WO2022001709A1

WO2022001709A1 - Device model recognition method, apparatus, network device and system

Info

Publication number: WO2022001709A1
Application number: PCT/CN2021/101042
Authority: WO
Inventors: 王海燕
Original assignee: 华为技术有限公司
Priority date: 2020-06-30
Filing date: 2021-06-18
Publication date: 2022-01-06
Also published as: CN113873521A

Abstract

The embodiments of the present application relate to a device model recognition method, an apparatus, a network device, and a system, for implementing the recognition of a device model of an access device, reducing the costs and workload of database maintenance during device model recognition. Said method comprises: a network device acquiring N pieces of device information of N access devices, the N access devices respectively corresponding to the N pieces of device information, N being greater than or equal to 2, and N being an integer; and the network device determining device models of a plurality of access devices according to common features of a plurality of pieces of extracted device information of the plurality of access devices, wherein the plurality of access devices belong to the N access devices, and the plurality of pieces of device information belong to the N pieces of device information.

Description

A device model identification method, device, network device and system

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority of the Chinese patent application filed on June 30, 2020, with the application number of 202010622529.2 and the application title of "A Device Model Identification Method, Device, Network Equipment and System", the entire contents of which are approved by Reference is incorporated in this application.

technical field

The present application relates to the field of terminal technologies, and in particular, to a device model identification method, device, network device and system.

Background technique

At present, with the rapid promotion and application of terminal equipment technology, the trend of Internet technology (internet technology, IT) consumerization is becoming more and more obvious. Enterprise employees want to use their terminal equipment to access corporate email, corporate intranet and other resources at home, and at the same time want to use own terminal equipment. Bring your own device (BYOD), as an important form of IT consumerization, affects the original enterprise network access management. To ensure the security of the enterprise network, the enterprise network administrator can configure different network access policies according to different types of terminal devices.

Identifying the type of terminal equipment has become one of the methods of terminal fingerprint identification. Different types of terminal devices usually have different characteristics, and these characteristics can be reflected, for example, in the communication behavior of the terminal devices. Therefore, through the communication behavior of the terminal device, specific characteristics can be analyzed according to the behavior, and the type of the terminal device can be identified according to the characteristics, so as to better provide customized services. However, the existing terminal fingerprint identification technology is limited to the field of network security or hacking. The database maintenance method for terminal fingerprint identification is complicated, and is not conducive to automatic identification and real-time update, and is not practical in office scenarios.

SUMMARY OF THE INVENTION

The present application provides a device model identification method, device, network device and system, which are used to realize the identification of the device model of the access device and reduce the cost and workload of database maintenance during the device model identification process.

In a first aspect, an embodiment of the present application provides a method for identifying a device model, including: a network device acquiring N device information of N access devices, and the N access devices and the N device information are in a one-to-one correspondence respectively , N≥2, N is an integer; the network device extracts common features of multiple device information of multiple access devices; the network device determines the device models of the multiple access devices according to the common features, wherein , the multiple access devices belong to the N access devices, and the multiple device information belongs to the N device information.

Optionally, the access device includes a terminal device.

In the method, the network device performs big data analysis on the N device information of the N access devices, and automatically identifies the device model of the access device, without maintaining a large amount of feature database data, the device model can be identified, and the device model can be reduced. Identify the cost and effort of database maintenance in the process.

It can be understood that the device model identification method provided in the embodiments of the present application can be applied to enterprise networks to realize device model identification in office scenarios (such as BYOD scenarios), and can also be applied to home networks to realize device model identification in home networks. . Of course, the device model identification method provided by the embodiment of the present application can also be applied to the field of network security.

The device model identification method provided by the embodiment of the present application can not only identify the device model of the access device, but also identify other dimensions of the access device. For example, the other dimensions may include one or more of an operating system, a version number (also called version information), a manufacturer (also called a manufacturer), or a device name, and the like.

Optionally, the network device may establish, construct, and maintain a feature database based on the determined device models of the multiple access devices, and the feature database may include the device model of the access device, the information of each device model. One or more of common features and performance data of each device model, so as to improve the identification efficiency of subsequent device models. The performance data may be, for example, an access frequency band of the access device, the number of negotiated antennas, a negotiation rate, a wireless fidelity (wireless fidelity, Wi-Fi) access mode, and the like.

In a possible implementation, the network device may also acquire first device information of a first access device, where the first access device is different from the N access devices; the network device The common feature is extracted from the first device information, and the model of the first access device is determined as the device model.

In this implementation, the network device may identify the device model of the access device to be confirmed based on the common features of the extracted device models. For example, the device model of the access device is determined to be A according to the fact that the access device to be confirmed has the same features as the device model A in common. In this way, the identification time of the device model can be saved by the method, and the identification efficiency of the device model can be improved.

In a possible implementation, the N pieces of device information respectively include at least one or more of the following: a media access control MAC address of the access device, a device name of the access device, an access frequency band of the access device, a The number of antennas negotiated between the access device and the gateway device, the rate negotiated between the access device and the gateway device, or the Wi-Fi access mode of the access device.

In a possible implementation, the network device determines the device models of the multiple access devices according to the common feature, including:

The multiple device information includes multiple device names, the network device determines the device models of the multiple access devices according to the multiple device names having a first common feature, and the first common feature belongs to the common characteristics; and/or,

The multiple device information includes multiple MAC addresses, and the network device determines the device models of the multiple access devices according to the multiple MAC addresses having a second common feature, and the second common feature belongs to the Common feature.

The method of determining the device model according to the device name and the method of determining the device model according to the MAC address may be used alone, or may be used in combination.

In this implementation, the network device can obtain common features among multiple pieces of device information by analyzing different device information, so as to identify the device model of the access device based on the common features.

In a possible implementation, the network device has a first common feature according to the multiple device names, and before determining the device models of the multiple access devices, the method further includes:

The network device processes device names that do not conform to the device naming rules.

In this implementation, the network device may filter or reject device names that do not conform to the device naming rules. For example, the device name obtained by the network device is a random character string, and the random character string has no regularity and is generally not used as a device name, so the network device can remove the obtained random character string.

Or in this implementation, the network device may extract a meaningful device name of the access device from the device names that do not conform to the device naming rules. The meaningful device name of the extracted access device conforms to the device naming rules. For example, the device name obtained by the network device is a meaningful device name + a random string, so the network device can extract a meaningful device name, and the meaningful device name can be regarded as the real device name of the access device Device name.

In a possible implementation, before the network device determines the device models of the multiple access devices according to the second common feature of the multiple MAC addresses, the method further includes:

The network device filters the MAC addresses that do not conform to the MAC address rules.

In a possible implementation, the network device may further determine that the first feature is the first common feature according to the number of occurrences of the first feature in the multiple device names exceeding a first threshold.

When a device name is repeated for a certain number of times, that is, when the number of a device name reaches a certain number, it can be considered that the device name corresponds to a device model, so the network device can determine the first feature according to the first feature in the device name. Common feature.

The first threshold may be set by a network administrator. The larger the first threshold is set, the higher the accuracy of device model recognition may be, but the more unrecognized device models may be; the smaller the first threshold is set, the more accurate the device model recognition is. It may be lower, but the number of device models that can be recognized may also be more.

In a possible implementation, the N pieces of device information include N device names, and the network device determines that the first feature is based on the number of occurrences of the first feature of the multiple device names exceeding a first threshold. The first common feature includes:

generating, by the network device, a prefix tree according to the N device names;

The network device determines that the first feature is the first common feature according to the number of occurrences of the first feature of the multiple device names in the prefix tree exceeding a first threshold.

Optionally, the network device may also determine the first common feature by means of a maximum prefix or an artificial intelligence (artificial intelligence, AI) algorithm.

In a possible implementation, the N device information includes N MAC addresses, and the network device determines the device models of the multiple access devices according to the second common feature of the multiple MAC addresses, including :

The network device performs clustering on the N MAC addresses;

The network device determines that the multiple MAC addresses have a second common feature according to the multiple MAC addresses of the multiple device information belonging to the same clustering category;

The network device determines the device models of the multiple access devices according to the second common feature.

The MAC addresses of the access devices of the same model are usually consecutive, so in this implementation, the second common feature can be determined for the MAC addresses belonging to the same clustering category by clustering multiple MAC addresses.

In a possible implementation, the first device information includes a first media access control MAC address of the first access device, and the method further includes:

The network device determines that the model of the first access device is the device model according to the presence of consecutive bits equal to or greater than a preset number of bits between the first MAC address and the M MAC addresses, wherein the The M MAC addresses are the MAC addresses of M access devices in the multiple access devices, 1≤M≤N, where M is an integer; or,

The network device determines that the model of the first access device is the device model according to the address distance between the first MAC address and the M MAC addresses being less than or equal to a second threshold, wherein the M MAC addresses is the MAC addresses of M access devices in the multiple access devices, 1≤M≤N, and M is an integer.

In a possible implementation, after the network device determines the device models of the multiple access devices according to the common feature, the network device may further extract K pieces of performance data according to K pieces of device information, and the K pieces of device information belong to the plurality of pieces of device information, where K≧1, where K is an integer.

The performance data can be used for rapid fault division and network insight, targeted optimization of access devices and customized services for access devices.

In a possible implementation, the method further includes:

The network device obtains, according to the performance data, the access capability and/or behavior of the access device of the device model; or,

The network device sends the analysis data obtained according to the performance data to a third party, so that the third party obtains the access capability and/or behavior of the access device of the device model according to the analysis data.

In a possible implementation, the performance data includes one or more of Wi-Fi access frequency band, Wi-Fi access mode, number of negotiated antennas, negotiation rate, and signal strength.

In a possible implementation, the network device acquires one or more of the access capabilities and behaviors of the access device of the device model according to the performance data, including:

The performance data includes multiple RSSIs of received signal strengths of the multiple access devices, and the network device obtains, according to the distribution of the multiple RSSIs, the accessible access rate of the access device with the device model ;or,

The performance data includes K Wi-Fi access frequency bands of the K access devices, and the network device determines the access device of the device model according to statistics on the K Wi-Fi access frequency bands Supports single-band access or dual-band access; or,

The performance data includes one or more of the K negotiated antenna numbers, K negotiated rates, and K Wi-Fi access modes of the K access devices, and the network device negotiates according to the K negotiated antennas. One or more of the number of antennas, K negotiated rates and/or K Wi-Fi access modes, to obtain the access capability of the access device with the device model; or,

The performance data includes K signal strengths of the K access devices and one or more of K Wi-Fi access frequency bands, the network device according to the K signal strengths and K Wi-Fi Access one or more of the frequency bands, and obtain the behavior of the access device with the device model.

In a possible implementation, the third party includes an operator management device or a gateway device.

In a second aspect, an embodiment of the present application further provides a device model identification device, the device model identification device has the function of implementing the network device in the first aspect or the implementation of any method described in the first aspect. Means corresponding to the steps or functions described for performing the respective methods are included. The steps or functions can be implemented by software, or by hardware (eg, circuits), or by a combination of hardware and software.

In a possible implementation, the above apparatus includes one or more processing units and transceiver units. The one or more processing units are configured to support the apparatus to perform the corresponding functions of the network device in the above method.

Specifically, the transceiver unit is configured to acquire N pieces of device information of N access devices, the N access devices and the N pieces of device information are in one-to-one correspondence, N≥2, and N is an integer;

a processing unit, configured to extract common features of multiple device information of multiple access devices, and determine device models of the multiple access devices according to the common features, wherein the multiple access devices belong to the N access devices, and the multiple pieces of equipment information belong to the N pieces of equipment information.

In a possible implementation, the transceiver unit is further configured to acquire first device information of a first access device, where the first access device is different from the N access devices;

The processing unit is further configured to determine the model of the first access device as the device model according to the common feature extracted from the first device information.

In a possible implementation, the N pieces of device information respectively include at least one or more of the following: the MAC address of the access device or the device name of the access device.

In a possible implementation, the processing unit is specifically configured to: the multiple device information includes multiple device names, and according to the multiple device names having a first common feature, determine the multiple access devices. The model of the device to which the first common feature belongs; or,

The multiple device information includes multiple MAC addresses, and the device models of the multiple access devices are determined according to the multiple MAC addresses having a second common feature, and the second common feature belongs to the common feature.

In a possible implementation, the processing unit is further configured to determine that the first feature is the first common feature according to the number of occurrences of the first feature in the multiple device names exceeding a first threshold.

In a possible implementation, the processing unit is specifically configured to: the N device information includes N device names, and a prefix tree is generated according to the N device names; according to the multiple devices in the prefix tree When the number of occurrences of the first feature of the name exceeds a first threshold, the first feature is determined to be the first common feature.

In a possible implementation, the processing unit is specifically configured to perform the clustering of the N MAC addresses according to the N pieces of device information including N MAC addresses; If the MAC addresses belong to the same clustering category, it is determined that the multiple MAC addresses have a second common feature; and the device models of the multiple access devices are determined according to the second common feature.

In a possible implementation, the processing unit is further configured for the first device information to include a first media access control MAC address of the first access device, according to the first MAC address and M MAC addresses The address has consecutive bits equal to or greater than the preset number of bits, and it is determined that the model of the first access device is the device model, wherein the M MAC addresses are M of the multiple access devices MAC address of each access device, 1≤M≤N, where M is an integer; or,

According to the address distance between the first MAC address and the M MAC addresses being less than or equal to a second threshold, it is determined that the model of the first access device is the device model, wherein the M MAC addresses are the multiple MAC addresses. MAC addresses of M access devices in the access devices, 1≤M≤N, where M is an integer.

In a possible implementation, the processing unit is further configured to extract K pieces of performance data according to K pieces of equipment information, where the K pieces of equipment information belong to the plurality of pieces of equipment information, K≥1, and K is an integer.

In a possible implementation, the processing unit is further configured to acquire, according to the performance data, the access capability and/or behavior of the access device of the device model; or,

The analysis data obtained according to the performance data is sent to a third party by the transceiver unit, so that the third party obtains the access capability and/or behavior of the access device of the device model according to the analysis data.

In a possible implementation, the performance data includes multiple received signal strength RSSIs of the multiple access devices, and the processing unit is specifically configured to, according to the distribution of the multiple RSSIs, transmit and receive The unit acquires the access reachable rate of the access device with the device model; or,

The performance data includes K Wi-Fi access frequency bands of the K access devices, and the processing unit is specifically configured to determine the device model according to statistics on the K Wi-Fi access frequency bands The access device supports single-frequency access or dual-frequency access; or,

The performance data includes one or more of the K negotiated antenna numbers, the K negotiated rates, and the K Wi-Fi access modes of the K access devices. one or more of the K negotiated antenna numbers, K negotiated rates and/or K Wi-Fi access modes, and obtain the access capability of the access device with the device model through the transceiver unit; or,

The performance data includes K signal strengths of the K access devices and one or more of the K Wi-Fi access frequency bands. In one or more of the Wi-Fi access frequency bands, the transceiver unit acquires the behavior of the access device with the device model.

In a third aspect, an embodiment of the present application further provides a network device, the device includes a processor and a memory, the processor is coupled to the memory;

memory for storing computer programs;

A processor for executing a computer program stored in the memory to cause the apparatus to perform the following operations:

Obtain N device information of N access devices, where the N access devices and the N device information are in one-to-one correspondence, N≥2, and N is an integer;

extracting common features of multiple device information of multiple access devices, and determining device models of the multiple access devices according to the common features, wherein the multiple access devices belong to the N access devices, The pieces of device information belong to the N pieces of device information.

In a possible implementation, the processor is further configured to execute the computer program to perform the following operations:

acquiring first device information of a first access device, where the first access device is different from the N access devices;

According to the common feature extracted from the first device information, it is determined that the model of the first access device is the device model.

In a possible implementation, the processor is specifically configured to execute the computer program to perform the following operations:

The multiple device information includes multiple device names, and the device models of the multiple access devices are determined according to the multiple device names having a first common feature, and the first common feature belongs to the common feature; or ,

According to the number of occurrences of the first feature in the plurality of device names exceeding a first threshold, it is determined that the first feature is the first common feature.

In a possible implementation, the N device information includes N device names, and the processor is specifically configured to execute the computer program to perform the following operations:

generating a prefix tree according to the N device names;

According to the number of occurrences of the first feature of the plurality of device names in the prefix tree exceeding a first threshold, it is determined that the first feature is the first common feature.

In a possible implementation, the N pieces of device information include N MAC addresses, and the processor is specifically configured to execute the computer program to perform the following operations:

clustering the N MAC addresses;

According to the plurality of MAC addresses of the plurality of device information belonging to the same clustering category, it is determined that the plurality of MAC addresses have a second common characteristic;

According to the second common feature, device models of the multiple access devices are determined.

In a possible implementation, the first device information includes a first media access control MAC address of the first access device, and the processor is further configured to execute the computer program to perform the following operations:

According to the existence of consecutive bits equal to or greater than a preset number of bits between the first MAC address and the M MAC addresses, it is determined that the model of the first access device is the device model, wherein the M MAC addresses is the MAC addresses of M access devices in the multiple access devices, 1≤M≤N, M is an integer; or,

Extract K pieces of performance data according to K pieces of equipment information, where the K pieces of equipment information belong to the plurality of pieces of equipment information, K≥1, and K is an integer.

Obtain the access capability and/or behavior of the access device of the device model according to the performance data; or,

The analysis data obtained according to the performance data is sent to a third party, so that the third party obtains the access capability and/or behavior of the access device of the device model according to the analysis data.

The performance data includes multiple RSSIs of the multiple received signal strengths of the multiple access devices, and according to the distribution of the multiple RSSIs, obtain the access reachable rate of the access device with the device model; or,

The performance data includes K Wi-Fi access frequency bands of the K access devices. According to statistics on the K Wi-Fi access frequency bands, it is determined that the access device of the device model supports single-frequency access. access or dual-band access; or,

The performance data includes one or more of the K negotiated antenna numbers, K negotiated rates, and K Wi-Fi access modes of the K access devices. According to the K negotiated antenna numbers, One or more of the K negotiated rates and/or K Wi-Fi access modes, obtain the access capability of the access device with the device model; or,

The performance data includes K signal strengths of the K access devices and one or more of the K Wi-Fi access frequency bands, according to the K signal strengths and the K Wi-Fi access frequency bands. One or more of , obtain the behavior of the access device with the device model.

In a possible implementation, the third party includes an operator or a gateway.

In a fourth aspect, the embodiments of the present application further provide a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the computer-readable storage medium runs on a computer, the computer executes the first aspect or any one of the first aspects. method in a possible implementation.

In a fifth aspect, an embodiment of the present application further provides a computer program product, the computer program product includes: computer program code, when the computer program code runs on a computer, the computer program code enables the computer to execute the first aspect or any of the first aspect. A method in a possible implementation.

In a sixth aspect, an embodiment of the present application further provides a communication system, where the system includes a first network device and an access device for executing the method in the first aspect or any possible implementation of the first aspect.

Optionally, the communication system may further include a second network device, and the second network device may be an operator management device and/or a gateway device or the like. The first network device may be a network management device or the like. The access device may be a terminal device or the like.

In a seventh aspect, an embodiment of the present application further provides a communication system, where the system includes a first network device and a second network device, and the first network device may be used to execute the first aspect or any possibility of the first aspect method in the implementation. The first network device is further configured to extract K pieces of performance data according to the K pieces of equipment information after determining the equipment models of the multiple pieces of access equipment according to the common features of the pieces of equipment information of the multiple pieces of access equipment. The K pieces of equipment information belong to the multiple pieces of equipment information, K≥1, K is an integer, and the access capability and/or behavior of the access equipment of the equipment model obtained according to the performance data is sent to the the second network device; or send the analysis data obtained according to the performance data to the second network device. the second network device, configured to receive the access capability and/or behavior of the access device of the device model; or obtain the access capability and/or performance of the access device of the device model according to the analysis data .

In a possible implementation, before the first network device acquires the N device information of the N access devices, the second network device is further configured to send the N device information to the first network device, N≥2, N is an integer.

In a possible implementation, the second network device is a gateway device or an operator management device. Optionally, the second network device may also be a digital subscriber line (digital subscriber line, DSL) device, a passive optical network (passive optical network, PON) device, a router, and/or a switch and other devices.

In a possible implementation, the first network device is a network management device.

In a possible implementation, the performance data includes multiple RSSIs of received signal strengths of multiple access devices, and the obtaining of the access capability includes: obtaining, according to the distribution of the multiple RSSIs, the devices with the RSSI. The access achievable rate of the access device of the model; or,

The performance data includes K Wi-Fi access frequency bands of the K access devices, and the acquisition of the access capability includes: determining the device according to statistics on the K Wi-Fi access frequency bands Models of access devices that support single-band access or dual-band access; or,

The performance data includes one or more of the K negotiated antenna numbers, the K negotiated rates, and the K Wi-Fi access modes of the K access devices, and the acquisition of the access capability includes: One or more of the K negotiated antenna numbers, K negotiated rates, and/or K Wi-Fi access modes, obtain the access capability of the access device with the device model; or,

The performance data includes K signal strengths of the K access devices and one or more of K Wi-Fi access frequency bands, and the acquisition of the device behavior includes: according to the K signal strengths and K For one or more of the Wi-Fi access frequency bands, obtain the behavior of the access device with the device model.

For the technical effect that can be achieved by any one of the above-mentioned second to seventh aspects and any possible design in any of them, please refer to the above-mentioned first aspect and the technical effect that the corresponding design in the first aspect can bring. description, which will not be repeated here.

Description of drawings

FIG. 1 is a schematic diagram of the architecture of an enterprise network to which an embodiment of the application is applied;

FIG. 2 is a schematic structural diagram of a home network to which an embodiment of the application is applied;

FIG. 3 is a schematic diagram of a MAC address applicable to an embodiment of the present application;

FIG. 4 is a schematic flowchart of a device model identification process applicable to the embodiment of the application;

FIG. 5 is a schematic diagram of a prefix tree applicable to the embodiment of the present application;

FIG. 6 is a schematic diagram of a prefix tree applicable to the embodiment of the present application;

FIG. 7 is a schematic diagram of a prefix tree to which an embodiment of the present application is applicable;

FIG. 8 is a schematic diagram of a network device to which an embodiment of the application is applied;

FIG. 9 is a schematic diagram of a device type identification device applicable to an embodiment of the present application.

detailed description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

FIG. 1 is a schematic structural diagram of a home network to which an embodiment of the present application is applied. As shown in FIG. 1 , a home network includes a home network management system, a home gateway and a terminal device, wherein the number of the home network management system, the home gateway and the terminal device may be one or more.

In the home network, a gateway agent (agent) is integrated into the home gateway, and the gateway agent is used to convert the request of the home network management system into a home gateway request, thereby realizing the control of the home gateway. After the home gateway is started, it can be connected to the home network management system through a network protocol. The terminal device may access the home gateway through a dynamic host configuration protocol (dynamic host configuration protocol, DHCP) protocol. The home gateway may acquire the device information of the terminal device, so as to determine the terminal device type (eg device model) according to the acquired device information.

The home network management system may be a home application function (application function, AF) network element, for example, the home network management system may be a management server or the like for remotely managing terminal devices in the home network.

The home gateway may be a router. The local area network (LAN) port of the home gateway may correspond to a service set identifier (service set identifier, SSID), and the value of the SSID may be the media access control (media access control, MAC) of the home gateway address.

The Agent is a runnable program, which is used to convert the request of the network management system into the request of the gateway.

The roles of the terminal device may include an access point (access point, AP) and/or a station (station, STA). The AP can be a wireless router, a Wi-Fi repeater and other devices, and the STA can be a personal computer, a mobile phone, a tablet computer, and other devices connected to the home network.

The home gateway may acquire the device information of the terminal device connected to the MAC address. The home gateway may also scan the SSID2 of the AP hotspot, so as to obtain the device information of the terminal device connected to the AP hotspot.

As shown in FIG. 1 , the home network may include multiple STAs/APs connected to the home gateway, and the STA/AP may also include multiple STAs connected to it.

It can be understood that, although the home network architecture shown in FIG. 1 is used as an example, the embodiments of the present application may also be applicable to other network architectures or network types. For example, as shown in FIG. 2, the enterprise network includes (one or more) enterprise network management systems, (one or more) enterprise gateways and (one or more) terminal devices. Similarities between FIG. 2 and FIG. 1 will not be repeated here.

This application will present various aspects, embodiments, or features around a system that may include a plurality of devices, components, modules, and the like. It is to be understood and appreciated that the various systems may include additional devices, components, modules, etc., and/or may not include all of the devices, components, modules, etc. discussed in connection with the figures. In addition, combinations of these schemes can also be used.

In addition, in the embodiments of the present application, the word "for example" is used to represent an example, illustration or illustration. Any embodiment or design described herein as "for example," should not be construed as preferred or advantageous over other embodiments or designs. Rather, the word example is used to present a concept in a concrete way.

The network architecture and service scenarios described in the embodiments of the present application are for the purpose of illustrating the technical solutions of the embodiments of the present application more clearly, and do not constitute the only limitation to the technical solutions provided by the embodiments of the present application. The evolution of the network architecture and the emergence of new service scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

Some terms in the embodiments of the present application are explained below to facilitate understanding by those skilled in the art.

1) Network equipment, including, for example, access network (AN) equipment, such as a base station (eg, an access point), which may refer to a device in the access network that communicates with wireless terminal equipment through one or more cells over the air interface , or, for example, a network device in a vehicle-to-everything (V2X) technology is a roadside unit (RSU). The base station may be used to interconvert the received air frames and IP packets, acting as a router between the terminal equipment and the rest of the access network, which may include the IP network. The RSU can be a fixed infrastructure entity supporting V2X applications and can exchange messages with other entities supporting V2X applications. The network device can also coordinate the attribute management of the air interface. For example, the network equipment may include an evolved base station (NodeB or eNB or e-NodeB, evolutional Node B) in a long term evolution (long term evolution, LTE) system or long term evolution-advanced (LTE-A), Alternatively, it may also include the next generation node B (gNB) in the 5th generation mobile communication technology (the 5th generation, 5G) NR system (also referred to as the NR system for short), or may also include a cloud access network (cloud access network). The embodiment of the present application is not limited to a centralized unit (centralized unit, CU) and a distributed unit (distributed unit, DU) in a radio access network, Cloud RAN) system.

The network device may also include a core network (core network, CN) device, and the core network device includes, for example, an access and mobility management function (access and mobility management function, AMF) and the like.

Or alternatively, in some possible application scenarios, the network device may also be a DSL device, a PON device, a router, and/or a switch and other devices.

As an example but not a limitation, in this embodiment of the present application, the network device may also be an application function entity (application function, AF) network element, a gateway (such as an enterprise gateway or a home gateway, etc.), or a network management system (such as an enterprise network management system) system or home network management system, etc.) and so on. For example, the gateway may be a router, and the network management system may be a management server or the like for managing terminal devices in the network.

2) Access equipment, user equipment (such as terminal equipment) or network access equipment used to access network resources.

Terminal devices, also known as smart terminals or terminals, include devices that provide voice and/or data connectivity to users, and may include, for example, handheld devices with wireless connectivity, or processing devices connected to wireless modems. The terminal equipment may communicate with the core network via a radio access network (RAN), and exchange voice and/or data with the RAN. The terminal equipment may include user equipment (UE), wireless terminal equipment, mobile terminal equipment, device-to-device (D2D) terminal equipment, vehicle to everything (V2X) terminal equipment , Machine-to-machine/machine-type communications (M2M/MTC) terminal equipment, Internet of things (IoT) terminal equipment, subscriber unit (subscriber unit), subscriber station (subscriber) station), mobile station, remote station, AP, remote terminal, access terminal, user terminal, user agent, or user equipment (user device), etc. For example, these may include mobile telephones (or "cellular" telephones), computers with mobile terminal equipment, portable, pocket-sized, hand-held, computer-embedded mobile devices, and the like. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (personal digital assistants), PDA), etc. Also includes constrained devices, such as devices with lower power consumption, or devices with limited storage capacity, or devices with limited computing power, etc. For example, it includes information sensing devices such as barcodes, radio frequency identification (RFID), sensors, global positioning system (GPS), and laser scanners.

As an example and not a limitation, in this embodiment of the present application, the terminal device may also be a wearable device. Wearable devices can also be called wearable smart devices or smart wearable devices, etc. It is a general term for the application of wearable technology to intelligently design daily wear and develop wearable devices, such as glasses, gloves, watches, clothing and shoes. Wait. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable device is not only a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. In a broad sense, wearable smart devices include full-featured, large-scale, complete or partial functions without relying on smart phones, such as smart watches or smart glasses, and only focus on a certain type of application function, which needs to cooperate with other devices such as smart phones. Use, such as all kinds of smart bracelets, smart helmets, smart jewelry, etc. for physical sign monitoring.

Or alternatively, in some application scenarios, the access device may also include other types of devices, such as a modem, a router, an optical network terminal (optical network terminal, ONT) and other devices.

The embodiments of the present application mainly take the access device including the terminal device as an example for description. For the device model identification process of other types of devices, reference may be made to the device model identification process of the terminal device.

3) Terminal device type, including one or more of the dimensions of device model, operating system, version number (also called version information), manufacturer (also called manufacturer or manufacturer), or device name.

Device model, used to indicate the type of terminal device. Terminal devices of the same device model have common features, that is, there is the same/matching device information.

The embodiments of this application mainly provide a method for identifying a device model. For the identification process of device types in other dimensions in the terminal device (such as operating system, manufacturer, etc.), please refer to the identification process of the device model, and the similarities will not be repeated.

The terminal devices involved in the embodiments of the present application may include one or more of the following: a personal computer (personal computer, PC), a smart phone (SmartPhone), a tablet computer (PAD), a set top box (set top box, STB), a smart TV ( SmartTV), router (Router), smart device (SmartDevice), TV set-top box (OTTTvBox), smart speaker (SmartSpeaker), camera (Camera), watch (Watch), game console (Games), or other equipment (Other), etc. .

4) Device information, which may include one or more of the following: the MAC address of the terminal device, the device name of the terminal device, the access frequency band of the terminal device, the number of antennas negotiated between the terminal device and the gateway device (also referred to as the gateway), The rate negotiated between the terminal device and the gateway device, or the Wi-Fi access mode of the terminal device. In the embodiment of the present application, the device model of the terminal device can be obtained by analyzing the commonality between the device information, and the commonality between the device information can also be understood as the common feature existing between the device information.

The MAC address of the terminal device is shown in FIG. 3 , the first six digits of the MAC address are generally the MAC organizationally unique identifier (OUI), and the MAC OUI is used to represent the Institute of Electrical and Electronics Engineers (Institute of Electrical) and electronics engineers, IEEE) is assigned to the company identification of each manufacturer, and the last six bits of the MAC address of the terminal equipment of the same equipment model can be consecutive.

The device name of the terminal device is generally the name adopted by the manufacturer when releasing the terminal device. For example, the device name of the terminal device is HUAWEI MATE 30, HUAWEI MATE 20, or HUAWEI P30, or iPhone X or iPhone 11, etc.

The access frequency band of the terminal device includes, but is not limited to, 2.4 gigahertz (GHz) or 5 GHz, for example.

The number of antennas negotiated by the terminal device and the gateway device may include 1*1, 2*2, or 4*4, etc.

The rate negotiated between the terminal device and the gateway device is the wireless rate negotiated with the gateway device for communication after the terminal device is connected to the wireless signal of the gateway device. For example, the rate negotiated between the terminal device and the gateway device may be 867 megabits per second (million bits per second, Mbps).

The Wi-Fi access mode of the terminal device includes but is not limited to one of the following: b: 802.11b, g: 802.11g, n: 802.11n, a: 802.11a, ac: 802.11ac, or ax: 802.11ax Wait.

5) The performance data of terminal equipment, such as access capability and behavior, can be used to quickly find and solve network faults, improve the insight of network health status, and can also carry out targeted optimization of terminal equipment and provide terminal equipment. Customized service.

In the embodiment of the present application, the network device can automatically learn the access capability and behavior of the terminal device of the device model by scanning the entire network according to the device model.

In this application, "and/or" describes the association relationship between associated objects, and means that there can be three kinds of relationships, for example, A and/or B, which can mean that A exists alone, A and B exist simultaneously, and B exists alone. a situation. The character "/" generally indicates that the associated objects are an "or" relationship.

The plural referred to in this application refers to two or more.

In addition, it should be understood that in the description of this application, words such as "first" and "second" are only used for the purpose of distinguishing the description, and should not be understood as indicating or implying relative importance, nor should it be understood as indicating or implied order.

To facilitate understanding of the embodiments of the present application, application scenarios of the embodiments of the present application are described below.

At present, with the rapid promotion and application of terminal equipment technology, the trend of IT consumerization (representing the behavior of using enterprise information systems on personal private information consumer products) is becoming more and more obvious. Enterprise employees want to use their terminal equipment at home or in other mobile phones Access resources such as company emails and corporate intranets in a network environment, and at the same time want to use your own terminal equipment for work. As an important form of IT consumerization, BYOD affects the original enterprise network access management. General office scenarios involve a lot of highly sensitive content, and even business secrets. Therefore, in order to ensure the security of the enterprise network, network administrators can configure different network access policies according to different types of terminal devices. The technology of identifying the type of terminal equipment is called terminal fingerprint identification technology, which is realized by collecting the communication behavior of the terminal equipment and analyzing the characteristics of the terminal equipment.

Terminal fingerprint identification technology includes active fingerprint identification technology and passive fingerprint identification technology.

When using active fingerprint identification technology to identify the type of terminal device, the identification device sends a certain number of combined data packets to the identified device, and determines the device model, operating system type and version of the identified device according to the response of the identified device. number, etc.

However, the active fingerprint identification technology is usually limited to the field of network security/hacking, and cannot be applied to the field of enterprise/home network. When security experts or hackers need to infiltrate a remote system, the fingerprinting process is often performed first. Security experts or hackers can use FIN (used to determine the operating system of the device being authenticated) detection, error transmission control protocol (TCP) flag detection, TCP start sequence number sampling, interface pointer identifier, IPID) sampling, TCP timestamp extension, TCP start window size, acknowledged (ACK) value, Internet control message protocol (ICMP) error information test, fragmentation processing phenomenon and other technical combinations to detect And identification, to achieve active identification of terminal fingerprints.

Generally, active fingerprint recognition technology is limited to the field of network security/hacking. In BYOD scenarios, passive fingerprint recognition technology is more commonly used.

When the passive fingerprint technology is used to identify the terminal device type, it can be realized based on the following technical directions: time to live (TTL) fingerprint analysis, Transmission Control Protocol (TCP) fingerprint analysis, Dynamic Host Configuration Protocol (Dynamic Host Configuration Protocol) , DHCP) fingerprint analysis, hypertext transfer protocol (hypertext transfer protocol, HTTP) fingerprint analysis, international mobile equipment identity (international mobile equipment identity, IMEI) analysis and other technologies.

Taking TTL fingerprint analysis as an example, the operating systems corresponding to the TTL start values of different terminal devices are different. When identifying the terminal device type by TTL fingerprint analysis, the authentication device can identify the operating system of the authenticated device according to the TTL initial value corresponding to the authenticated device. For example: the starting TTL value corresponding to the operating system Macintosh OSX is 255, the starting TTL value corresponding to the operating system Novell Netware is 128, the starting value TTL corresponding to the operating system Windows XP/2000/2003/Vista is 128, and the operating system Windows The corresponding TTL start value of 95 is 32, the corresponding TTL start value of the operating system Windows 95A/B is 128, the corresponding TTL start value of the operating system Cisco Catalyst 6000 is 60, and the corresponding TTL start value of the operating system Linksys printer server is 32.

Taking TCP fingerprint analysis as an example, there are differences in the implementation of communication specifications between versions of various operating systems in different periods. When identifying the terminal device type by TCP fingerprint analysis, the authentication device can identify the operating system of the authenticated device according to the communication process of the TCP protocol corresponding to the authenticated device. For example, the authentication device may determine the operating system of the authenticated device according to information such as parameters selected by the authenticated device during the TCP three-way handshake process.

For smart terminals, the HTTP header generally carries information such as operating system, version information, terminal type, device model or manufacturer. When identifying a terminal device for HTTP fingerprint analysis, the identification device can determine the operating system, version number, device model or manufacturer of the authenticated device according to the HTTP header of the data sent by the authenticated device (such as the terminal device).

The IMEI generally includes 15 digits. The first six digits of the IMEI represent the device model, and the last two digits of the IMEI represent the manufacturer. When identifying the type of terminal device by analyzing the IMEI, the identification device can determine the device model and manufacturer of the identified device according to the IMEI of the identified device.

Passive fingerprint identification requires manual maintenance of the feature database, that is, to maintain the correspondence between device features and device types, so that the identification device can identify the terminal device type according to the device information of a terminal device against the feature database. Due to the diversity of terminal equipment, there are many manufacturers of terminal equipment (possibly tens of thousands of manufacturers), and the signature database needs to maintain too much information, resulting in high maintenance cost and workload of the signature database, and due to the high update frequency of equipment products , the manual maintenance of the feature database leads to poor recognition flexibility and real-time performance, and some of the recognition methods may involve user privacy. Therefore, the practicability of passive fingerprint identification technology in enterprise networks (such as BYOD scenarios) or home networks is not high.

Based on this, in order to quickly identify the device model of the terminal device in the network and realize the adaptation to the enterprise network (such as the BYOD scenario) or the home network, the present application proposes a device model identification method. In this method, the network device can obtain N device information of N terminal devices, the N terminal devices and the N device information are in a one-to-one correspondence, and the network device can extract multiple data of multiple terminal devices. Common features of the pieces of equipment information, determine the equipment models of the multiple terminal equipments according to the common characteristics, the multiple terminal equipments belong to the N terminal equipments, and the multiple pieces of equipment information belong to the N equipments information. The network device can automatically identify the device model of the terminal device by performing big data analysis on the device information of multiple terminal devices, without maintaining a large number of feature database data, the device model of the terminal device in the network can be identified, and the device model can be reduced. The cost and workload of database maintenance during the identification process are improved, and the flexibility and real-time performance of equipment model identification are improved.

The device model identification method provided in this embodiment of the present application can be applied to the network architecture shown in FIG. 1 or 2. In an actual possible scenario, the network may also include other possible network devices and terminal devices. The type and number of devices included are not limited. Referring to Figure 4 below, the device model identification process will be described:

S401: The network device acquires N pieces of device information of N terminal devices, the N terminal devices and the N pieces of device information are in one-to-one correspondence, N≥2, and N is an integer.

The device information includes at least one or more of the following: the MAC address of the terminal device, the device name of the terminal device, the access frequency band of the terminal device, the number of antennas negotiated between the terminal device and the gateway device, the terminal device and the gateway device. The rate negotiated by the device, or the Wi-Fi access mode of the terminal device.

The network device can be understood as an authentication device in the process of device model identification, and the terminal device can be understood as an authenticated device in the device model identification process.

The network device may be a network management system (eg, an enterprise network management system or a home network management system), or a gateway device (eg, an enterprise gateway device or a home gateway device). The terminal device may be a STA or an AP.

Taking the network device as a network management system as an example, for example, in S401, the network device may send a first message to the terminal device, where the first message is used to request to obtain device information of the terminal device, and the first message is used to request the terminal device. A message is used to instruct the terminal device to report device information. The terminal device may send its own device information to the network device, and the network device receives the device information of the terminal device.

For another example, in S401, the network device may send a second message to the gateway device, where the second message is used to instruct the gateway device to collect device information of the terminal device. The gateway device can collect device information of the devices attached to it, and the devices attached to the gateway device include terminal devices connected to the wireless network of the gateway device. The gateway device reports the device information of the attached device to the network device, and the network device receives the device information of the terminal device. Exemplarily, when the terminal device accesses the gateway device, the gateway device may allocate part of the device information to the accessed terminal device.

Optionally, the N terminal devices may be all terminal devices within the management range of the network device, or may be part of the terminal devices within the management range of the network device. Generally, the number of terminal devices within the management range of the network device is large, and in some scenarios, the amount of data may reach 100,000, 1,000,000, and so on.

S402: The network device extracts common features of multiple device information of multiple terminal devices, and determines device models of the multiple terminal devices according to the common features, wherein the multiple terminal devices belong to the N terminals equipment, the pieces of equipment information belong to the N pieces of equipment information.

The network device may, according to the N device information of the N terminal devices acquired in S401, extract the common features of multiple device information in the N device information, and the multiple device information belongs to the N terminal devices. multiple end devices. In this S402, when the network device extracts the common feature of the multiple device information of the multiple terminal devices, it may directly extract the feature information included in the multiple device information to determine the common feature. The multiple pieces of equipment information have the common feature; or it may be based on input data, such as the N pieces of equipment information or the multiple pieces of equipment information, to perform processing analysis, and to determine the A common feature of multiple pieces of device information. In this case, the common feature may not be directly included in the multiple pieces of device information. For example, the common feature is specifically a certain category after clustering N pieces of device information. Optionally, extracting common features includes but is not limited to the following methods: clustering the multiple device information, constructing a prefix tree corresponding to the multiple device information, or using an AI algorithm to extract the multiple device information. characteristic information.

The common feature described in S402 may be determined according to a common feature, that is, the common feature described in S402 is a common feature, or a set including a common feature. In this case, the common feature described in S402 may be determined according to multiple common features. A common feature is determined, that is, the common feature described in S402 is a set including multiple common features, for example, the common feature described in S402 includes a first common feature and a second common feature, and the first common feature is based on the device name. Determine, the second common characteristic is determined according to the MAC address.

In an example, the multiple device information includes multiple device names, and in S402, the network device may determine the device models of the multiple terminal devices according to the multiple device names having a first common feature , the first common feature belongs to the common feature.

The multiple device names having the first common feature can be understood as the first common feature can be directly obtained from the content included in the multiple device names, or it can be understood as further analysis based on the multiple device names or Derivation to determine the first common characteristic.

Optionally, the network device may determine that the first feature is the first common feature according to the number of occurrences of the first feature in the multiple device names exceeding a first threshold.

The first threshold may be any integer, for example, the first threshold may be 1000 times, 10000 times or 50000 times, etc. The first threshold may be set by a network administrator. When the number of occurrences of the first feature in the multiple device names exceeds the first threshold, the device models of the multiple terminal devices can be determined according to the first feature. The larger the first threshold is, the more accurate the device model identification is. The higher the rate may be, the more unrecognized device models may be. The smaller the first threshold is set, the lower the accuracy rate of device model identification may be, but the more device models that can be identified may also be.

In addition, the final identified device model content may also be affected by the threshold value. For example, when the first threshold is set to a first value, the first feature is HUAWEI MATE 20, and thus it is determined that the models of the plurality of terminal devices are HUAWEI MATE 20. When the first threshold is set to the second value, the first feature is HUAWEI MATE, thereby determining that the models of the multiple terminal devices are HUAWEI MATE. Therefore, the first threshold can be specifically determined according to needs or experience.

Or alternatively, the N device information includes N device names, and the network device may generate a prefix (Trie) tree according to the N device names. Prefix tree, used to store strings. Each node of the prefix tree represents a string (or a prefix). There may be multiple child nodes under each node, and the paths leading to different child nodes have different characters. The string represented by the child node is composed of the original string of the node itself, and all the characters on the path to the child node. In addition, in the embodiment of the present application, the number of occurrences of the character string represented by the node may also be counted for each node. Optionally, the character string represented by each leaf node in the prefix tree may be regarded as a complete device name, and a character string determined from the root node to the leaf node is the character string with the longest length on the path. For example, the network device generates a prefix tree as shown in FIG. 5 according to the number of occurrences of the device name iPhone-6s. The network generates a prefix tree as shown in FIG. 6 according to the number of occurrences of the device name iPhone-8. Referring to the process of generating the prefix tree shown in FIG. 5 and FIG. 6 , the prefix tree of the N device names is generated, as shown in FIG. 7 , where iPhone-6s and iPhone-8 each appear 10,000 times.

The network device may determine that the first feature is the first common feature according to the number of occurrences of the first feature of the multiple device names in the prefix tree exceeding a first threshold. There may be one or more of the first features whose number of occurrences exceeds the first threshold. Exemplarily, if the number of occurrences of only one first feature exceeds the first threshold, the first feature may be directly determined as the first common feature. If the number of occurrences of multiple first features exceeds the first threshold, the first feature with the least number of occurrences among the multiple first features may be determined as the first common feature, or the first feature may be determined as the first common feature. The first feature with the longest character string length among the multiple first features is determined as the first common feature; or the multiple first features may be determined as the first common feature of different types of terminal devices respectively. For example, the first threshold is 9,000. In Figure 5, the number of occurrences of iPhone is 30,000, the number of occurrences of iPhone-6 is 20,000, and the number of occurrences of iPhone-6s is 10,000, all exceeding the first threshold. The first feature with the least number of occurrences, that is, the iPhone-6s that appears 10,000 times, is determined as the first common feature, or the first feature with the longest string length, that is, the iPhone-6s, is determined as the first feature. common feature; similarly, in FIG. 6 , the first feature with the least number of occurrences, that is, the iPhone-8 with 10,000 occurrences, can be determined as the first common feature, or the first feature with the longest string length can be determined as the first common feature. The feature, namely iPhone-8, is determined as the first common feature. For example, the device model determined according to the prefix tree shown in FIG. 5 is iPhone-6s, and the device model determined according to the prefix tree shown in FIG. 6 is iPhone-8.

In other possible implementation manners, the identified terminal device model may also be determined only by considering whether the number of occurrences of the first feature of the path to the leaf node exceeds a first threshold. In a prefix tree, there may be paths of multiple leaf nodes, wherein a string composed of all characters on the path from the root node to the leaf node can be used to represent the path of the leaf node. In this case, a plurality of first common features corresponding to different terminal device models can be determined through the first threshold. In the prefix tree shown in Figure 7, the leaf nodes include 0, 8 and S. The path of leaf node 0 is MATE10, the path of leaf node 8 is iPhone-8, and the path of leaf node S is iPhone-6S, but this In this case, other sub-paths on the path to the leaf node are no longer analyzed, for example, the arrival of the leaf node is no longer determined. By setting the first threshold, three models of MATE10, iPhone-8 and iPhone-6S can be identified at the same time.

The network device may also determine the first common feature through methods such as an AI algorithm. If the network device determines the first common feature through an AI algorithm, exemplarily, the network device may store a trained neural network model, and the network device may input the multiple device names into the neural network model. In the network model, the first common feature is determined according to the output result of the neural network model. The neural network model may be a classification model or a discriminant model, or the like.

Before S402, the network device may also process device names that do not conform to the device naming rules. Exemplarily, processing the device names that do not meet the device naming rules includes, but is not limited to, one or more of the following methods: filtering, rejecting the device names that do not meet the device naming rules, or The device name that conforms to the device naming rules is extracted from the device name.

The device naming rule may be a set including device names, and/or the device naming rule may set a length threshold. The set including the device names may include the device names of all or part of the terminal devices currently on the market. The preset length threshold may be set by the network administrator, or determined according to the general length of the device name of the terminal device currently on the market.

When filtering or eliminating device names that do not meet the device naming regulations, for example, the acquired device name is an irregular string such as android-567812345678, the string does not contain information related to the real device name, so The string can be filtered out directly. When extracting a device name that conforms to the device naming rules from a device name that does not conform to the device naming rules, for example, the acquired device name is a meaningful device name + an irregular string (such as Mate10-567812345678), the device name may contain a meaningful device name, at this time, you can extract a meaningful device name (such as Mate10); for example, when the length of the acquired device name exceeds the preset length threshold, you can search for the delimiter in the device name (such as space, -, @ and other delimiters), and determine the content before the delimiter as a meaningful device name.

Optionally, when determining the device models of the multiple terminal devices according to the multiple device names having the first common feature, the device names may be case-insensitive, that is, the device names are not case-sensitive.

In another example, the pieces of equipment information include multiple MAC addresses, and in S402, the network equipment may determine the equipment of the multiple terminal equipment according to the second common feature of the multiple MAC addresses. model, said second common feature belongs to said common feature.

The fact that the multiple MAC addresses have the second common feature may be understood that the second common feature can be directly obtained from the content included in the multiple MAC addresses, or it may be understood that further analysis can be performed based on the multiple MAC addresses or deriving the second common characteristic.

Optionally, the second common feature is directly obtained from the content included in the multiple MAC addresses, and the network device may determine the second common feature according to consecutive bits of preset bit numbers in the multiple MAC addresses. . The preset number of bits is an integer greater than 0 and less than the length of the MAC address. For example, the consecutive bits of the preset number of bits may be the first 6 bits or the last 6 bits of the MAC address.

Alternatively, when deriving the second common feature from the plurality of MAC addresses, the network device may determine, according to the plurality of MAC addresses whose address distance is less than or equal to the second threshold, the corresponding MAC addresses. The plurality of terminal devices have a second common characteristic. The second threshold may be any value, and the second threshold may be set by a network administrator, or determined according to the address distance between the MAC addresses of terminal devices of the same device model currently on the market. This is because the MAC addresses of terminal devices of the same model are usually consecutive.

For example, the MAC address of the iPhone-8 mobile phone exists at 08:00:20:0A:8C:6D, and another terminal device has no device name or cannot identify the device model according to the device name, but the MAC address of the terminal device can be obtained as 08: 00:20:0A:8C:00, if the calculated address distance between the MAC address of the terminal device and the known MAC address of the iPhone-8 is less than or equal to the second threshold, the network device can determine the device of the terminal device. The model number is iPhone-8.

Or alternatively, the N pieces of device information include N MAC addresses, and when deriving the second common feature from the plurality of MAC addresses, the network device may further aggregate the N MAC addresses. class; the network device determines that the multiple MAC addresses have a second common feature according to the multiple MAC addresses of the multiple device information belong to the same clustering category; the network device determines that the multiple MAC addresses have the second common feature according to the second common feature , and determine the device models of the multiple terminal devices. For example, the second common feature is a certain clustering category in a clustering result obtained by clustering MAC addresses.

The process of clustering the N MAC addresses by the network device may be implemented by a clustering algorithm.

Before S402, the network device may also filter or reject MAC addresses that do not conform to the MAC address rule. The MAC address rules can be set by the network administrator.

In this embodiment of the present application, S401 and S402 may be performed each time a device model is identified. Alternatively, the network device can automatically establish and maintain a dynamic feature library based on the identification result of the device model, and subsequently identify the device model according to the feature library, thereby reducing the identification time of each device model and improving the device model identification efficiency. The feature library may include N device information of the N terminal devices, device models of the terminal devices, and common features of each device model (including the first common feature and/or the second common feature of each device model. ).

In this way, the network device can identify other terminal devices based on the identification results of the device models in S401 and S402. Exemplarily, the network device obtains first device information of a first terminal device, and the first terminal device is different from the N terminal devices; the network device extracts the first device information according to the first device information. The common feature is that the model of the first terminal device is determined to be the device model. That is, the network device may identify the acquired first device information based on the common features of the extracted device models.

If the first device information includes the first MAC address of the first terminal device, the network determines that the model of the first terminal device is the type of the first terminal device according to the common feature extracted from the first device information. When the device model is described: the network device may determine that the model of the first terminal device is the device model according to the presence of consecutive bits equal to or greater than the preset number of bits in the first MAC address and the M MAC addresses , wherein the M MAC addresses are the MAC addresses of M terminal devices in the multiple terminal devices, 1≤M≤N, and M is an integer.

Or when the network device determines that the model of the first terminal device is the device model according to the common feature extracted from the first device information: the network device may match the first MAC address with the device model according to the first MAC address. The address distances of the M MAC addresses are less than or equal to the second threshold, and it is determined that the model of the first terminal device is the device model, where the M MAC addresses are M terminal devices in the multiple terminal devices MAC address, 1≤M≤N, M is an integer.

Optionally, after S402, the network device may also obtain the access capability and/or behavior of the terminal device through the device model, so that the network device or other third-party devices can be based on the access capability of the terminal device. and/or behavior, perform targeted optimization on terminal equipment and provide customized services for terminal equipment, or help improve the service performance of the network equipment or other third-party equipment, etc. For example, the network device determines, according to the device model of the terminal device, that the terminal device is an old model with an earlier delivery time. Due to hardware limitations, this type of terminal device is generally similar to an access point (Access Point, AP). The maximum bandwidth cannot reach higher bandwidths such as 200M or 500M, so 50M or 100M bandwidth services can be recommended for such terminal equipment to avoid waste caused by too high bandwidth. Equipment model, determine that the terminal equipment is a newer model when it leaves the factory. This type of terminal equipment can reach 200M or 500M bandwidth, so a 200M or 500M bandwidth service can be recommended for this type of terminal equipment to bring better benefits to users. user experience. For another example, the network device determines that the negotiation rate of the terminal device is 128M according to the device model of the terminal device, and the gateway device and the terminal device communicate at a rate below 128M; or the network According to the device model of the terminal model, the device determines that the negotiation rate of the terminal device is 1024M, and the gateway device and the terminal device communicate at a rate below 1024M to ensure better and more stable performance for the user. user experience.

Exemplarily, the network device may extract K pieces of performance data according to K pieces of device information, where the K pieces of device information belong to the plurality of pieces of device information, where K≧1, and K is an integer. The performance data is used to determine the access capability and/or behavior of the terminal device.

The performance data includes the Wi-Fi access frequency band (that is, the access frequency band of the terminal device), the Wi-Fi access mode (that is, the Wi-Fi access mode of the terminal device), and the number of negotiated antennas (that is, the terminal device and the gateway). One or more of the number of antennas negotiated by the device), the negotiation rate (ie the rate negotiated by the terminal device and the gateway device), and the signal strength (including the transmitted signal strength of the terminal device and/or the received signal strength of the network device).

The network device may obtain the access capability and/or behavior of the terminal device of the device model according to the performance data; or, the network device may send the analysis data obtained according to the performance data to a third party, The third party acquires the access capability and/or behavior of the terminal device of the device model according to the analysis data. The third party may be, for example, an operator or a gateway. The obtained access capability of the terminal device may be the maximum access capability of the terminal device.

When the network device acquires one or more of the access capabilities and behaviors of the terminal device of the device model according to the performance data, it includes one or more of the following implementation manners. It can be understood that, any combination of one or more of the following implementations can be made.

Manner 1: The performance data includes multiple received signal strength indicators (RSSIs) of the multiple terminal devices, and the network device obtains, according to the distribution of the multiple RSSIs, a signal with the device model. Access achievable rate of the terminal device. The accessible access rate is an estimated value. The third party may provide customized services to the terminal device of the device model according to the access reachable rate.

Mode 2, the performance data includes K Wi-Fi access frequency bands of the K terminal devices, and the network device determines the terminal of the device model according to statistics on the K Wi-Fi access frequency bands The device supports single frequency access or dual frequency access. The single-frequency access means that the terminal equipment is connected through 2.4G or 5G, and the dual-frequency access means that the terminal equipment is connected through both 2.4G and 5G. For example, according to the K Wi-Fi access frequency bands, it is determined that the terminal device of the terminal model is connected through both 2.4G and 5G, then it can be determined that the terminal device of the terminal model supports dual-band access. The network device or the third party can support single-frequency access or dual-frequency access according to the terminal equipment, and can provide customized services for the terminal equipment. For example, the recommended bandwidth for single-frequency access terminal equipment is smaller than that for dual-frequency access. The recommended bandwidth of the incoming terminal device.

Mode 3, the performance data includes one or more of the K negotiated antenna numbers, K negotiated rates, and K Wi-Fi access modes of the K terminal devices, and the network device according to the K One or more of the number of negotiated antennas, the K negotiated rates, and/or the K Wi-Fi access modes, and the access capability of the terminal device with the device model is acquired. The network device can communicate with the terminal device according to the access capability of the terminal device. For example, the terminal device can communicate with the terminal device at a negotiated rate to avoid channel congestion or waste of communication resources. The access capability of the terminal device of the device model may include one or more of the maximum number of negotiated antennas, the maximum negotiated rate, and/or the maximum Wi-Fi access mode.

Manner 4, the performance data includes K signal strengths of the K terminal devices and one or more of the K Wi-Fi access frequency bands, and the network device is based on the K signal strengths and K Wi-Fi access frequency bands. - Fi access to one or more of the frequency bands, obtain the behavior of the terminal device with the device model. For example, when the third party determines that the terminal device of the device model is not within the management scope of the third party, for example, when it is determined that the terminal device has roaming behavior, it temporarily cuts off the channel provided for the terminal device, or the third party temporarily cuts off the channel provided for the terminal device. When it is determined that the terminal device returns to the management range, for example, when the behavior of the terminal device is a local behavior, a channel connection is re-established for the terminal device that has been in a non-roaming state, and the like.

One of the possible identification processes of the device model will be described below with reference to the network architecture shown in FIG. 1 and FIG. 2 .

The network management system sends the first command (such as the GET_SUB_DEVICE_LIST command) to the gateway through the remote channel, instructing the gateway to collect the list information of the DHCP STA mounted on the gateway.

The gateway collects list information of the mounted STAs, where the list information includes device information of the mounted STAs, and the number of the mounted STAs is multiple, for example, the number of the mounted STAs is 10,000. The information of the device mounted on the STA may include the MAC address of the STA, the device name of the STA, the access frequency band of the STA, the number of antennas negotiated by the STA and the gateway, the rate negotiated by the STA and the gateway, and the Wi-Fi access of the STA one or more of the patterns.

The network management system models the acquired device names in the STA-mounted device information, and generates a prefix tree, for example, generates a prefix tree for 10,000 device names in 10,000 device information. In other cases, the network management system may also select a part of the device names as required, such as 7000 device names to generate a prefix tree.

The network management system can determine the model of the device that mounts the STA according to the string corresponding to the last layer node (ie, the leaf node) and the set threshold. As shown in FIG. 7 , the gateway management system can determine the prefix. Device models in the tree include: iPhone-6, iPhone-8, and (HUAWEI)MATE 10.

And/or, the network device management system performs clustering on the acquired MAC addresses in the device information on which the STA is mounted, and can determine one or more clustering categories after the clustering, for example, 3000 of the 10,000 MAC addresses. The addresses are clustered into the same category, and the model of the device that mounts the STA is determined. For example, the network management system may determine, according to the clustering category, that the device models of the STAs mounted on the gateway include HUAWEI MATE 30 and HUAWEI P40.

Based on the foregoing FIG. 1 to FIG. 7 , an embodiment of the present application further provides a network device, and FIG. 8 is a schematic diagram of a network device 800 provided by an embodiment of the present application. The network device 800 can be applied to the network architecture shown in FIG. 1 or FIG. 2 , for example, it can be the network management system in the network architecture shown in FIG. 1 or FIG. operate.

As shown in FIG. 8 , the network device 800 may include a processor 801 , a memory 802 coupled to the processor 801 , and a transceiver 803 . The processor 801 may be a central processing unit (English: central processing unit, CPU), a network processor (English: network processor, NP), or a combination of CPU and NP. The processor 801 may further include a hardware chip. The above-mentioned hardware chip may be an application specific integrated circuit (English: application specific integrated circuit, ASIC), a programmable logic device (English: programmable logic device, PLD) or a combination thereof. The above-mentioned PLD can be a complex programmable logic device (English: complex programmable logic device, CPLD), a field programmable logic gate array (English: field programmable gate array, FPGA), a general-purpose array logic (English: generic array logic, GAL) or any combination thereof. The processor 801 may refer to one processor, or may include multiple processors. The memory 802 may include volatile memory (English: volatile memory), such as random access memory (English: random access memory, RAM); the memory may also include non-volatile memory (English: non-volatile memory), such as only Read memory (English: read only memory, ROM), flash memory (English: flash memory), hard disk drive (English: hard disk drive, HDD) or solid state hard disk (English: solid state disk, SSD); memory 802 can also Include a combination of the above types of memory. The memory 802 may refer to one memory, or may include multiple memories. The number of transceivers 803 may be one or more.

In this embodiment, the processor 801 performs corresponding operations according to the computer-readable instructions stored in the memory. For example, the processor 801 is configured to extract common features according to multiple device information of multiple terminal devices, and determine the device models of the multiple terminal devices. The transceiver 803 is configured to acquire N device information of the N terminal devices.

In one possible implementation, the computer-readable instructions stored in memory 802 may include software modules, such as processing module 804 . After executing each software module, the processor 801 can perform corresponding operations according to the instructions of each software module, and can cooperate with the transceiver 803 to complete the corresponding method steps.

FIG. 9 shows a schematic block diagram of a device model identification device 900 provided in an embodiment of the present application, and the device model identification device may be the network device (or a component having a network device function) in the foregoing FIG. 4 , or the device Components can be used with network equipment to support network equipment to achieve corresponding functions). The device model identification device 900 may exist in the form of software, or may be a chip that can be used for the device. The device type identification device 900 includes: a processing unit 901 and a transceiver unit 902 . Optionally, the transceiver unit 902 may be further divided into a sending unit (not shown in FIG. 9 ) and a receiving unit (not shown in FIG. 9 ). The sending unit is used to support the device model identification device 900 to send information to other network elements. The receiving unit is configured to support the device model identification apparatus 900 to receive information from other network elements.

If the device model identification device 900 is the network device mentioned above in FIG. 4 , the processing unit 901 can be used to support the network device in FIG. 4 to perform S401, S402, etc., and/or other processes for the solution described herein , for example, the network device obtains the access capability and/or behavior of the terminal device. The transceiver unit 902 is used to support communication between the network device and other network elements, for example, to support the network device in FIG. device information, etc.

It should be noted that the division method of the apparatus 900 described above is schematic, and the division of units may be the division of logical functions, and there may be other division or combination methods during specific implementation, and different division or combination methods do not affect the corresponding function realization.

An embodiment of the present application further provides a chip system, including: a processor, where the processor is coupled with a memory, the memory is used to store a program or an instruction, and when the program or instruction is executed by the processor, the The chip system implements the method in any of the foregoing method embodiments.

Optionally, the number of processors in the chip system may be one or more. The processor can be implemented by hardware or by software. When implemented in hardware, the processor may be a logic circuit, an integrated circuit, or the like. When implemented in software, the processor may be a general-purpose processor implemented by reading software codes stored in memory.

Optionally, there may also be one or more memories in the chip system. The memory may be integrated with the processor, or may be provided separately from the processor, which is not limited in this application. Exemplarily, the memory can be a non-transitory processor, such as a read-only memory ROM, which can be integrated with the processor on the same chip, or can be provided on different chips. The setting method of the processor is not particularly limited.

Exemplarily, the system-on-chip may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or a system on chip (SoC), It can also be a central processing unit (CPU), a network processor (NP), a digital signal processing circuit (DSP), or a microcontroller (microcontroller). controller unit, MCU), it can also be a programmable logic device (PLD) or other integrated chips.

It should be understood that, each step in the above method embodiments may be implemented by a hardware integrated logic circuit in a processor or an instruction in the form of software. The method steps disclosed in conjunction with the embodiments of the present application may be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

Embodiments of the present application further provide a computer-readable storage medium, where computer-readable instructions are stored in the computer storage medium, and when the computer reads and executes the computer-readable instructions, the computer is made to execute any of the foregoing method embodiments method in .

Embodiments of the present application further provide a computer program product, which, when the computer reads and executes the computer program product, causes the computer to execute the method in any of the above method embodiments.

An embodiment of the present application further provides a communication system, where the communication system includes a first network device and a terminal device for implementing the foregoing embodiments.

Optionally, the communication system may further include a second network device, and the second network device includes an operator management device and/or a gateway device.

An embodiment of the present application further provides a communication system, where the communication system includes a first network device and a second network device for implementing the foregoing embodiments.

Optionally, the second network device may be an operator management device and/or a gateway device.

Optionally, in other application scenarios, the second network device may also be a device such as a DSL device, a PON device, a router, and/or a switch.

It should be understood that the processor mentioned in the embodiments of the present application may be a central processing unit (central processing unit, CPU), and may also be other general-purpose processors, digital signal processors (digital signal processors, DSP), application-specific integrated circuits ( application specific integrated circuit, ASIC), off-the-shelf programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It should also be understood that the memory mentioned in the embodiments of the present application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory. Volatile memory may be random access memory (RAM), which acts as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synchlink DRAM, SLDRAM) ) and direct memory bus random access memory (direct rambus RAM, DR RAM).

It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components, the memory (storage module) is integrated in the processor.

It should be noted that the memory described herein is intended to include, but not be limited to, these and any other suitable types of memory.

It should be understood that, in the various embodiments of the present application, the size of the sequence numbers of the above-mentioned processes does not mean the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not be dealt with in the embodiments of the present invention. implementation constitutes any limitation.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above may refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution, and the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .

The above are only specific embodiments of the present application, but the protection scope of the present application is not limited to this. should be covered within the scope of protection of this application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

A device model identification method, characterized in that the method comprises:

The network device acquires N device information of N access devices, the N access devices and the N device information are in one-to-one correspondence, N≥2, and N is an integer;

The network device extracts common features of multiple device information of multiple access devices;

The network device determines the device models of the multiple access devices according to the common feature, wherein the multiple access devices belong to the N access devices, and the multiple device information belongs to the N access devices Device Information.
The method of claim 1, wherein the method further comprises:

obtaining, by the network device, first device information of a first access device, where the first access device is different from the N access devices;

The network device determines that the model of the first access device is the device model according to the common feature extracted from the first device information.
The method according to claim 1 or 2, wherein the N pieces of device information respectively include at least one or more of the following: a media access control MAC address of the access device or a device name of the access device.
The method according to claim 3, wherein the network device determines the device models of the multiple access devices according to the common feature, comprising:

The multiple device information includes multiple device names, the network device determines the device models of the multiple access devices according to the multiple device names having a first common feature, and the first common feature belongs to the common characteristics; or,

The multiple device information includes multiple MAC addresses, and the network device determines the device models of the multiple access devices according to the multiple MAC addresses having a second common feature, and the second common feature belongs to the Common feature.
The method of claim 4, wherein the method further comprises:

The network device determines that the first feature is the first common feature according to the number of occurrences of the first feature in the multiple device names exceeding a first threshold.
The method of claim 5, wherein the N pieces of device information include N device names, and the network device determines the number of device names according to the number of occurrences of the first feature of the plurality of device names exceeding a first threshold. The first feature is the first common feature, including:

generating, by the network device, a prefix tree according to the N device names;

The network device determines that the first feature is the first common feature according to the number of occurrences of the first feature of the multiple device names in the prefix tree exceeding a first threshold.
The method according to claim 4, wherein the N pieces of device information include N MAC addresses, and the network device determines the plurality of access devices according to the second common feature of the plurality of MAC addresses. device models, including:

The network device performs clustering on the N MAC addresses;

The network device determines that the multiple MAC addresses have a second common feature according to the multiple MAC addresses of the multiple device information belonging to the same clustering category;

The network device determines the device models of the multiple access devices according to the second common feature.
The method of claim 2, wherein the first device information includes a first media access control MAC address of the first access device, and the method further comprises:

The network device determines that the model of the first access device is the device model according to the presence of consecutive bits equal to or greater than a preset number of bits between the first MAC address and the M MAC addresses, wherein the The M MAC addresses are the MAC addresses of M access devices in the multiple access devices, 1≤M≤N, where M is an integer; or,

The network device determines that the model of the first access device is the device model according to the address distance between the first MAC address and the M MAC addresses being less than or equal to a second threshold, wherein the M MAC addresses is the MAC addresses of M access devices in the multiple access devices, 1≤M≤N, and M is an integer.
The method according to any one of claims 1-8, wherein after the network device determines the device models of the multiple access devices according to the common feature, the method further comprises:

The network device extracts K pieces of performance data according to the K pieces of equipment information, where the K pieces of equipment information belong to the plurality of pieces of equipment information, where K≧1, and K is an integer.
The method of claim 9, wherein the method further comprises:

The network device obtains, according to the performance data, the access capability and/or behavior of the access device of the device model; or,

The network device sends the analysis data obtained according to the performance data to a third party, so that the third party obtains the access capability and/or behavior of the access device of the device model according to the analysis data.
The method of claim 10, wherein the performance data comprises one or more of a Wi-Fi access frequency band, Wi-Fi access mode, number of negotiated antennas, negotiation rate, and signal strength Piece.
The method according to claim 11, wherein the network device acquires one or more of the access capabilities and behaviors of the access device of the device model according to the performance data, comprising:

The performance data includes multiple RSSIs of received signal strengths of the multiple access devices, and the network device obtains, according to the distribution of the multiple RSSIs, the accessible access rate of the access device with the device model ;or,

The performance data includes K Wi-Fi access frequency bands of the K access devices, and the network device determines the access device of the device model according to statistics on the K Wi-Fi access frequency bands Supports single-band access or dual-band access; or,

The performance data includes one or more of the K negotiated antenna numbers, K negotiated rates, and K Wi-Fi access modes of the K access devices, and the network device negotiates according to the K negotiated antennas. One or more of the number of antennas, K negotiated rates and/or K Wi-Fi access modes, to obtain the access capability of the access device with the device model; or,

The performance data includes K signal strengths of the K access devices and one or more of K Wi-Fi access frequency bands, the network device according to the K signal strengths and K Wi-Fi Access one or more of the frequency bands, and obtain the behavior of the access device with the device model.
The method of claim 10, wherein the third party comprises an operator management device or a gateway device.
The method according to any one of claims 1-13, wherein the access device comprises a terminal device.
A device type identification device, characterized in that it includes:

a transceiver unit, configured to acquire N pieces of device information of N pieces of access equipment, the N pieces of access equipment and the N pieces of equipment information are in one-to-one correspondence, N≥2, and N is an integer;

a processing unit, configured to extract common features of multiple device information of multiple access devices, and determine device models of the multiple access devices according to the common features, wherein the multiple access devices belong to the N access devices, and the multiple pieces of equipment information belong to the N pieces of equipment information.
The apparatus of claim 15, wherein the transceiver unit is further configured to acquire first device information of a first access device, and the first access device is different from the N access devices;

The processing unit is further configured to determine the model of the first access device as the device model according to the common feature extracted from the first device information.
The apparatus according to claim 15 or 16, wherein the N pieces of device information respectively include at least one or more of the following: a media access control MAC address of the access device or a device name of the access device.
The apparatus according to claim 17, wherein the processing unit is specifically configured to: the multiple device information includes multiple device names, and determine the multiple device names according to the first common feature of the multiple device names. The device model of each access device, the first common feature belongs to the common feature; or,

The multiple device information includes multiple MAC addresses, and the device models of the multiple access devices are determined according to the multiple MAC addresses having a second common feature, and the second common feature belongs to the common feature.
The apparatus according to claim 18, wherein the processing unit is further configured to determine that the first feature is the first feature according to the number of occurrences of the first feature in the multiple device names exceeding a first threshold The first common feature.
The apparatus according to claim 19, wherein the processing unit is specifically configured to: the N device information includes N device names, and generate a prefix tree according to the N device names; When the number of occurrences of the first feature of the plurality of device names exceeds a first threshold, the first feature is determined to be the first common feature.
The apparatus according to claim 17, wherein the processing unit is specifically configured to perform the clustering of the N MAC addresses according to the N device information including N MAC addresses; The multiple MAC addresses of the information belong to the same clustering category, and it is determined that the multiple MAC addresses have a second common feature; and the device models of the multiple access devices are determined according to the second common feature.
The apparatus of claim 16, wherein the processing unit is further configured to: the first device information includes a first media access control MAC address of the first access device, according to the first MAC address The address and M MAC addresses have consecutive bits equal to or greater than a preset number of bits, and the model of the first access device is determined to be the device model, wherein the M MAC addresses are the multiple access devices. MAC addresses of M access devices in the incoming device, 1≤M≤N, where M is an integer; or,

According to the address distance between the first MAC address and the M MAC addresses being less than or equal to a second threshold, it is determined that the model of the first access device is the device model, wherein the M MAC addresses are the multiple MAC addresses. MAC addresses of M access devices in the access devices, 1≤M≤N, where M is an integer.
The apparatus according to claims 15-22, wherein the processing unit is further configured to extract K pieces of performance data according to K pieces of equipment information, where the K pieces of equipment information belong to the plurality of pieces of equipment information, and K≥ 1, K is an integer.
The apparatus according to claim 23, wherein the processing unit is further configured to acquire, according to the performance data, the access capability and/or behavior of the access device of the device model; or,

The analysis data obtained according to the performance data is sent to a third party by the transceiver unit, so that the third party obtains the access capability and/or behavior of the access device of the device model according to the analysis data.
The apparatus of claim 24, wherein the performance data comprises one or more of Wi-Fi access frequency band, Wi-Fi access mode, number of negotiated antennas, negotiation rate, and signal strength.
The apparatus according to claim 25, wherein the performance data comprises multiple RSSIs of the multiple access devices, and the processing unit is configured to, according to the distribution of the multiple RSSIs, pass obtaining, by the transceiver unit, the access reachable rate of the access device with the device model; or,

The performance data includes K Wi-Fi access frequency bands of the K access devices, and the processing unit is configured to determine the connection of the device model according to statistics on the K Wi-Fi access frequency bands. The incoming device supports single-band access or dual-band access; or,

The performance data includes one or more of the K negotiated antenna numbers, the K negotiated rates, and the K Wi-Fi access modes of the K access devices, and the processing unit is configured to One or more of the number of negotiated antennas, K negotiated rates, and/or K Wi-Fi access modes, obtain the access capability of the access device with the device model through the transceiver unit; or,

The performance data includes K signal intensities of the K access devices and one or more of K Wi-Fi access frequency bands, and the processing unit is configured to - In one or more of the Fi access frequency bands, the transceiver unit acquires the behavior of the access device with the device model.
The apparatus of claim 24, wherein the third party comprises an operator management device or a gateway device.
The apparatus according to any one of claims 15-27, wherein the access device comprises a terminal device.
A network device, comprising a processor and a memory, wherein the processor is coupled with the memory;

memory for storing computer programs;

A processor for executing a computer program stored in the memory, so that the network device executes the method according to any one of claims 1-14.
A network system, characterized in that the system includes a first network device and a second network device, the first network device is configured to execute the method according to any one of claims 1-8,

The first network device is further configured to extract K pieces of performance data according to the K pieces of equipment information after determining the equipment models of the multiple pieces of access equipment according to the common features of the pieces of equipment information of the multiple pieces of access equipment. The K pieces of equipment information belong to the multiple pieces of equipment information, K≥1, K is an integer, and the access capability and/or behavior of the access equipment of the equipment model obtained according to the performance data is sent to the a second network device; or send the analysis data obtained according to the performance data to the second network device;

the second network device, configured to receive the access capability and/or behavior of the access device of the device model; or obtain the access capability and/or performance of the access device of the device model according to the analysis data .
The system of claim 30, wherein the performance data includes one or more of Wi-Fi access frequency band, Wi-Fi access mode, number of negotiated antennas, negotiation rate, and signal strength.
The system according to claim 31, wherein before the first network device acquires N device information of N access devices, the second network device is further configured to send the first network device the N device information, N≥2, N is an integer.
The system according to any one of claims 30-32, wherein the second network device is a gateway device or an operator management device.
The system according to any one of claims 30-33, wherein the first network device is a network management device.
The system according to any one of claims 30-34, wherein the access device is a terminal device.