Abstract: A data processing method, a server, and a data collection device are provided. The method includes: obtaining, by a server, first network key performance indicator KPI data and performance data of a first set-top box STB, where the first network KPI data is network KPI data of a first video service stream, and the first STB is an STB that receives the first video service stream; and calculating, by the server, first video quality of experience QoE of the first video service stream based on an associated model, the first network KPI data, and the performance data of the first STB, where the associated model is a model obtained through training based on historical data, and the associated model is used by the server to calculate video QoE based on network KPI data and performance data of an STB.

Abstract: A network congestion control method, a node and a system are disclosed, where the method is applied to a spine-leaf network system. The method includes: a spine node receives network information sent by the at least one leaf node, where the network information includes network topology information of the leaf node and a network performance indicator of the leaf node; networks the at least one leaf node and the spine node based on the network topology information of the at least one leaf node, to obtain a combined network topology; and if the combined network topology is a global network topology of the spine-leaf network system, performs network congestion control on the at least one leaf node based on the network performance indicator of the at least one leaf node.

Abstract: The technology of this disclosure relates to a method, an apparatus, a device, a storage medium, and a system for determining a collection period. The technology relates to the field of machine learning technologies. In this disclosure, a machine learning model is obtained by using a training dataset collected based on candidate collection periods of X features, and a candidate collection period of each of the X features is determined as a target collection period of each feature based on the obtained machine learning model and a first condition. Because the target collection period of each feature is greater than a minimum collection period of each feature, subsequently, if data is collected based on the target collection period of each feature, an amount of the collected data is reduced, to reduce collection load of a device and memory occupied by sampled data, thereby reducing time redundancy.

Abstract: This application provides a network quality monitoring method and apparatus. A network quality monitoring apparatus obtains network running data, where the network running data includes dynamic data corresponding to a plurality of sampling periods and static data that are of an AP; determines one channel efficiency value of the AP based on each of a plurality of groups of dynamic data of the AP, so as to obtain a plurality of channel efficiency values of the AP; determines a channel efficiency baseline of the AP based on the static data of the AP; and determines, based on the plurality of channel efficiency values of the AP and the channel efficiency baseline of the AP, network quality of a wireless local area network in which the AP is located.

Abstract: A device identification method, apparatus, and system are provided. A management device or a collection device first determines a network traffic feature of a to-be-identified device based on a first dataset. The first dataset includes a plurality of pieces of first data, and each piece of first data includes a data amount of a data packet that is of the to-be-identified device and that is collected within one first periodicity. Then, the management device or the collection device determines a device type of the to-be-identified device based on a device identification model and the network traffic feature of the to-be-identified device.

Abstract: A network device inputs first network status information of the network device in a first time period to an ECN inference model, to obtain an inference result that is output by the ECN inference model based on the first network status information. Then, the network device sends an ECN parameter sample to an analysis device that manages the network device, where the ECN parameter sample includes the first network status information and a target ECN configuration parameter corresponding to the first network status information, and the target ECN configuration parameter is obtained based on the inference result. The network device receives an updated ECN inference model sent by the analysis device.

Abstract: A network device inputs first network status information of the network device in a first time period to an ECN inference model, to obtain an inference result that is output by the ECN inference model based on the first network status information. Then, the network device sends an ECN parameter sample to an analysis device that manages the network device, where the ECN parameter sample includes the first network status information and a target ECN configuration parameter corresponding to the first network status information, and the target ECN configuration parameter is obtained based on the inference result. The network device receives an updated ECN inference model sent by the analysis device.

Abstract: This application provides a data collection method and a device. A data collection device determines, based on a threshold corresponding to a target indicator, a collection interval for to-be-collected data of the target indicator from a plurality of available collection intervals; and the data collection device collects the data of the target indicator based on the collection interval.

Abstract: A network quality determining method includes, when experience quality represented by a customer experience index of a target user within a first time period is lower than experience quality represented by a customer experience index threshold, determining, using a first parameter value that is of a network key performance indicator (KPI) parameter of the target user within a second time period and that is collected by a collection device in a carrier network, a second parameter value of the network KPI parameter of the target user within the second time period in a home network, and when network quality represented by the second parameter value of the network KPI parameter is lower than network quality represented by a first threshold corresponding to the network KPI parameter in the home network, determining that quality of the home network is poor.

Abstract: A forwarding device receives at least one service flow; the forwarding device obtains service information of the at least one service flow, where the service information of the service flow includes identification information of a network object to which the service flow belongs and M key performance indicators KPIs of the service flow, M is an integer greater than 0, and the network object includes one or more devices; and the forwarding device sends training information to a first device, where the training information includes the service information of the at least one service flow or a feature set obtained based on the service information of the at least one service flow, the training information is used to train a fault detection model, and the fault detection model is used to detect whether the network object is in a faulty state.

Abstract: A network congestion control method, a node and a system are disclosed, where the method is applied to a spine-leaf network system. The method includes: a spine node receives network information sent by the at least one leaf node, where the network information includes network topology information of the leaf node and a network performance indicator of the leaf node; networks the at least one leaf node and the spine node based on the network topology information of the at least one leaf node, to obtain a combined network topology; and if the combined network topology is a global network topology of the spine-leaf network system, performs network congestion control on the at least one leaf node based on the network performance indicator of the at least one leaf node.

Abstract: A network congestion handling method includes obtaining network status information; determining, based on the network status information and an Explicit Congestion Notification (ECN) optimization model, a reference probability corresponding to recommended ECN configuration information; determining destination ECN configuration information based on the reference probability; and performing ECN marking on a packet by using the destination ECN configuration information.

Abstract: A sampling frequency recommendation method, apparatus, and device, and a storage medium relating to the field of communications technologies are disclosed.

Abstract: A network device inputs first network status information of the network device in a first time period to an ECN inference model, to obtain an inference result that is output by the ECN inference model based on the first network status information. Then, the network device sends an ECN parameter sample to an analysis device that manages the network device, where the ECN parameter sample includes the first network status information and a target ECN configuration parameter corresponding to the first network status information, and the target ECN configuration parameter is obtained based on the inference result. The network device receives an updated ECN inference model sent by the analysis device.

Abstract: This application provides a network quality monitoring method and apparatus. A network quality monitoring apparatus obtains network running data, where the network running data includes dynamic data corresponding to a plurality of sampling periods and static data that are of an AP; determines one channel efficiency value of the AP based on each of a plurality of groups of dynamic data of the AP, so as to obtain a plurality of channel efficiency values of the AP; determines a channel efficiency baseline of the AP based on the static data of the AP; and determines, based on the plurality of channel efficiency values of the AP and the channel efficiency baseline of the AP, network quality of a wireless local area network in which the AP is located.

Abstract: A data processing method, a server, and a data collection device are provided. The method includes: obtaining, by a server, first network key performance indicator KPI data and performance data of a first set-top box STB, where the first network KPI data is network KPI data of a first video service stream, and the first STB is an STB that receives the first video service stream; and calculating, by the server, first video quality of experience QoE of the first video service stream based on an associated model, the first network KPI data, and the performance data of the first STB, where the associated model is a model obtained through training based on historical data, and the associated model is used by the server to calculate video QoE based on network KPI data and performance data of an STB.

Abstract: A sampling frequency recommendation method, apparatus, and device, and a storage medium relating to the field of communications technologies are disclosed.

Abstract: A network quality determining method includes: when experience quality represented by a customer experience index of a target user within a first time period is lower than experience quality represented by a customer experience index threshold, determining, by using a first parameter value that is of a network KPI parameter of the target user within a second time period and that is collected by a collection device in a carrier network, a second parameter value of the network KPI parameter of the target user within the second time period in a home network; and when network quality represented by the second parameter value of the network KPI parameter is lower than network quality represented by a first threshold corresponding to the network KPI parameter in the home network, determining that quality of the home network is poor.