accuracy of network abnormality positioning. In addition, by pre-training the network detection model and realizing network abnormality positioning through the network detection model, the efficiency of network abnormality positioning is greatly improved, saving the network abnormality positioning time.

另一方面，本公开实施例提供一种网络检测模型训练方法，包括：On the other hand, an embodiment of the present disclosure provides a network detection model training method, including:

获取多个网络拓扑结构中的样本网络链路的样本链路信息，以及所述样本网络链路的标签信息；其中，所述样本网络链路包括：网络状况正常的样本网络链路和网络状况异常的样本网络链路；所述样本链路信息包括所述样本网络链路上的设备的指标信息；所述标签信息用于表征以下至少一项：所述样本网络链路是否异常、所述样本网络链路上的设备是否异常；Obtain sample link information of sample network links in multiple network topology structures, and label information of the sample network links; wherein the sample network links include: sample network links with normal network conditions and sample network links with abnormal network conditions; the sample link information includes indicator information of devices on the sample network links; the label information is used to characterize at least one of the following: whether the sample network link is abnormal, whether the device on the sample network link is abnormal;

将所述样本网络链路信息输入待训练的网络检测模型中，得到所述样本网络链路对应的分类结果，所述分类结果包括以下至少一项：所述样本网络链路是否异常、所述样本网络链路上的设备是否异常；Input the sample network link information into the network detection model to be trained to obtain a classification result corresponding to the sample network link, wherein the classification result includes at least one of the following: whether the sample network link is abnormal, and whether the device on the sample network link is abnormal;

根据所述样本网络链路的分类结果以及所述标签信息，对所述待训练的网络检测模型的模型参数进行调整。According to the classification result of the sample network link and the label information, the model parameters of the network detection model to be trained are adjusted.

采用本公开实施例的技术方案，通过将多个网络拓扑结构中包括的样本网络链路的样本链路信息(包括网络状况正常的样本网络链路和网络状况异常的样本网络链路)输入至待训练的网络检测模型中，得到样本网络链路对应的分类结果(包括样本网络链路是否异常和/或样本网络链路上的设备是否异常)，进而根据分类结果以及样本网络链路的标签信息，对待训练的网络检测模型的模型参数进行调整。可见，本技术方案通过预先训练网络检测模型，使得网络检测模型能够用于网络异常定位。从而利用网络检测模型来实现网络异常定位时，能够准确定位到发生异常的网络链路和/或网络链路上发生异常的设备，从而准确检测出整个网络链路上可能潜在的异常情况，为网络异常排查和网络维护提供有力的数据支撑。进一步地，相较于现有技术中需要依赖人力来检测异常网络的方案而言，本技术方案能够自动化地定位到发生异常的网络链路和/或网络链路上发生异常的设备，无需用户参与，因此避免了人力因素可能带来的定位不准确情况，提升了网络异常定位的准确度。此外，基于网络检测模型的智能化和自动化，使得网络异常定位的效率大大提升，节省了网络异常定位时间。By adopting the technical solution of the embodiment of the present disclosure, the sample link information of the sample network links included in the multiple network topology structures (including the sample network links with normal network conditions and the sample network links with abnormal network conditions) is input into the network detection model to be trained, and the classification results corresponding to the sample network links (including whether the sample network links are abnormal and/or whether the equipment on the sample network links is abnormal) are obtained, and then the model parameters of the network detection model to be trained are adjusted according to the classification results and the label information of the sample network links. It can be seen that the technical solution enables the network detection model to be used for network anomaly positioning by pre-training the network detection model. Therefore, when the network detection model is used to realize network anomaly positioning, the abnormal network link and/or the abnormal equipment on the network link can be accurately positioned, so as to accurately detect the potential abnormal conditions on the entire network link, and provide strong data support for network anomaly troubleshooting and network maintenance. Furthermore, compared with the solution in the prior art that needs to rely on manpower to detect abnormal networks, the technical solution can automatically locate the abnormal network link and/or the abnormal equipment on the network link without user participation, thereby avoiding the inaccurate positioning caused by human factors and improving the accuracy of network anomaly positioning. In addition, the intelligence and automation of network detection models greatly improves the efficiency of network anomaly locating and saves time.

再一方面，本公开实施例提供一种网络检测装置，包括：On the other hand, the present disclosure provides a network detection device, including:

第一获取模块，用于获取网络拓扑结构中包括的网络链路对应的链路信息，所述链路信息包括所述网络链路上的设备的指标信息；A first acquisition module, configured to acquire link information corresponding to a network link included in a network topology structure, wherein the link information includes indicator information of a device on the network link;

检测模块，用于将所述链路信息输入至预先训练的网络检测模型中进行网络状况检测，得到网络状况检测结果；其中，所述网络状况检测结果包括以下至少一项：所述网络链路是否异常的检测结果、所述网络链路上的设备是否异常的检测结果。A detection module is used to input the link information into a pre-trained network detection model to perform network status detection and obtain a network status detection result; wherein the network status detection result includes at least one of the following: a detection result of whether the network link is abnormal, and a detection result of whether the device on the network link is abnormal.

再一方面，本公开实施例提供一种网络检测模型训练装置，包括：On the other hand, the present disclosure provides a network detection model training device, including:

第二获取模块，用于获取多个网络拓扑结构中包括的样本网络链路的样本链路信息，以及所述样本网络链路的标签信息；其中，所述样本网络链路包括：网络状况正常的样本网络链路和网络状况异常的样本网络链路；所述样本链路信息包括所述样本网络链路上的设备的指标信息；所述标签信息用于表征以下至少一项：所述样本网络链路是否异常、所述样本网络链路上的设备是否异常；The second acquisition module is used to acquire sample link information of sample network links included in multiple network topology structures, and label information of the sample network links; wherein the sample network links include: sample network links with normal network conditions and sample network links with abnormal network conditions; the sample link information includes indicator information of devices on the sample network links; the label information is used to characterize at least one of the following: whether the sample network link is abnormal, whether the device on the sample network link is abnormal;

分类模块，用于将所述样本链路信息输入待训练的网络检测模型中，得到所述样本网络链路对应的分类结果，所述分类结果包括以下至少一项：所述样本网络链路是否异常、所述样本网络链路上的设备是否异常；A classification module, used for inputting the sample link information into the network detection model to be trained to obtain a classification result corresponding to the sample network link, wherein the classification result includes at least one of the following: whether the sample network link is abnormal, and whether the device on the sample network link is abnormal;

模型训练模块，用于根据所述样本网络链路的分类结果以及所述标签信息，对所述网络检测模型的模型参数进行调整。The model training module is used to adjust the model parameters of the network detection model according to the classification results of the sample network links and the label information.

再一方面，本公开实施例提供一种电子设备，包括处理器和与所述处理器电连接的存储器，所述存储器存储有计算机程序，所述处理器用于从所述存储器调用并执行所述计算机程序以实现上述的网络检测方法，或者，所述处理器用于从所述存储器调用并执行所述计算机程序以实现上述的网络检测模型训练方法。On the other hand, an embodiment of the present disclosure provides an electronic device, including a processor and a memory electrically connected to the processor, the memory storing a computer program, the processor being used to call and execute the computer program from the memory to implement the above-mentioned network detection method, or the processor being used to call and execute the computer program from the memory to implement the above-mentioned network detection model training method.

再一方面，本公开实施例提供一种存储介质，用于存储计算机程序，所述计算机程序能够被处理器执行以实现上述的网络检测方法，或者，所述计算机程序能够被处理器执行以实现上述的网络检测模型训练方法。On the other hand, an embodiment of the present disclosure provides a storage medium for storing a computer program, wherein the computer program can be executed by a processor to implement the above-mentioned network detection method, or the computer program can be executed by a processor to implement the above-mentioned network detection model training method.

附图说明BRIEF DESCRIPTION OF THE DRAWINGS

为了更清楚地说明本公开实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本公开中记载的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

图1是根据本公开一实施例的一种网络检测方法的示意性流程图；FIG1 is a schematic flow chart of a network detection method according to an embodiment of the present disclosure;

图2是根据本公开一实施例的一种网络检测方法的示意性原理图；FIG2 is a schematic diagram of a network detection method according to an embodiment of the present disclosure;

图3是根据本公开一实施例的一种网络拓扑结构的示意性结构图；FIG3 is a schematic structural diagram of a network topology structure according to an embodiment of the present disclosure;

图4是根据本公开一实施例的一种网络检测模型的示意性原理图；FIG4 is a schematic diagram of a network detection model according to an embodiment of the present disclosure;

图5是根据本公开一实施例的一种网络状况检测结果的示意性输出界面图；FIG5 is a schematic output interface diagram of a network status detection result according to an embodiment of the present disclosure;

图6是根据本公开一实施例的一种网络检测模型训练方法的示意性流程图；FIG6 is a schematic flow chart of a network detection model training method according to an embodiment of the present disclosure;

图7是根据本公开一实施例的一种网络检测模型训练过程的示意性原理图；FIG7 is a schematic diagram of a network detection model training process according to an embodiment of the present disclosure;

图8是根据本公开一实施例的一种网络检测装置的示意性框图；FIG8 is a schematic block diagram of a network detection device according to an embodiment of the present disclosure;

图9是根据本公开一实施例的一种网络检测模型训练装置的示意性框图；FIG9 is a schematic block diagram of a network detection model training device according to an embodiment of the present disclosure;

图10是根据本公开一实施例的一种电子设备的示意性框图。FIG. 10 is a schematic block diagram of an electronic device according to an embodiment of the present disclosure.

具体实施方式DETAILED DESCRIPTION

本公开实施例提供一种网络检测方法、网络检测模型训练方法及装置，提高网络检测的效率以及精确度。The embodiments of the present disclosure provide a network detection method, a network detection model training method and a device to improve the efficiency and accuracy of network detection.

为了使本技术领域的人员更好地理解本公开中的技术方案，下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都应当属于本公开保护的范围。In order to enable those skilled in the art to better understand the technical solutions in the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present disclosure.

在网络状况检测方面，现有技术中，通常是通过监测应用或宿主机的网络指标来检测网络质量，这种监控方式往往仅涉及宿主机的网络指标，例如对宿主机进行流量、带宽和数据包数量的监控，即，仅能对网络指标进行采集、整理以及可视化展示。在网络发生故障时，也仅能从应用层面定位到服务之间的网络异常，而难以准确定位故障原因及发生故障的网络链路。本公开实施例提供的网络检测方法，通过获取网络拓扑结构中包括的网络链路的链路信息，包括网络链路上设备的指标信息，并将网络链路信息输入至预先训练的网络检测模型中，利用网络检测模型对网络链路的网络状况进行检测，从而得到网络状况检测结果，包括网络链路是否异常的检测结果和/或网络链路上的设备是否异常的检测结果，因此完善了应用层以下的链路监控及设备监控机制，能够在网络出现异常时，准确定位到发生异常的网络链路和/或网络链路上发生异常的设备，从而准确检测出整个网络链路上可能潜在的异常情况，为网络异常排查和网络维护提供有力的数据支撑。此外，若网络链路出现异常，即使是轻微的时延，蔓延到实际的应用服务需要一定时间，也仍然会造成应用服务的滞后，给客户端造成不同程度的影响。因此，本公开实施例通过预先训练网络检测模型，并通过网络检测模型来实现网络异常定位，不仅能够定位到发生异常的网络链路，还能够定位到发生异常的设备，从而在网络出现异常的情况下及时排查出问题和原因，大大提升了网络异常定位的效率，节省了网络异常定位时间。In terms of network status detection, in the prior art, the network quality is usually detected by monitoring the network indicators of the application or the host. This monitoring method often only involves the network indicators of the host, such as monitoring the traffic, bandwidth and number of data packets of the host, that is, only the network indicators can be collected, sorted and visualized. When a network failure occurs, only the network anomaly between services can be located from the application level, and it is difficult to accurately locate the cause of the failure and the network link where the failure occurs. The network detection method provided by the embodiment of the present disclosure obtains the link information of the network link included in the network topology structure, including the indicator information of the device on the network link, and inputs the network link information into the pre-trained network detection model, and uses the network detection model to detect the network status of the network link, thereby obtaining a network status detection result, including a detection result of whether the network link is abnormal and/or a detection result of whether the device on the network link is abnormal, thereby improving the link monitoring and device monitoring mechanism below the application layer, and can accurately locate the abnormal network link and/or the abnormal device on the network link when the network is abnormal, so as to accurately detect the potential abnormal situation on the entire network link, and provide strong data support for network abnormality troubleshooting and network maintenance. In addition, if an abnormality occurs in a network link, even if it is a slight delay, it will take some time to spread to the actual application service, which will still cause a lag in the application service and cause varying degrees of impact on the client. Therefore, the disclosed embodiment pre-trains a network detection model and uses the network detection model to implement network anomaly location, which can not only locate the abnormal network link, but also locate the abnormal device, so that the problem and cause can be promptly checked when the network is abnormal, greatly improving the efficiency of network anomaly location and saving network anomaly location time.

本公开实施例提供的网络检测方法可由网络检测设备执行，或者由安装于网络检测设备中的软件执行，具体地，网络检测设备可以是终端设备或者服务端设备。The network detection method provided in the embodiments of the present disclosure may be executed by a network detection device, or by software installed in the network detection device. Specifically, the network detection device may be a terminal device or a server device.

图1是根据本公开一实施例的一种网络检测方法的示意性流程图，如图1所示，该方法包括：FIG. 1 is a schematic flow chart of a network detection method according to an embodiment of the present disclosure. As shown in FIG. 1 , the method includes:

S102，获取网络拓扑结构中包括的网络链路的链路信息，链路信息包括网络链路上的设备的指标信息。S102, obtaining link information of a network link included in the network topology structure, where the link information includes indicator information of a device on the network link.

可选地，链路信息除包括网络链路上的设备的指标信息外，还可包括网络链路的链路相关信息。链路相关信息可包括网络链路上包括的设备数量、设备信息、设备位置信息、链路标识信息(如链路名称)和链路流向，其中，设备信息可包括设备标识信息(如设备名称)、设备MAC地址(硬件地址、物理地址或链路地址)、设备类型等中的至少一项。Optionally, in addition to the indicator information of the devices on the network link, the link information may also include link-related information of the network link. The link-related information may include the number of devices included in the network link, device information, device location information, link identification information (such as link name) and link flow direction, wherein the device information may include at least one of device identification information (such as device name), device MAC address (hardware address, physical address or link address), device type, etc.

在获取链路相关信息时，首先获取网络拓扑结构，网络拓扑结构中包括一条或多条网络链路。其次，对网络拓扑结构进行解析，即可得到每条网络链路对应的链路相关信息。When obtaining link related information, first obtain the network topology structure, which includes one or more network links. Then, parse the network topology structure to obtain link related information corresponding to each network link.

在获取设备的指标信息时，可选地，设备本身具有采集自身指标信息的能力，因此，设备可向网络检测设备上报各自采集到的指标信息。可选地，可在设备上安装指标采集探针，指标采集探针与网络检测设备连接，指标采集探针具有采集设备的指标信息的能力，从而将采集到的指标信息传输至网络检测设备。When obtaining the indicator information of the device, optionally, the device itself has the ability to collect its own indicator information, so the device can report the indicator information collected to the network detection device. Optionally, an indicator collection probe can be installed on the device, and the indicator collection probe is connected to the network detection device. The indicator collection probe has the ability to collect the indicator information of the device, so as to transmit the collected indicator information to the network detection device.

S104，将网络链路信息输入至预先训练的网络检测模型中进行网络状况检测，得到网络状况检测结果；其中，网络状况检测结果包括以下至少一项：网络链路是否异常的检测结果、网络链路上的设备是否异常的检测结果。S104, input the network link information into a pre-trained network detection model to perform network status detection and obtain a network status detection result; wherein the network status detection result includes at least one of the following: a detection result of whether the network link is abnormal, and a detection result of whether the device on the network link is abnormal.

本实施例中，网络检测模型对网络状况检测结果的输出方式不受限定。可选地，网络检测模型可输出以下至少一项信息：发生异常的网络链路的链路标识信息、发生异常的设备的标识信息、发生异常的网络链路的链路状况分值、发生异常的设备的性能分值。其中，链路状况分值用于表征网络链路的链路状况好坏，分值越高，网络链路的链路状况就越好。设备的性能分值用于表征设备性能好坏，分值越高，设备的性能就越好。链路状况分值和设备性能分值的计算方式将在下述实施例中详细说明，此处不作赘述。In this embodiment, the network detection model is not limited in the way it outputs the network status detection results. Optionally, the network detection model may output at least one of the following information: link identification information of the network link where the abnormality occurs, identification information of the device where the abnormality occurs, link status score of the network link where the abnormality occurs, and performance score of the device where the abnormality occurs. Among them, the link status score is used to characterize the link status of the network link. The higher the score, the better the link status of the network link. The performance score of the device is used to characterize the performance of the device. The higher the score, the better the performance of the device. The calculation method of the link status score and the device performance score will be described in detail in the following embodiments and will not be repeated here.

图2是根据本公开一实施例的一种网络检测方法的示意性原理图。由图2可看出，获取到网络链路的链路信息后，仅需将链路信息输入预先训练的网络检测模型，即可得到网络状况检测结果，从而及时检测出整个网络链路上可能潜在的异常情况。下面详细说明本公开实施例提供的一种网络检测方法，首先介绍网络拓扑结构及其对应的网络链路信息。FIG2 is a schematic diagram of a network detection method according to an embodiment of the present disclosure. As can be seen from FIG2, after obtaining the link information of the network link, it is only necessary to input the link information into a pre-trained network detection model to obtain the network status detection result, thereby timely detecting the potential abnormal conditions on the entire network link. A network detection method provided by an embodiment of the present disclosure is described in detail below, first introducing the network topology structure and its corresponding network link information.

图3是根据本公开一实施例的一种网络拓扑结构的示意性结构图。如图3所示，网络拓扑结构中包括机房A和机房B，机房A中包括设备router1、router2、router3、switch1、switch2和gateway1，机房B中包括设备router4、router5、router6、switch3、switch4和gateway2，其中，router1、router2、router3、router4、router5和router6为路由器，switch1、switch2、switch3和switch4为交换机，gateway1和gateway2为网关。通过解析该网路拓扑结构，可得到如下表1所示的链路相关信息，其中包括各个设备的设备名称、设备位置信息、设备MAC地址和设备类型。FIG3 is a schematic diagram of a network topology structure according to an embodiment of the present disclosure. As shown in FIG3, the network topology structure includes computer room A and computer room B. Computer room A includes devices router1, router2, router3, switch1, switch2 and gateway1, and computer room B includes devices router4, router5, router6, switch3, switch4 and gateway2, wherein router1, router2, router3, router4, router5 and router6 are routers, switch1, switch2, switch3 and switch4 are switches, and gateway1 and gateway2 are gateways. By parsing the network topology structure, the link-related information shown in Table 1 below can be obtained, including the device name, device location information, device MAC address and device type of each device.

表1Table 1

设备名称Device Name设备位置信息Device location information设备MAC地址Device MAC address设备类型Device Typerouter1router1A机房-3柜1排A room - 3 cabinets, 1 rowaa-bb-xx-xx-23-12aa-bb-xx-xx-23-12路由器routerrouter2router2A机房-3柜2排A computer room - 3 cabinets, 2 rowsaa-bb-xx-xx-23-11aa-bb-xx-xx-23-11路由器routerrouter3router3A机房-3柜3排A computer room - 3 cabinets, 3 rowsaa-bb-xx-xx-23-13aa-bb-xx-xx-23-13路由器routerswitch1switch1A机房-2柜1排A computer room - 2 cabinets, 1 rowaa-bb-xx-xx-24-12aa-bb-xx-xx-24-12交换机switchswitch2switch2A机房-1柜1排A room - 1 cabinet 1 rowaa-bb-xx-xx-25-11aa-bb-xx-xx-25-11交换机switchgateway1gateway1A机房-1柜2排A room - 1 cabinet 2 rowsaa-bb-xx-xx-26-11aa-bb-xx-xx-26-11网关Gatewayrouter4router4B机房-2柜1排B room - 2 cabinets, 1 rowcc-bb-xx-xx-26-13cc-bb-xx-xx-26-13路由器routerrouter5router5B机房-2柜2排Room B - 2 cabinets, 2 rowscc-bb-xx-xx-26-12cc-bb-xx-xx-26-12路由器routerrouter6router6B机房-2柜4排Room B - 2 cabinets, 4 rowscc-bb-xx-xx-26-15cc-bb-xx-xx-26-15路由器routerswitch3switch3B机房-1柜2排B room - 1 cabinet 2 rowscc-bb-xx-xx-27-13cc-bb-xx-xx-27-13交换机switchswitch4switch4B机房-1柜1排B room - 1 cabinet 1 rowcc-bb-xx-xx-27-12cc-bb-xx-xx-27-12交换机switchgateway2gateway2B机房-3柜1排Room B - 3 cabinets, 1 rowcc-bb-xx-xx-36-12cc-bb-xx-xx-36-12网关Gateway

由表1可看出，通过解析网络拓扑结果，可获知从根节点的网关到叶子节点的路由器的链路相关信息，从而解析出多条单向的网络链路，下表2示意性地列举出部分网络链路的链路相关信息，包括链路名称、网络链路中的设备数量和链路流向。As can be seen from Table 1, by parsing the network topology results, the link-related information from the gateway of the root node to the router of the leaf node can be obtained, thereby parsing multiple unidirectional network links. The following Table 2 schematically lists the link-related information of some network links, including the link name, the number of devices in the network link, and the link flow direction.

表2Table 2

需要说明的是，图3仅是示意性地示出一种网络拓扑结构，在实际应用中，网络拓扑结构中能够包括的网络链路数量可以是一条或多条，每条网络链路上包括的设备也可以是一个或多个，本公开实施例对网络拓扑结构中的网络链路和设备的数量均不作限定。It should be noted that Figure 3 only schematically shows a network topology structure. In actual applications, the number of network links that can be included in the network topology structure can be one or more, and the number of devices included in each network link can also be one or more. The embodiments of the present disclosure do not limit the number of network links and devices in the network topology structure.

在一个实施例中，如图4所示，网络检测模型包括设备评分层、网络链路评分层和分类层，基于此，将网络链路信息输入至预先训练的网络检测模型中，对网络链路进行网络状况检测时，可通过网络检测模型的各个层具体执行为以下动作。In one embodiment, as shown in FIG4 , the network detection model includes a device scoring layer, a network link scoring layer, and a classification layer. Based on this, the network link information is input into a pre-trained network detection model. When the network status of the network link is detected, the following actions can be specifically performed through each layer of the network detection model.

网络检测模型的设备评分层，用于根据网络链路上的设备的指标信息，计算网络链路上的设备的性能分值。The device scoring layer of the network detection model is used to calculate the performance score of the device on the network link based on the indicator information of the device on the network link.

其中，在计算设备的性能分值时，可首先确定设备的每个指标信息对应的第一权重，设备的指标信息可包括网络抖动、网络丢包、网络时延和网络带宽中的至少一项信息。其次，根据设备的指标信息以及每个指标信息对应的第一权重，确定设备的性能分值。When calculating the performance score of a device, the first weight corresponding to each indicator information of the device may be determined first, and the indicator information of the device may include at least one of network jitter, network packet loss, network delay and network bandwidth. Secondly, the performance score of the device is determined based on the indicator information of the device and the first weight corresponding to each indicator information.

可选地，设备的性能分值的计算方式可表示为以下公式(1)：Optionally, the performance score of the device may be calculated as follows:

其中，score(device)表示设备的性能分值，weight_k表示第k个指标信息对应的第一权重，metric_k表示第k个指标信息(或设备指标值)，n表示设备的指标信息的数量。Among them, score(device) represents the performance score of the device, weight_k represents the first weight corresponding to the k-th indicator information, metric_k represents the k-th indicator information (or device indicator value), and n represents the number of indicator information of the device.

由于不同设备在网络链路中承担的角色不同，因此对于不同类型的设备而言，其核心指标也有所不同。例如，路由器对应的核心指标为网络抖动和网络丢包，交换机对应的核心指标为网络带宽、网络时延和网络丢包，网关对应的核心指标为网络时延和网络抖动。对于不同类型的设备而言，同一指标信息对应的第一权重可相同或不同，如下表3所示。Since different devices play different roles in the network link, the core indicators for different types of devices are also different. For example, the core indicators for routers are network jitter and network packet loss, the core indicators for switches are network bandwidth, network latency and network packet loss, and the core indicators for gateways are network latency and network jitter. For different types of devices, the first weight corresponding to the same indicator information can be the same or different, as shown in Table 3 below.

表3Table 3

需要说明的是，表3所列举的权重值仅是示意性地举例，在实际应用中，可根据不同的设备类型对各个第一权重值进行有针对性的、灵活的定义和设置。It should be noted that the weight values listed in Table 3 are merely illustrative examples. In actual applications, each first weight value may be defined and set in a targeted and flexible manner according to different device types.

网络检测模型的网络链路评分层，用于根据网络链路上的设备的性能分值，计算网络链路的链路状况分值。The network link scoring layer of the network detection model is used to calculate the link status score of the network link according to the performance score of the device on the network link.

其中，在计算链路状况分值时，可首先确定网络链路上的每个设备对应的第二权重，进而根据每个设备对应的第二权重以及每个设备的性能分值，确定网络链路的链路状况分值。设备对应的第二权重用于表示对应设备在网络链路上的重要程度。When calculating the link status score, the second weight corresponding to each device on the network link can be first determined, and then the link status score of the network link can be determined according to the second weight corresponding to each device and the performance score of each device. The second weight corresponding to the device is used to indicate the importance of the corresponding device on the network link.

可选地，链路状况分值的计算方式可表示为以下公式(2)：Optionally, the link status score can be calculated as follows:

其中，Score(link)表示链路状况分值，weight(device_i)表示网络链路上的第i个设备对应的第二权重，score(device_i)表示第i个设备的性能分值，m为网络链路上包括的设备数量。可选地，若根据公式(2)计算出的链路状况分值不是整数，则可以对计算出的分值进行取整处理，如向上取整或者向下取整。Wherein, Score(link) represents the link status score, weight(device_i ) represents the second weight corresponding to the i-th device on the network link, score(device_i ) represents the performance score of the i-th device, and m is the number of devices included in the network link. Optionally, if the link status score calculated according to formula (2) is not an integer, the calculated score can be rounded up or down.

可选地，可根据设备对应的设备类型，确定网络链路上的设备对应的第二权重。设备对应的设备类型不同，则设备对应的第二权重也有所不同，如表4所示。Optionally, the second weight corresponding to the device on the network link may be determined according to the device type corresponding to the device. If the device type corresponding to the device is different, the second weight corresponding to the device is also different, as shown in Table 4.

表4Table 4

设备类型Device Type第二权重Second weight路由器router0.60.6交换机switch0.70.7网关Gateway0.90.9

网络检测模型的分类层，用于根据网络链路对应的链路状况分值，确定网络链路是否异常；和/或，根据网络链路上的设备的性能分值，确定网络链路上的设备是否异常。The classification layer of the network detection model is used to determine whether a network link is abnormal based on the link status score corresponding to the network link; and/or determine whether a device on the network link is abnormal based on the performance score of the device on the network link.

其中，若网络链路的链路状况分值小于第一预设阈值，则确定网络链路异常。若网络链路的链路状况分值大于或等于第一预设阈值，则确定网络链路正常。If the link status score of the network link is less than the first preset threshold, the network link is determined to be abnormal. If the link status score of the network link is greater than or equal to the first preset threshold, the network link is determined to be normal.

沿用上表2所示的网络链路，各个网络链路的链路状况分值如下表5所示。假设第一预设阈值为8，则表5中所示的网络链路Link8为网络状况异常的网络链路。Using the network links shown in Table 2 above, the link status scores of the network links are shown in Table 5. Assuming that the first preset threshold is 8, the network link Link8 shown in Table 5 is a network link with abnormal network status.

表5Table 5

在一个实施例中，网络检测模型的分类层在确定出发生异常的网络链路(以下简称为异常网络链路)之后，还可根据异常网络链路上的每个设备的性能分值，确定异常网络链路上的设备是否异常。具体地，若异常网络链路上的设备的性能分值小于第二预设阈值，则确定设备异常。若异常网络链路上的设备的性能分值大于或等于第二预设阈值，则确定设备正常。In one embodiment, after determining the abnormal network link (hereinafter referred to as the abnormal network link), the classification layer of the network detection model can also determine whether the device on the abnormal network link is abnormal according to the performance score of each device on the abnormal network link. Specifically, if the performance score of the device on the abnormal network link is less than the second preset threshold, the device is determined to be abnormal. If the performance score of the device on the abnormal network link is greater than or equal to the second preset threshold, the device is determined to be normal.

可见，本实施例提供的技术方案在网络出现异常时，不仅能够准确定位到发生异常的网络链路，还能够定位到异常网络链路上发生异常的设备，从而在网络出现异常的情况下及时排查出问题和原因，大大提升了网络异常定位的效率，节省了网络异常定位时间。It can be seen that the technical solution provided by this embodiment can not only accurately locate the network link where the abnormality occurs, but also locate the device where the abnormality occurs on the abnormal network link when an abnormality occurs in the network, so as to promptly find out the problem and cause when an abnormality occurs in the network, greatly improving the efficiency of locating network abnormalities and saving network abnormality locating time.

在一个实施例中，链路信息还包括网络链路上的设备的位置信息。在确定设备异常之后，可确定异常设备的位置信息，从而将异常设备的位置信息提供至前端，以使前端维护人员根据异常设备的位置信息准确定位到异常设备，从而对异常设备进行维修，快速解决网络异常问题。In one embodiment, the link information also includes the location information of the device on the network link. After determining that the device is abnormal, the location information of the abnormal device can be determined, and the location information of the abnormal device can be provided to the front end, so that the front-end maintenance personnel can accurately locate the abnormal device according to the location information of the abnormal device, thereby repairing the abnormal device and quickly solving the network abnormality problem.

在一个实施例中，若异常网络链路包括多条，则网络检测模型的分类层还可按照每条异常网络链路的链路状况分值，对多条异常网络链路的链路信息进行排序，并按照排序结果输出多条异常网络链路的链路信息。In one embodiment, if there are multiple abnormal network links, the classification layer of the network detection model can also sort the link information of the multiple abnormal network links according to the link status score of each abnormal network link, and output the link information of the multiple abnormal network links according to the sorting results.

在一个实施例中，在检测到存在异常网络链路时，可发出预警信息，预警信息用于标识网络拓扑结构中存在异常网络链路。预警信息可包括异常网络链路的链路标识信息(如链路名称)、异常网络链路上的异常设备的标识信息(如设备名称)、异常设备的位置信息等中的至少一项。In one embodiment, when an abnormal network link is detected, an early warning message may be issued, and the early warning message is used to identify the presence of an abnormal network link in the network topology. The early warning message may include at least one of link identification information (such as link name) of the abnormal network link, identification information (such as device name) of an abnormal device on the abnormal network link, and location information of the abnormal device.

本实施例中，可将网络状况检测结果输出在显示屏上，并发出预警信息，预警信息可通过文字和/或语音的形式输出，比如在显示窗口中输出“网络链路Link8出现异常！”，同时发出响铃。In this embodiment, the network status detection result can be output on the display screen and a warning message can be issued. The warning message can be output in the form of text and/or voice, such as outputting "Network link Link8 is abnormal!" in the display window and sounding a bell at the same time.

图5是根据本公开一实施例的一种网络状况检测结果的示意性输出界面图，如图5所示，检测结果显示窗口中用于显示网络状况检测结果，显示内容可包括：异常网络链路、链路流向、异常设备以及异常设备位置(即异常设备的位置信息)。预警窗口用于显示预警信息。检测结果显示窗口和预警窗口可以显示在同一界面上，或者，预警窗口以弹窗的形式显示于检测结果上方。FIG5 is a schematic output interface diagram of a network status detection result according to an embodiment of the present disclosure. As shown in FIG5, the detection result display window is used to display the network status detection result, and the displayed content may include: abnormal network links, link flows, abnormal devices, and abnormal device locations (i.e., location information of abnormal devices). The warning window is used to display warning information. The detection result display window and the warning window can be displayed on the same interface, or the warning window is displayed above the detection result in the form of a pop-up window.

由图5可看出，采用本实施例提供的网络检测方法，前端维护人员可以直观地查看到异常网络链路的链路相关信息，从而根据异常设备位置准确定位到异常设备，进而对异常设备进行维修，快速解决网络异常问题。As can be seen from Figure 5, by adopting the network detection method provided in this embodiment, the front-end maintenance personnel can intuitively view the link-related information of the abnormal network link, so as to accurately locate the abnormal device according to the position of the abnormal device, and then repair the abnormal device to quickly solve the network abnormality problem.

图6是根据本公开一实施例的一种网络检测模型训练方法的示意性流程图，如图6所示，该方法包括：FIG6 is a schematic flow chart of a network detection model training method according to an embodiment of the present disclosure. As shown in FIG6 , the method includes:

S602，获取多个网络拓扑结构中包括的样本网络链路的样本链路信息，以及样本网络链路的标签信息；其中，样本网络链路包括：网络状况正常的样本网络链路和网络状况异常的样本网络链路；样本链路信息包括样本网络链路上的设备的指标信息；标签信息用于表征以下至少一项：样本网络链路是否异常、样本网络链路上的设备是否异常。S602, obtaining sample link information of sample network links included in multiple network topology structures, and label information of the sample network links; wherein the sample network links include: sample network links with normal network conditions and sample network links with abnormal network conditions; the sample link information includes indicator information of devices on the sample network links; the label information is used to characterize at least one of the following: whether the sample network link is abnormal, whether the device on the sample network link is abnormal.

可选地，样本链路信息除包括设备的指标信息外，还可包括样本网络链路的链路相关信息。链路相关信息可包括样本网络链路中包括的设备数量、设备信息、设备位置信息、链路标识信息(如链路名称)和链路流向，其中，设备信息可包括设备标识信息(如设备名称)、设备MAC地址、设备类型等中的至少一项。Optionally, the sample link information may include link-related information of the sample network link in addition to the device indicator information. The link-related information may include the number of devices included in the sample network link, device information, device location information, link identification information (such as link name) and link flow direction, wherein the device information may include at least one of device identification information (such as device name), device MAC address, device type, etc.

在获取链路相关信息时，首先获取网络拓扑结构，网络拓扑结构中包括一条或多条样本网络链路。其次，对网络拓扑结构进行解析，即可得到样本网络链路对应的链路相关信息。When obtaining link related information, first obtain the network topology structure, which includes one or more sample network links. Then, parse the network topology structure to obtain link related information corresponding to the sample network link.

在获取设备的指标信息时，可选地，设备本身具有采集自身指标信息的能力，因此，每个设备可上报各自采集到的指标信息。可选地，可在设备上安装指标采集探针，指标采集探针具有采集设备的指标信息的能力，从而上报采集到的指标信息。When obtaining the indicator information of the device, optionally, the device itself has the ability to collect its own indicator information, so each device can report the indicator information collected by itself. Optionally, an indicator collection probe can be installed on the device, and the indicator collection probe has the ability to collect the indicator information of the device, so as to report the collected indicator information.

S604，将样本链路信息输入待训练的网络检测模型中，得到样本网络链路对应的分类结果，分类结果包括以下至少一项：样本网络链路是否异常、样本网络链路上的设备是否异常。S604, input the sample link information into the network detection model to be trained to obtain a classification result corresponding to the sample network link, where the classification result includes at least one of the following: whether the sample network link is abnormal, and whether the device on the sample network link is abnormal.

如何利用待训练的网络检测模型对样本网络链路进行分类，将在下述实施例中详细说明，此处暂不赘述。How to classify sample network links using the network detection model to be trained will be described in detail in the following embodiments and will not be described in detail here.

S606，根据样本网络链路的分类结果以及标签信息，对待训练的网络检测模型的模型参数进行调整。S606: Adjust the model parameters of the network detection model to be trained according to the classification results and label information of the sample network links.

本实施例中，通过对待训练的网络检测模型的模型参数进行多次调整，以实现对待训练的网络检测模型进行迭代训练，从而得到训练后的网络检测模型。In this embodiment, the model parameters of the network detection model to be trained are adjusted multiple times to achieve iterative training of the network detection model to be trained, thereby obtaining a trained network detection model.

采用本公开实施例的技术方案，通过将多个网络拓扑结构中包括的样本网络链路的样本链路信息(包括网络状况正常的样本网络链路和网络状况异常的样本网络链路)输入至待训练的网络检测模型中，得到样本网络链路对应的分类结果(包括样本网络链路是否异常和/或样本网络链路上的设备是否异常)，进而根据分类结果以及样本网络链路的标签信息，对网络检测模型的模型参数进行调整。可见，本技术方案通过预先训练网络检测模型，使得网络检测模型能够用于网络异常定位。从而利用网络检测模型来实现网络异常定位时，能够准确定位到发生异常的网络链路和/或网络链路上发生异常的设备，从而准确检测出整个网络链路上可能潜在的异常情况，为网络异常排查和网络维护提供有力的数据支撑。进一步地，相较于现有技术中需要依赖人力来检测异常网络的方案而言，本技术方案能够自动化地定位到发生异常的网络链路和/或网络链路上发生异常的设备，无需用户参与，因此避免了人力因素可能带来的定位不准确情况，提升了网络异常定位的准确度。此外，基于网络检测模型的智能化和自动化，使得网络异常定位的效率大大提升，节省了网络异常定位时间。By adopting the technical solution of the embodiment of the present disclosure, the sample link information of the sample network links included in the multiple network topology structures (including the sample network links with normal network conditions and the sample network links with abnormal network conditions) is input into the network detection model to be trained, and the classification results corresponding to the sample network links (including whether the sample network links are abnormal and/or whether the equipment on the sample network links is abnormal) are obtained, and then the model parameters of the network detection model are adjusted according to the classification results and the label information of the sample network links. It can be seen that the technical solution enables the network detection model to be used for network anomaly positioning by pre-training the network detection model. Therefore, when the network detection model is used to realize network anomaly positioning, the abnormal network link and/or the abnormal equipment on the network link can be accurately positioned, so as to accurately detect the potential abnormal conditions on the entire network link, and provide strong data support for network anomaly troubleshooting and network maintenance. Furthermore, compared with the solution in the prior art that needs to rely on manpower to detect abnormal networks, the technical solution can automatically locate the abnormal network link and/or the abnormal equipment on the network link without user participation, thereby avoiding the inaccurate positioning caused by human factors and improving the accuracy of network anomaly positioning. In addition, the intelligence and automation of network detection models greatly improves the efficiency of network anomaly locating and saves time.

在一个实施例中，网络检测模型的模型参数包括以下至少一种：In one embodiment, the model parameters of the network detection model include at least one of the following:

(1)设备的各指标信息对应的第一权重，设备的指标信息可包括网络抖动、网络丢包、网络时延和网络带宽中的至少一项信息。(1) A first weight corresponding to each indicator information of a device, where the indicator information of the device may include at least one of network jitter, network packet loss, network delay and network bandwidth.

(2)网络链路上的每个设备对应的第二权重，设备对应的第二权重用于表示对应设备在网络链路上的重要程度。(2) A second weight corresponding to each device on the network link. The second weight corresponding to the device is used to indicate the importance of the corresponding device on the network link.

(3)异常网络链路对应的与链路状况分值相关的第一预设阈值。(3) A first preset threshold value related to the link status score corresponding to the abnormal network link.

(4)异常设备对应的与设备的性能分值相关的第二预设阈值。(4) A second preset threshold value corresponding to the abnormal device and related to the performance score of the device.

在一个实施例中，待训练的网络检测模型包括：设备评分层、网络链路评分层和分类层。基于此，将样本链路信息输入待训练的网络检测模型中，以得到样本网络链路对应的分类结果时，可通过待训练的网络检测模型的各个层具体执行为以下动作。In one embodiment, the network detection model to be trained includes: a device scoring layer, a network link scoring layer, and a classification layer. Based on this, when the sample link information is input into the network detection model to be trained to obtain the classification result corresponding to the sample network link, the following actions can be specifically performed through each layer of the network detection model to be trained.

待训练的网络检测模型的设备评分层，用于根据样本网络链路上的设备的指标信息，计算样本网络链路上的设备的性能分值。The device scoring layer of the network detection model to be trained is used to calculate the performance score of the device on the sample network link according to the indicator information of the device on the sample network link.

其中，在计算设备的性能分值时，可首先确定设备的指标信息对应的第一权重，设备的指标信息可包括网络抖动、网络丢包、网络时延和网络带宽中的至少一项信息。其次，根据设备的指标信息以及每个指标信息对应的第一权重，确定设备的性能分值。设备的性能分值的计算方式可表示为以上公式(1)，由于公式(1)已在上述实施例中进行详细说明，因此此处不再赘述。Among them, when calculating the performance score of the device, the first weight corresponding to the indicator information of the device can be determined first, and the indicator information of the device may include at least one of network jitter, network packet loss, network delay and network bandwidth. Secondly, according to the indicator information of the device and the first weight corresponding to each indicator information, the performance score of the device is determined. The calculation method of the performance score of the device can be expressed as the above formula (1). Since formula (1) has been described in detail in the above embodiment, it will not be repeated here.

待训练的网络检测模型的网络链路评分层，用于根据样本网络链路上的设备的性能分值，计算样本网络链路的链路状况分值。The network link scoring layer of the network detection model to be trained is used to calculate the link status score of the sample network link according to the performance score of the device on the sample network link.

其中，在计算链路状况分值时，可首先确定样本网络链路上的每个设备对应的第二权重，进而根据每个设备对应的第二权重以及每个设备的性能分值，确定样本网络链路的链路状况分值。链路状况分值的计算方式可表示为以上公式(2)，由于公式(2)已在上述实施例中进行详细说明，因此此处不再赘述。When calculating the link status score, the second weight corresponding to each device on the sample network link can be first determined, and then the link status score of the sample network link can be determined according to the second weight corresponding to each device and the performance score of each device. The calculation method of the link status score can be expressed as the above formula (2). Since formula (2) has been described in detail in the above embodiment, it will not be repeated here.

待训练的网络检测模型的分类层，用于根据样本网络链路的链路状况分值，确定样本网络链路是否异常；和/或，根据样本网络链路上的设备的性能分值，确定样本网络链路上的设备是否异常。The classification layer of the network detection model to be trained is used to determine whether the sample network link is abnormal based on the link status score of the sample network link; and/or, to determine whether the device on the sample network link is abnormal based on the performance score of the device on the sample network link.

其中，利用待训练的网络检测模型的分类层确定样本网络链路是否异常和/或设备是否异常的具体过程，与上述实施例中利用网络检测模型确定待检测的网络链路是否异常和/或设备是否异常的过程类似，此处不再重复。Among them, the specific process of using the classification layer of the network detection model to be trained to determine whether the sample network link is abnormal and/or whether the device is abnormal is similar to the process of using the network detection model to determine whether the network link to be detected is abnormal and/or whether the device is abnormal in the above embodiment, and will not be repeated here.

在一个实施例中，若样本网络链路的分类结果不满足预设分类条件，则根据分类结果调整待训练的网络检测模型的模型参数，并将样本链路信息重新输入调整参数后的网络检测模型中对样本网络链路进行分类；若分类结果满足预设分类条件，则停止迭代，得到训练后的网络检测模型。In one embodiment, if the classification result of the sample network link does not meet the preset classification conditions, the model parameters of the network detection model to be trained are adjusted according to the classification results, and the sample link information is re-input into the network detection model with adjusted parameters to classify the sample network link; if the classification result meets the preset classification conditions, the iteration is stopped to obtain the trained network detection model.

其中，预设分类条件可包括以下至少一项：分类结果的准确率大于或等于预设准确率阈值、迭代次数达到预设次数阈值。预设准确率阈值可根据对网络检测模型的精确度要求来设定。预设准确率阈值越高，则网络检测模型的精确度越高。The preset classification condition may include at least one of the following: the accuracy of the classification result is greater than or equal to the preset accuracy threshold, and the number of iterations reaches the preset number threshold. The preset accuracy threshold may be set according to the accuracy requirement of the network detection model. The higher the preset accuracy threshold, the higher the accuracy of the network detection model.

图7是根据本公开一实施例的一种网络检测模型训练方法的示意性原理图。在图7中，通过将样本链路信息输入至待训练的网络检测模型中，利用待训练的网络检测模型的各个层对样本链路信息进行处理，得到样本网络链路的分类结果。若分类结果满足预设分类条件，则停止迭代，得到训练后的网络检测模型；若分类结果不满足预设分类条件，则调整待训练的网络检测模型的模型参数，并基于调整模型参数之后的网络检测模型，再次对样本网络链路进行分类，最终得到训练后的网络检测模型。FIG7 is a schematic diagram of a network detection model training method according to an embodiment of the present disclosure. In FIG7, by inputting sample link information into the network detection model to be trained, the sample link information is processed using each layer of the network detection model to be trained to obtain the classification result of the sample network link. If the classification result meets the preset classification condition, the iteration is stopped to obtain the trained network detection model; if the classification result does not meet the preset classification condition, the model parameters of the network detection model to be trained are adjusted, and based on the network detection model after the model parameters are adjusted, the sample network link is classified again to finally obtain the trained network detection model.

综上，已经对本主题的特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作可以按照不同的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序，以实现期望的结果。在某些实施方式中，多任务处理和并行处理可以是有利的。In summary, specific embodiments of the present subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing may be advantageous.

以上为本公开实施例提供的网络检测方法及网络检测模型训练方法。基于同样的思路，本公开实施例还提供一种网络检测装置及网络检测模型训练装置。The above is a network detection method and a network detection model training method provided by the embodiments of the present disclosure. Based on the same idea, the embodiments of the present disclosure also provide a network detection device and a network detection model training device.

图8是根据本公开一实施例的一种网络检测装置的示意性框图，如图8所示，该装置包括：FIG8 is a schematic block diagram of a network detection device according to an embodiment of the present disclosure. As shown in FIG8 , the device includes:

第一获取模块81，用于获取网络拓扑结构中包括的网络链路的链路信息，所述链路信息包括所述网络链路上的设备的指标信息；Afirst acquisition module 81 is used to acquire link information of a network link included in the network topology structure, wherein the link information includes indicator information of a device on the network link;

检测模块82，用于将所述链路信息输入至预先训练的网络检测模型中进行网络状况检测，得到网络状况检测结果；其中，所述网络状况检测结果包括以下至少一项：所述网络链路是否异常的检测结果、所述网络链路上的设备是否异常的检测结果。Thedetection module 82 is used to input the link information into a pre-trained network detection model to perform network status detection and obtain a network status detection result; wherein the network status detection result includes at least one of the following: a detection result of whether the network link is abnormal, and a detection result of whether the device on the network link is abnormal.

在一个实施例中，所述网络检测模型包括：设备评分层、网络链路评分层和分类层；In one embodiment, the network detection model includes: a device scoring layer, a network link scoring layer, and a classification layer;

所述设备评分层，用于根据所述网络链路上的设备的指标信息，计算所述网络链路上的设备的性能分值；The device scoring layer is used to calculate the performance score of the device on the network link according to the indicator information of the device on the network link;

所述网络链路评分层，用于根据所述网络链路上的设备的性能分值，计算所述网络链路的链路状况分值；The network link scoring layer is used to calculate the link status score of the network link according to the performance score of the device on the network link;

所述分类层，用于根据所述网络链路的链路状况分值，确定所述网络链路是否异常；和/或，根据所述网络链路上的设备的性能分值，确定所述网络链路上的设备是否异常。The classification layer is used to determine whether the network link is abnormal based on the link status score of the network link; and/or determine whether the device on the network link is abnormal based on the performance score of the device on the network link.

在一个实施例中，所述检测模块82包括：In one embodiment, thedetection module 82 includes:

第一确定单元，用于确定所述设备的每个指标信息对应的第一权重，所述指标信息包括网络抖动、网络丢包、网络时延和网络带宽中的至少一项信息；A first determining unit, configured to determine a first weight corresponding to each indicator information of the device, wherein the indicator information includes at least one of network jitter, network packet loss, network delay, and network bandwidth;

第二确定单元，用于根据所述设备的指标信息以及每个指标信息对应的所述第一权重，确定所述设备的性能分值。The second determining unit is used to determine the performance score of the device according to the indicator information of the device and the first weight corresponding to each indicator information.

第三确定单元，用于确定所述网络链路上的每个设备对应的第二权重，所述第二权重用于表示对应设备在所述网络链路上的重要程度；A third determining unit, configured to determine a second weight corresponding to each device on the network link, wherein the second weight is used to indicate the importance of the corresponding device on the network link;

第四确定单元，用于根据每个设备对应的所述第二权重以及每个设备的所述性能分值，确定所述网络链路的链路状况分值。The fourth determining unit is used to determine the link status score of the network link according to the second weight corresponding to each device and the performance score of each device.

在一个实施例中，所述第三确定单元还用于：In one embodiment, the third determining unit is further configured to:

根据所述设备对应的设备类型，确定所述设备对应的第二权重。A second weight corresponding to the device is determined according to a device type corresponding to the device.

在一个实施例中，若异常网络链路包括多条，则所述分类层还用于按照每条异常网络链路的链路状况分值，对多条异常网络链路的链路信息进行排序，并按照排序结果输出所述多条异常网络链路的链路信息。In one embodiment, if there are multiple abnormal network links, the classification layer is further used to sort the link information of the multiple abnormal network links according to the link status score of each abnormal network link, and output the link information of the multiple abnormal network links according to the sorting result.

本领域的技术人员应可理解，上述网络检测装置能够用来实现前文所述的网络检测方法，其中的细节描述应与前文方法部分描述类似，为避免繁琐，此处不另赘述。Those skilled in the art should understand that the above-mentioned network detection device can be used to implement the network detection method described above, and the detailed description thereof should be similar to the description of the method part above, and will not be further described here to avoid redundancy.

采用本公开实施例的装置，通过获取网络拓扑结构中包括的网络链路的链路信息输入至预先训练的网络检测模型中，利用网络检测模型对网络链路进行网络状况检测，得到网络状况检测结果，包括网络链路是否异常的检测结果和/或网络链路上的设备是否异常的检测结果。可见，该装置提供了应用层以下的链路监控及设备监控机制，能够在网络出现异常时，准确定位到发生异常的网络链路和/或网络链路上发生异常的设备，从而准确检测出整个网络链路上可能潜在的异常情况，为网络异常排查和网络维护提供有力的数据支撑。进一步地，相较于现有技术中需要依赖人力来检测异常网络的方案而言，本技术方案能够自动化地定位到发生异常的网络链路和/或网络链路上发生异常的设备，无需用户参与，因此避免了人力因素可能带来的定位不准确情况，提升了网络异常定位的准确度。并且，通过预先训练网络检测模型，并通过网络检测模型来实现网络异常定位，使得网络异常定位的效率大大提升，节省了网络异常定位时间。The device of the embodiment of the present disclosure is adopted, by obtaining the link information of the network link included in the network topology structure and inputting it into the pre-trained network detection model, the network detection model is used to detect the network status of the network link, and the network status detection result is obtained, including the detection result of whether the network link is abnormal and/or the detection result of whether the device on the network link is abnormal. It can be seen that the device provides a link monitoring and device monitoring mechanism below the application layer, which can accurately locate the abnormal network link and/or the abnormal device on the network link when the network is abnormal, so as to accurately detect the potential abnormal situation on the entire network link, and provide strong data support for network abnormality troubleshooting and network maintenance. Further, compared with the solution in the prior art that needs to rely on manpower to detect abnormal networks, the technical solution can automatically locate the abnormal network link and/or the abnormal device on the network link without user participation, thereby avoiding the inaccurate positioning situation that may be caused by human factors and improving the accuracy of network abnormality positioning. In addition, by pre-training the network detection model and realizing network abnormality positioning through the network detection model, the efficiency of network abnormality positioning is greatly improved, and the network abnormality positioning time is saved.

图9是根据本公开另一实施例的一种网络检测装置的示意性框图，如图9所示，该装置包括：FIG. 9 is a schematic block diagram of a network detection device according to another embodiment of the present disclosure. As shown in FIG. 9 , the device includes:

第二获取模块91，用于获取多个网络拓扑结构中的样本网络链路的样本链路信息，以及所述样本网络链路的标签信息；其中，所述样本网络链路包括：网络状况正常的样本网络链路和网络状况异常的样本网络链路；所述样本链路信息包括所述样本网络链路上的设备的指标信息；所述标签信息用于表征以下至少一项：所述样本网络链路是否异常、所述样本网络链路上的设备是否异常；Thesecond acquisition module 91 is used to acquire sample link information of sample network links in multiple network topology structures, and label information of the sample network links; wherein the sample network links include: sample network links with normal network conditions and sample network links with abnormal network conditions; the sample link information includes indicator information of devices on the sample network links; the label information is used to characterize at least one of the following: whether the sample network link is abnormal, whether the device on the sample network link is abnormal;

分类模块92，用于将所述样本链路信息输入待训练的网络检测模型中，得到所述样本网络链路对应的分类结果，所述分类结果包括以下至少一项：所述样本网络链路是否异常、所述样本网络链路上的设备是否异常；Aclassification module 92 is used to input the sample link information into the network detection model to be trained to obtain a classification result corresponding to the sample network link, wherein the classification result includes at least one of the following: whether the sample network link is abnormal, and whether the device on the sample network link is abnormal;

模型训练模块93，用于根据所述样本网络链路的分类结果以及所述标签信息，对所述网络检测模型的模型参数进行调整。Themodel training module 93 is used to adjust the model parameters of the network detection model according to the classification results of the sample network links and the label information.

在一个实施例中，所述待训练的网络检测模型包括：设备评分层、网络链路评分层和分类层；In one embodiment, the network detection model to be trained includes: a device scoring layer, a network link scoring layer, and a classification layer;

所述设备评分层，用于根据所述样本网络链路上的设备的指标信息，计算所述样本网络链路上的设备的性能分值；The device scoring layer is used to calculate the performance score of the device on the sample network link according to the indicator information of the device on the sample network link;

所述网络链路评分层，用于根据所述样本网络链路上的设备的性能分值，计算所述样本网络链路的链路状况分值；The network link scoring layer is used to calculate the link status score of the sample network link according to the performance score of the device on the sample network link;

所述分类层，用于根据所述样本网络链路的链路状况分值，确定所述样本网络链路是否异常；和/或，根据所述样本网络链路上的设备的性能分值，确定所述样本网络链路上的设备是否异常。The classification layer is used to determine whether the sample network link is abnormal based on the link status score of the sample network link; and/or determine whether the device on the sample network link is abnormal based on the performance score of the device on the sample network link.

采用本公开实施例的装置，通过获取多个网络拓扑结构中包括的样本网络链路的样本链路信息(包括网络状况正常的样本网络链路和网络状况异常的样本网络链路)输入至待训练的网络检测模型中，得到样本网络链路对应的分类结果(包括样本网络链路是否异常和/或样本网络链路上的设备是否异常)，进而根据分类结果以及样本网络链路的标签信息，对网络检测模型的模型参数进行调整。可见，该装置通过预先训练网络检测模型，使得网络检测模型能够用于网络异常定位。从而利用网络检测模型来实现网络异常定位时，能够准确定位到发生异常的网络链路和/或网络链路上发生异常的设备，从而准确检测出整个网络链路上可能潜在的异常情况，为网络异常排查和网络维护提供有力的数据支撑。进一步地，相较于现有技术中需要依赖人力来检测异常网络的方案而言，本技术方案能够自动化地定位到发生异常的网络链路和/或网络链路上发生异常的设备，无需用户参与，因此避免了人力因素可能带来的定位不准确情况，提升了网络异常定位的准确度。此外，基于网络检测模型的智能化和自动化，使得网络异常定位的效率大大提升，节省了网络异常定位时间。The device of the embodiment of the present disclosure obtains sample link information of sample network links included in multiple network topology structures (including sample network links with normal network conditions and sample network links with abnormal network conditions) and inputs them into the network detection model to be trained to obtain the classification results corresponding to the sample network links (including whether the sample network links are abnormal and/or whether the equipment on the sample network links is abnormal), and then adjusts the model parameters of the network detection model according to the classification results and the label information of the sample network links. It can be seen that the device pre-trains the network detection model so that the network detection model can be used for network anomaly positioning. Therefore, when the network detection model is used to realize network anomaly positioning, the abnormal network link and/or the abnormal equipment on the network link can be accurately positioned, so as to accurately detect the potential abnormal conditions on the entire network link, and provide strong data support for network anomaly troubleshooting and network maintenance. Furthermore, compared with the solution in the prior art that needs to rely on manpower to detect abnormal networks, the present technical solution can automatically locate the abnormal network link and/or the abnormal equipment on the network link without user participation, thereby avoiding the inaccurate positioning caused by human factors and improving the accuracy of network anomaly positioning. In addition, the intelligence and automation of network detection models greatly improves the efficiency of network anomaly locating and saves time.

本领域的技术人员应可理解，上述网络检测模型训练装置能够用来实现前文所述的网络检测模型训练方法，其中的细节描述应与前文方法部分描述类似，为避免繁琐，此处不另赘述。Those skilled in the art should understand that the above-mentioned network detection model training device can be used to implement the network detection model training method described above, and the detailed description thereof should be similar to the description of the method part above, and will not be further described here to avoid tediousness.

基于同样的思路，本公开实施例还提供一种电子设备，如图10所示。电子设备可因配置或性能不同而产生比较大的差异，可以包括一个或一个以上的处理器1001和存储器1002，存储器1002中可以存储有一个或一个以上存储应用程序或数据。其中，存储器1002可以是短暂存储或持久存储。存储在存储器1002的应用程序可以包括一个或一个以上模块(图示未示出)，每个模块可以包括对电子设备中的一系列计算机可执行指令。更进一步地，处理器1001可以设置为与存储器1002通信，在电子设备上执行存储器1002中的一系列计算机可执行指令。电子设备还可以包括一个或一个以上电源1003，一个或一个以上有线或无线网络接口1004，一个或一个以上输入输出接口1005，一个或一个以上键盘1006。Based on the same idea, the embodiment of the present disclosure also provides an electronic device, as shown in FIG10. The electronic device may have relatively large differences due to different configurations or performances, and may include one ormore processors 1001 andmemory 1002, and thememory 1002 may store one or more storage applications or data. Among them, thememory 1002 may be a short-term storage or a persistent storage. The application stored in thememory 1002 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the electronic device. Furthermore, theprocessor 1001 may be configured to communicate with thememory 1002 and execute a series of computer executable instructions in thememory 1002 on the electronic device. The electronic device may also include one ormore power supplies 1003, one or more wired orwireless network interfaces 1004, one or more input andoutput interfaces 1005, and one ormore keyboards 1006.

具体在本实施例中，电子设备包括有存储器，以及一个或一个以上的程序，其中一个或者一个以上程序存储于存储器中，且一个或者一个以上程序可以包括一个或一个以上模块，且每个模块可以包括对电子设备中的一系列计算机可执行指令，且经配置以由一个或者一个以上处理器执行该一个或者一个以上程序包含用于进行以下计算机可执行指令：Specifically in this embodiment, the electronic device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions for the electronic device, and the one or more programs are configured to be executed by one or more processors, including the following computer executable instructions:

采用本公开实施例的技术方案，通过将网络拓扑结构中包括的网络链路的链路信息输入至预先训练的网络检测模型中，利用网络检测模型对网络链路进行网络状况进行检测，得到网络状况检测结果，包括网络链路是否异常的检测结果和/或网络链路上的设备是否异常的检测结果。可见，本技术方案提供了应用层以下的链路监控及设备监控机制，能够在网络出现异常时，准确定位到发生异常的网络链路和/或网络链路上发生异常的设备，从而准确检测出整个网络链路上可能潜在的异常情况，为网络异常排查和网络维护提供有力的数据支撑。进一步地，相较于现有技术中需要依赖人力来检测异常网络的方案而言，本技术方案能够自动化地定位到发生异常的网络链路和/或网络链路上发生异常的设备，无需用户参与，因此避免了人力因素可能带来的定位不准确情况，提升了网络异常定位的准确度。并且，通过预先训练网络检测模型，并通过网络检测模型来实现网络异常定位，使得网络异常定位的效率大大提升，节省了网络异常定位时间。By adopting the technical solution of the embodiment of the present disclosure, the link information of the network link included in the network topology structure is input into the pre-trained network detection model, and the network status of the network link is detected by using the network detection model to obtain the network status detection result, including the detection result of whether the network link is abnormal and/or the detection result of whether the device on the network link is abnormal. It can be seen that the technical solution provides a link monitoring and device monitoring mechanism below the application layer, which can accurately locate the abnormal network link and/or the abnormal device on the network link when the network is abnormal, so as to accurately detect the potential abnormal situation on the entire network link, and provide strong data support for network abnormality troubleshooting and network maintenance. Further, compared with the solution in the prior art that needs to rely on manpower to detect abnormal networks, the technical solution can automatically locate the abnormal network link and/or the abnormal device on the network link without user participation, thereby avoiding the inaccurate positioning situation that may be caused by human factors and improving the accuracy of network abnormality positioning. In addition, by pre-training the network detection model and realizing network abnormality positioning through the network detection model, the efficiency of network abnormality positioning is greatly improved, saving the network abnormality positioning time.

具体在另一实施例中，电子设备包括有存储器，以及一个或一个以上的程序，其中一个或者一个以上程序存储于存储器中，且一个或者一个以上程序可以包括一个或一个以上模块，且每个模块可以包括对电子设备中的一系列计算机可执行指令，且经配置以由一个或者一个以上处理器执行该一个或者一个以上程序包含用于进行以下计算机可执行指令：Specifically in another embodiment, the electronic device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions for the electronic device, and the one or more programs are configured to be executed by one or more processors, including computer executable instructions for performing the following:

获取多个网络拓扑结构中的样本网络链路的样本链路信息，以及所述样本网络链路的标签信息；其中，所述样本网络链路包括：网络状况正常的样本网络链路和网络状况异常的样本网络链路；所述样本链路信息包括所述样本网络链路上的设备的指标信息；所述标签信息用于表征以下至少一项：所述样本网络链路是否异常、所述样本网络链路上的设备是否异常；Obtaining sample link information of sample network links in multiple network topology structures and label information of the sample network links; wherein the sample network links include: sample network links with normal network conditions and sample network links with abnormal network conditions; the sample link information includes indicator information of devices on the sample network links; the label information is used to characterize at least one of the following: whether the sample network link is abnormal, whether the device on the sample network link is abnormal;

本公开实施例还提出了一种存储介质，该存储介质存储一个或多个计算机程序，该一个或多个计算机程序包括指令，该指令当被包括多个应用程序的电子设备执行时，能够使该电子设备执行上述网络检测方法实施例的各个过程，并具体用于执行：The embodiment of the present disclosure further proposes a storage medium, which stores one or more computer programs, wherein the one or more computer programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to perform each process of the above network detection method embodiment, and are specifically used to perform:

本公开实施例还提出了一种存储介质，该存储介质存储一个或多个计算机程序，该一个或多个计算机程序包括指令，该指令当被包括多个应用程序的电子设备执行时，能够使该电子设备执行上述网络检测模型训练方法实施例的各个过程，并具体用于执行：The present disclosure also provides a storage medium that stores one or more computer programs. The one or more computer programs include instructions. When the instructions are executed by an electronic device including multiple application programs, the electronic device can execute each process of the above network detection model training method embodiment, and are specifically used to execute:

获取多个网络拓扑结构中的样本网络链路的样本链路信息，以及所述样本网络链路的标签信息；其中，所述样本网络链路包括：网络状况正常的样本网络链路和网络状况异常的样本网络链路；所述样本链路信息包括所述样本网络链路上的设备的指标信息；所述标签信息用于表征以下至少一项：所述样本网络链路是否网络状况异常、所述样本网络链路上的设备是否异常；Obtain sample link information of sample network links in multiple network topology structures, and label information of the sample network links; wherein the sample network links include: sample network links with normal network conditions and sample network links with abnormal network conditions; the sample link information includes indicator information of devices on the sample network links; the label information is used to characterize at least one of the following: whether the network condition of the sample network link is abnormal, and whether the device on the sample network link is abnormal;

根据所述样本网络链路的分类结果以及所述标签信息，对所述网络检测模型的模型参数进行调整。According to the classification result of the sample network link and the label information, the model parameters of the network detection model are adjusted.

上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的，计算机例如可以为个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

为了描述的方便，描述以上装置时以功能分为各种单元分别描述。当然，在实施本公开时可以把各单元的功能在同一个或多个软件和/或硬件中实现。For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present disclosure, the functions of each unit can be implemented in the same or multiple software and/or hardware.

本领域内的技术人员应明白，本公开的实施例可提供为方法、系统、或计算机程序产品。因此，本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

本公开是参照根据本公开实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。The present disclosure is described with reference to the flowchart and/or block diagram of the method, device (system), and computer program product according to the embodiment of the present disclosure. It should be understood that each process and/or box in the flowchart and/or block diagram, as well as the combination of the process and/or box in the flowchart and/or block diagram 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, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one process or multiple processes in the flowchart and/or one box or multiple boxes in the block diagram.

这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。In a typical configuration, a computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.

内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and/or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

本公开可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本公开，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。The present disclosure may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present disclosure may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

以上所述仅为本公开的实施例而已，并不用于限制本公开。对于本领域技术人员来说，本公开可以有各种更改和变化。凡在本公开的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本公开的权利要求范围之内。The above description is only an embodiment of the present disclosure and is not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the scope of the claims of the present disclosure.