CN110809309B - Access point identification method, device and storage medium - Google Patents

Abstract

The application discloses an access point identification method, an access point identification device and a storage medium, and belongs to the technical field of network positioning. The method comprises the following steps: acquiring a network identifier corresponding to a target access point; extracting key information of the network identification from the network identification; and determining the access point category of the target access point through an access point classification model according to the key information of the network identification, wherein the access point category is a mobile access point or a non-mobile access point, and the access point classification model is used for identifying the access point category of any access point. The method and the device avoid the problem that the identification error is easy to occur when the mobile access point is identified according to the MAC address, and improve the identification accuracy.

Description

Access point identification method, device and storage medium

Technical Field

The present application relates to the field of network positioning technologies, and in particular, to a method and an apparatus for identifying an access point, and a storage medium.

Background

In the technical field of network positioning, a device can be positioned according to the strength of a network signal received by the device from at least one surrounding access point and the position information of the at least one access point, which is stored in advance. However, since the access points generally include a mobile access point and a non-mobile access point, and the mobile access point refers to a mobile access point such as a mobile phone, the location changes frequently, and there may be an error between the pre-stored location information and the actual location information thereof, and therefore, when the mobile access point is included around the device, the location accuracy may be affected. Based on this, in the network positioning process, the mobile access points also need to be identified from the access points required for positioning, so as to filter the mobile access points.

In the related art, technicians may obtain MAC (Media Access Control) addresses of a large number of Access points in advance, and count the MAC addresses of the Access points to find out the rule applied to the MAC address of the mobile Access point. And then, for the target access point to be identified, firstly acquiring the MAC address of the target access point, then judging whether the MAC address of the target access point meets the rule of statistics in advance, if so, determining that the target access point is a mobile access point, and if not, determining that the target access point is a non-mobile access point.

However, when a merchant allocates a MAC address to an access point from which the merchant leaves the factory, the MAC address is often used in an irregular manner, so that some MAC addresses which should be originally allocated to non-mobile access points are allocated to mobile access points for use, and thus, an identification error is likely to occur when the mobile access points are identified according to the MAC addresses, and the identification accuracy is low.

Disclosure of Invention

The embodiment of the application provides an access point identification method, an access point identification device and a storage medium, which can be used for solving the problems that identification errors are easy to occur and the identification accuracy is low when mobile access points are identified according to MAC addresses in the related art. The technical scheme is as follows:

in one aspect, a method for identifying an access point is provided, where the method includes:

acquiring a network identifier corresponding to a target access point;

extracting key information of the network identification from the network identification;

and determining the access point category of the target access point through an access point classification model according to the key information of the network identifier, wherein the access point category is a mobile access point or a non-mobile access point, and the access point classification model is used for identifying the access point category of any access point.

Optionally, the extracting key information of the network identifier from the network identifier includes:

performing character segmentation on the network identification to obtain a character segmentation result;

and screening preset characters from the character segmentation result to obtain key information of the network identification, wherein the preset characters comprise meaningless characters and designated symbols.

Optionally, the determining, according to the key information of the network identifier, the access point category of the target access point through an access point classification model includes:

determining the probability that the target access point is a mobile access point through the access point classification model according to the key information of the network identifier;

if the probability is larger than a probability threshold value, determining that the target access point is a mobile access point;

and if the probability is less than or equal to the probability threshold, determining that the target access point is a non-mobile access point.

Optionally, the determining, according to the key information of the network identifier, the probability that the target access point is a mobile access point through the access point classification model includes:

taking the key information of the network identification as the input of the access point classification model, and determining the probability that the target access point is a mobile access point through the access point classification model; or,

and determining the network identification category to which the network identification belongs according to the key information of the network identification and the corresponding relation between the stored key information and the network identification category, taking the network identification category as the input of the access point classification model, and determining the probability that the target access point is a mobile access point through the access point classification model.

Optionally, before determining the access point category of the target access point through an access point classification model according to the key information of the network identifier, the method further includes:

acquiring key information of network identifications corresponding to a plurality of sample access points and access point categories of the plurality of sample access points;

and training the classification model of the access point to be trained according to the key information of the network identification corresponding to the plurality of sample access points and the access point categories of the plurality of sample access points to obtain the classification model of the access point.

Optionally, the training the classification model of the access point to be trained according to the key information of the network identifier corresponding to the multiple sample access points and the access point categories of the multiple sample access points includes:

clustering the network identifications corresponding to the sample access points according to the key information of the network identifications corresponding to the sample access points to obtain various network identification categories;

determining the access point category corresponding to each network identification category according to the access point category of the sample access point corresponding to at least one network identification included in each network identification category;

and training the access point classification model to be trained according to the multiple network identification categories and the access point categories corresponding to the multiple network identification categories to obtain the access point classification model.

Optionally, the determining, according to the access point category of the sample access point corresponding to at least one network identifier included in each network identifier category, an access point category corresponding to each network identifier category includes:

determining the mobile access point occupation ratio of each network identification type according to the access point type of the sample access point corresponding to at least one network identification included in each network identification type, wherein the access point occupation ratio refers to the occupation ratio of the mobile access point in the sample access point corresponding to at least one network identification included in each network identification type;

and determining the access point category corresponding to each network identification category according to the mobile access point proportion of each network identification category.

Optionally, the determining the access point category corresponding to each network identifier category according to the mobile access point proportion of each network identifier category includes:

if the proportion of the mobile access points in the reference network identification category is greater than a preset threshold value, determining that the access point category corresponding to the reference network identification category is the mobile access point, wherein the reference network identification is any one of the multiple network identification categories;

and if the proportion of the mobile access points of the reference network identifier category is less than or equal to a preset threshold value, determining that the access point category corresponding to the reference network identifier category is a non-mobile access point.

In one aspect, an apparatus for identifying an access point is provided, the apparatus including:

the first acquisition module is used for acquiring a network identifier corresponding to a target access point;

the extraction module is used for extracting key information of the network identifier from the network identifier;

and the determining module is used for determining the access point category of the target access point through an access point classification model according to the key information of the network identifier, wherein the access point category is a mobile access point or a non-mobile access point, and the access point classification model is used for identifying the access point category of any access point.

Optionally, the extraction module is configured to:

performing character segmentation on the network identification to obtain a character segmentation result;

and screening preset characters from the character segmentation result to obtain key information of the network identification, wherein the preset characters comprise meaningless characters and designated symbols.

Optionally, the determining module includes:

a first determining unit, configured to determine, according to the key information of the network identifier, a probability that the target access point is a mobile access point through the access point classification model;

a second determining unit, configured to determine that the target access point is a mobile access point if the probability is greater than a probability threshold;

a third determining unit, configured to determine that the target access point is a non-mobile access point if the probability is less than or equal to the probability threshold.

Optionally, the first determining unit is configured to:

taking the key information of the network identification as the input of the access point classification model, and determining the probability that the target access point is a mobile access point through the access point classification model; or,

and determining the network identification category to which the network identification belongs according to the key information of the network identification and the corresponding relation between the stored key information and the network identification category, taking the network identification category as the input of the access point classification model, and determining the probability that the target access point is a mobile access point through the access point classification model.

Optionally, the apparatus further comprises:

the second acquisition module is used for acquiring key information of network identifications corresponding to a plurality of sample access points and access point categories of the plurality of sample access points;

and the training module is used for training the classification model of the access point to be trained according to the key information of the network identification corresponding to the plurality of sample access points and the access point categories of the plurality of sample access points to obtain the classification model of the access point.

Optionally, the training module comprises:

the clustering unit is used for clustering the network identifications corresponding to the sample access points according to the key information of the network identifications corresponding to the sample access points to obtain various network identification categories;

a fourth determining unit, configured to determine, according to access point categories of sample access points corresponding to at least one network identifier included in each network identifier category, access point categories corresponding to each network identifier category;

and the training unit is used for training the access point classification model to be trained according to the multiple network identification categories and the access point categories corresponding to the multiple network identification categories to obtain the access point classification model.

Optionally, the fourth determining unit is configured to:

determining the mobile access point occupation ratio of each network identification type according to the access point type of the sample access point corresponding to at least one network identification included in each network identification type, wherein the access point occupation ratio refers to the occupation ratio of the mobile access point in the sample access point corresponding to at least one network identification included in each network identification type;

and determining the access point category corresponding to each network identification category according to the mobile access point proportion of each network identification category.

Optionally, the fourth determining unit is configured to:

if the proportion of the mobile access points in the reference network identification category is greater than a preset threshold value, determining that the access point category corresponding to the reference network identification category is the mobile access point, wherein the reference network identification is any one of the multiple network identification categories;

and if the proportion of the mobile access points of the reference network identifier category is less than or equal to a preset threshold value, determining that the access point category corresponding to the reference network identifier category is a non-mobile access point.

In one aspect, an apparatus for identifying an access point is provided, the apparatus including:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to perform the steps of the method of identifying an access point of any of the above.

In one aspect, a computer-readable storage medium is provided, having instructions stored thereon, which when executed by a processor, implement the steps of the method for identifying an access point according to any of the above.

The technical scheme provided by the embodiment of the application has the following beneficial effects:

in the embodiment of the application, the network identification corresponding to the target access point is obtained, the key information of the network identification is extracted from the network identification, and whether the target access point is a mobile access point or a non-mobile access point is determined through the access point classification model according to the key information of the network identification, so that the problem that identification errors easily occur when the mobile access point is identified according to an MAC address is solved, and the identification accuracy is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a method for training an access point classification model according to an embodiment of the present disclosure;

fig. 2 is a flowchart of an identification method of an access point according to an embodiment of the present disclosure;

FIG. 3 is a flow chart of a model training and prediction process provided by an embodiment of the present application;

fig. 4 is a block diagram of an identification apparatus of an access point according to an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of an identification apparatus for an access point according to an embodiment of the present disclosure.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

Before explaining the embodiments of the present application in detail, an environment in which the embodiments of the present application are implemented will be described. The method provided by the embodiment of the application is applied to the identification device of the access point, and the identification device can be a terminal or a server. For example, the terminal is a mobile phone, a tablet computer, a computer, or the like, and the identification device may be a background server of the network positioning system.

It should be noted that the method for identifying an access point provided in the embodiment of the present application is an identification method based on deep learning, and an access point classification model needs to be trained through deep learning before identifying a mobile access point.

Fig. 1 is a flowchart of a method for training an access point classification model according to an embodiment of the present disclosure, where the method is applied to an electronic device, where the electronic device may be a terminal or a server, and as shown in fig. 1, the method includes the following steps:

step 101: and acquiring key information of network identifications corresponding to the multiple sample access points and access point categories of the multiple sample access points.

The plurality of sample access points are access points meeting model training requirements and are used for training access point classification models. The access point category includes mobile access points and non-mobile access points. The mobile access point refers to an access point with a movable position, such as an access point or a mobile phone arranged on a vehicle. A non-mobile access point refers to an access point that is relatively fixed in location, such as a router or the like.

Each sample access point is used for accessing a wireless network, and the network identifier corresponding to each sample access point is the network identifier of the wireless network corresponding to each sample access point. For example, the network Identifier is an SSID (Service Set Identifier). The key information of the network identifier refers to backbone information extracted from the network identifier, and may indicate core content of the network identifier. For example, the key information of the network identifier may include chinese backbone information and/or english backbone information.

As an example, network identifiers corresponding to a plurality of sample access points may be obtained first, and then key information is extracted from the network identifier corresponding to each sample access point, so as to obtain key information of the network identifiers corresponding to the plurality of sample access points.

As an example, an implementation of extracting key information from a network identifier corresponding to each sample access point includes: performing character segmentation on the network identification corresponding to the target sample access point to obtain a character segmentation result; and screening preset characters from the character segmentation result to obtain key information of the network identification corresponding to the target sample access point.

The preset characters are preset characters needing to be screened out. For example, the preset characters may include some meaningless characters and designated symbols. For example, a nonsense character can be a character with insubstantial meaning such as "is", etc. The preset coincidences may be some special coincidences such as (), -,/,. and so on.

Wherein the access point classes of the plurality of sample access points are real access point classes of the plurality of sample access points. As an example, to improve the accuracy of the access point classes, the access point classes of the plurality of sample access points may be determined manually. In addition, after the access point categories of the multiple sample access points are obtained, the multiple sample access points may be labeled to obtain access point category labels of the multiple sample access points, where the access point category labels are used to indicate the access point categories of the sample access points.

Step 102: and training the access point classification model to be trained according to the key information of the network identification corresponding to the plurality of sample access points and the access point categories of the plurality of sample access points to obtain the access point classification model.

Wherein the access point classification model is used for identifying the access point category of any access point. For example, the access point category of any access point may be identified according to the key information of the network identifier corresponding to any access point.

Wherein, the access point classification model is a deep learning model. For example, the access point classification model may be an LR model, a CNN model, an RNN model, or the like.

In the embodiment of the present application, according to the key information of the network identifier corresponding to the multiple sample access points and the access point categories of the multiple sample access points, the operation of training the classification model of the access point to be trained may include the following several implementation manners:

the first implementation mode comprises the following steps: and directly taking the key information of the network identification corresponding to the sample access points and the access point categories of the sample access points as training data to train the classification model of the access point to be trained.

Specifically, key information of network identifiers corresponding to a plurality of sample access points can be used as input of the classification model of the access point to be trained, training categories of the plurality of sample access points are obtained, category errors are determined according to the training categories and the access point categories of the plurality of sample access points, model parameters of the classification model of the access point to be trained are adjusted according to the category errors, and the classification model of the access point to be trained after the model parameters are adjusted is determined.

As an example, the model parameters of the classification model of the access point to be trained may be adjusted by using a gradient descent method according to the class error. By way of example, the gradient descent method may be a random gradient descent method.

As an example, the training data may also include other data, such as location characteristics of each sample access point. For example, historical location information of each sample access point may be obtained, and location characteristics of each sample access point may be determined based on the historical location information of each sample access point.

As one example, the location characteristic may indicate a range of movement of the sample access point. For example, the location feature may be used to indicate a moving radius of the sample access point, or indicate a moving radius interval in which the moving radius of the sample access point is located. For example, if the moving radius of the sample access point is greater than the first threshold and less than the second threshold, the location characteristic of the sample access point is 0; if the moving radius of the sample access point is greater than or equal to the second threshold, the location characteristic of the sample access point is 1. The first threshold and the second threshold may be preset, for example, the first threshold is 5km, and the second threshold is 50 km.

As one example, the training data may also include a number of sample access points corresponding to various location feature classes in the plurality of sample access points. For example, the location features of a plurality of sample access points may be clustered to obtain a plurality of location feature categories, and the number of sample access points corresponding to the location features included in each location feature category may be determined.

As an example, the training data may further include a proportion of mobile access points in the plurality of sample access points, and of course, the training data may further include other characteristics of the sample access points, which is not limited in this embodiment of the present application.

The second implementation mode comprises the following steps: clustering network identifications corresponding to the multiple sample access points according to key information of the network identifications corresponding to the multiple sample access points to obtain multiple network identification categories; determining the access point category corresponding to each network identification category according to the access point category of the sample access point corresponding to at least one network identification included in each network identification category; and training the access point classification model to be trained according to the multiple network identification categories and the access point categories corresponding to the multiple network identification categories to obtain the access point classification model.

For example, if the network id of an ap installed on some high-speed rails usually contains the key information "HZA 50", the network ids containing HZA50 may be clustered together to obtain a network id category.

By clustering the network identifications corresponding to the sample access points according to the key information of the network identifications corresponding to the sample access points, the network identifications similar to the key information can be clustered together to obtain various network identification categories. Then, the network identification category and the access point category to which the network identification category belongs may be used as training data to train the access point classification model to be trained. In this way, the trained access point classification model can identify the access point class of the access point corresponding to each network identification class.

As an example, when determining the access point category corresponding to each network identification category according to the access point category of the sample access point corresponding to at least one network identification included in each network identification category, the access point category with a higher percentage of the access points corresponding to each network identification category may be determined as the access point category corresponding to each network identification category.

For example, the access point proportion of each network identifier category, which is the proportion of mobile access points in sample access points corresponding to at least one network identifier included in each network identifier category, may be determined according to the access point category of the sample access point corresponding to at least one network identifier included in each network identifier category; and determining the access point category corresponding to each network identification category according to the mobile access point proportion of each network identification category.

For example, if the proportion of the mobile access points in the reference network identifier category is greater than a preset threshold, determining that the access point category corresponding to the reference network identifier category is a mobile access point, and the reference network identifier is any one of the multiple network identifier categories; and if the proportion of the mobile access points of the reference network identifier category is less than or equal to a preset threshold value, determining that the access point category corresponding to the reference network identifier category is a non-mobile access point.

The preset threshold is a preset percentage threshold, for example, the preset threshold may be 50%, 60%, or 70%.

As an example, the training data corresponding to each network identification category may further include one or more of a location characteristic of a sample access point corresponding to at least one network identification included in each network identification category, a number of sample access points corresponding to each location characteristic category, and a proportion of mobile access points. Of course, the training data corresponding to each network identification category may also include other category features, which is not limited in this embodiment of the present application.

After the access point classification model is obtained through training, the access point category to which the access point belongs can be identified based on the access point classification model. Fig. 2 is a flowchart of an identification method for an access point according to an embodiment of the present application, where the method is used in an identification apparatus for an access point. Referring to fig. 2, the method includes:

step 201: and acquiring a network identifier corresponding to the target access point.

The target access point is an access point to be identified. The target access point may be, for example, any access point in the vicinity of the device to be located, i.e. any one of the at least one access point required for location.

Step 202: and extracting key information of the network identification from the network identification.

The key information of the network identifier refers to backbone information extracted from the network identifier, and may indicate core content of the network identifier. For example, the key information of the network identifier may include chinese backbone information and/or english backbone information.

As an example, implementations that can extract key information for each sample access point from the network identification include: carrying out character segmentation on the network identification to obtain a character segmentation result; and screening preset characters from the character segmentation result to obtain key information of the network identifier.

The preset characters are preset characters needing to be screened out. For example, the preset characters may include some meaningless characters and designated symbols. For example, a nonsense character can be a character with insubstantial meaning such as "is", etc. The preset coincidences may be some special coincidences such as (), -,/,. and so on.

For example, extracting the key information of the network identifier of the access point on a certain high-speed rail may obtain the key information: HZA50 are provided.

Step 203: and determining the access point category of the target access point through an access point classification model according to the key information of the network identification, wherein the access point category is a mobile access point or a non-mobile access point, and the access point classification model is used for identifying the access point category of any access point.

As an example, the probability that the target access point belongs to the mobile access point may be determined through an access point classification model according to the key information of the network identifier, and then the access point category of the target access point may be determined according to the probability that the target access point belongs to the mobile access point.

For example, if the probability is greater than the probability threshold, the target access point is determined to be a mobile access point; and if the probability is less than or equal to the probability threshold, determining that the target access point is a non-mobile access point. The probability threshold may be preset, for example, the probability threshold may be 0.5 or 0.6, and the like, which is not limited in this embodiment of the application.

As an example, the operation of determining the probability that the target access point belongs to the mobile access point through the access point classification model according to the key information of the network identification may include the following two implementation manners:

the first implementation mode comprises the following steps: and determining the probability that the target access point is a mobile access point by taking the key information of the network identifier as the input of an access point classification model.

The second implementation mode comprises the following steps: determining the network identification category to which the network identification belongs according to the key information of the network identification and the corresponding relation between the stored key information and the network identification category, taking the network identification category as the input of an access point classification model, and determining the probability that the target access point is a mobile access point through the access point classification model.

For example, if the key information of the network identifier is HZA50, the network identifier category may be determined to be a high-speed rail network identifier category, and then the network identifier category may be used as an input of an access point classification model, and a probability that the target access point is a mobile access point is determined through the access point classification model.

Further, the network identifier category to which the network identifier belongs can be determined according to the key information of the network identifier and the corresponding relationship between the format of the stored key information and the network identifier category.

As an example, in the process of network positioning the device, the device may be located according to the strength of a network signal received by the device from at least one surrounding access point, then identify each access point of the at least one access point according to the method of the embodiment of fig. 2, determine an access point category of each access point, then filter out mobile access points from the at least one access point, and based on the signal strength and location information of the filtered access points.

Referring to fig. 3, fig. 3 is a flowchart of a model training and predicting process provided in an embodiment of the present application, as shown in fig. 3, in the model training process, SSIDs of multiple sample access points, such as SSIDs of multiple high-speed rail access points, may be acquired, location information of multiple sample access points is acquired from a location acquisition table, then the SSIDs of multiple sample access points are character-segmented and screened to obtain keywords of the SSIDs corresponding to each sample access point, the SSIDs of multiple sample access points are clustered according to the corresponding keywords to obtain SSIDs of multiple categories, then feature extraction is performed on the sample access point corresponding to the SSID of each category to obtain features corresponding to the SSIDs of multiple categories and corresponding access point category labels, the features corresponding to the SSIDs of multiple categories and corresponding access point category labels are used as training data to train an access point classification model to be trained, and obtaining the trained access point classification model. In the model prediction process, key information of an SSID corresponding to any access point to be identified can be acquired, and the access point category of the access point is predicted through an access point classification model according to the key information of the SSID corresponding to the access point to be identified so as to identify whether the access point is a mobile access point.

In the embodiment of the application, the network identification corresponding to the target access point is obtained, the key information of the network identification is extracted from the network identification, and whether the target access point is a mobile access point or a non-mobile access point is determined through the access point classification model according to the key information of the network identification, so that the problem that identification errors easily occur when the mobile access point is identified according to an MAC address is solved, and the identification accuracy is improved.

Fig. 4 is a block diagram of an apparatus for identifying an access point according to an embodiment of the present application, where the apparatus includes a first obtainingmodule 401, an extractingmodule 402, and a determiningmodule 403.

A first obtainingmodule 401, configured to obtain a network identifier corresponding to a target access point;

an extractingmodule 402, configured to extract key information of the network identifier from the network identifier;

a determiningmodule 403, configured to determine, according to the key information of the network identifier, an access point category of the target access point through an access point classification model, where the access point category is a mobile access point or a non-mobile access point, and the access point classification model is used to identify an access point category of any access point.

Optionally, the extractingmodule 402 is configured to:

performing character segmentation on the network identification to obtain a character segmentation result;

and screening preset characters from the character segmentation result to obtain key information of the network identification, wherein the preset characters comprise meaningless characters and designated symbols.

Optionally, the determiningmodule 403 includes:

a first determining unit, configured to determine, according to the key information of the network identifier, a probability that the target access point is a mobile access point through the access point classification model;

a second determining unit, configured to determine that the target access point is a mobile access point if the probability is greater than a probability threshold;

a third determining unit, configured to determine that the target access point is a non-mobile access point if the probability is less than or equal to the probability threshold.

Optionally, the first determining unit is configured to:

taking the key information of the network identification as the input of the access point classification model, and determining the probability that the target access point is a mobile access point through the access point classification model; or,

and determining the network identification category to which the network identification belongs according to the key information of the network identification and the corresponding relation between the stored key information and the network identification category, taking the network identification category as the input of the access point classification model, and determining the probability that the target access point is a mobile access point through the access point classification model.

Optionally, the apparatus further comprises:

the second acquisition module is used for acquiring key information of network identifications corresponding to a plurality of sample access points and access point categories of the plurality of sample access points;

and the training module is used for training the classification model of the access point to be trained according to the key information of the network identification corresponding to the plurality of sample access points and the access point categories of the plurality of sample access points to obtain the classification model of the access point.

Optionally, the training module comprises:

the clustering unit is used for clustering the network identifications corresponding to the sample access points according to the key information of the network identifications corresponding to the sample access points to obtain various network identification categories;

a fourth determining unit, configured to determine, according to access point categories of sample access points corresponding to at least one network identifier included in each network identifier category, access point categories corresponding to each network identifier category;

and the training unit is used for training the access point classification model to be trained according to the multiple network identification categories and the access point categories corresponding to the multiple network identification categories to obtain the access point classification model.

Optionally, the fourth determining unit is configured to:

determining the mobile access point occupation ratio of each network identification type according to the access point type of the sample access point corresponding to at least one network identification included in each network identification type, wherein the access point occupation ratio refers to the occupation ratio of the mobile access point in the sample access point corresponding to at least one network identification included in each network identification type;

and determining the access point category corresponding to each network identification category according to the mobile access point proportion of each network identification category.

Optionally, the fourth determining unit is configured to:

if the proportion of the mobile access points in the reference network identification category is greater than a preset threshold value, determining that the access point category corresponding to the reference network identification category is the mobile access point, wherein the reference network identification is any one of the multiple network identification categories;

and if the proportion of the mobile access points of the reference network identifier category is less than or equal to a preset threshold value, determining that the access point category corresponding to the reference network identifier category is a non-mobile access point.

In the embodiment of the application, the network identification corresponding to the target access point is obtained, the key information of the network identification is extracted from the network identification, and whether the target access point is a mobile access point or a non-mobile access point is determined through the access point classification model according to the key information of the network identification, so that the problem that identification errors easily occur when the mobile access point is identified according to an MAC address is solved, and the identification accuracy is improved.

It should be noted that: the identification apparatus for an access point provided in the foregoing embodiment is only illustrated by the above-mentioned division of each functional module when identifying the category of the access point, and in practical applications, the above-mentioned function allocation may be completed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules, so as to complete all or part of the above-mentioned functions. In addition, the identification apparatus of the access point and the identification method of the access point provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.

Fig. 5 is a schematic structural diagram of anidentification apparatus 500 of an access point according to an embodiment of the present disclosure, where theidentification apparatus 500 may be an electronic device such as a terminal or a server, and theidentification apparatus 500 of the access point may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 501 and one ormore memories 502, where thememory 502 stores at least one instruction, and the at least one instruction is loaded and executed by theprocessors 501 to implement the identification method of the access point according to the above-mentioned method embodiments. Certainly, theidentification apparatus 500 of the access point may further include a wired or wireless network interface, a keyboard, an input/output interface, and other components to facilitate input and output, and theidentification apparatus 500 of the access point may further include other components for implementing functions of the device, which is not described herein again.

In an exemplary embodiment, a computer-readable storage medium is also provided, which stores instructions that when executed by a processor implement the above-mentioned method for identifying an access point.

In an exemplary embodiment, there is also provided a computer program product for implementing the above-mentioned method of identifying an access point when the computer program product is executed.

It should be understood that reference to "a plurality" herein means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims (7)

1. A method for identifying an access point, the method comprising:

acquiring a network identifier corresponding to a target access point;

extracting key information of the network identifier from the network identifier, wherein the key information is backbone information which is extracted from the network identifier and used for indicating core content of the network identifier;

determining a network identification category to which the network identification belongs according to the key information of the network identification and the corresponding relation between the stored key information and the network identification category, taking the network identification category as the input of an access point classification model, and determining the probability that the target access point is a mobile access point through the access point classification model, wherein the access point classification model is used for identifying the access point category of any access point;

if the probability is larger than a probability threshold value, determining that the target access point is a mobile access point;

if the probability is smaller than or equal to the probability threshold, determining that the target access point is a non-mobile access point;

before determining the probability that the target access point is a mobile access point through the access point classification model by taking the network identification category as an input of the access point classification model, the method further includes:

acquiring key information of network identifications corresponding to a plurality of sample access points and access point categories of the plurality of sample access points;

clustering the network identifications corresponding to the sample access points according to the key information of the network identifications corresponding to the sample access points to obtain various network identification categories;

determining the access point category corresponding to each network identification category according to the access point category of the sample access point corresponding to at least one network identification included in each network identification category;

and training the access point classification model to be trained according to the multiple network identification categories and the access point categories corresponding to the multiple network identification categories to obtain the access point classification model.

2. The method of claim 1, wherein the extracting key information of the network identifier from the network identifier comprises:

performing character segmentation on the network identification to obtain a character segmentation result;

and screening preset characters from the character segmentation result to obtain key information of the network identification, wherein the preset characters comprise meaningless characters and designated symbols.

3. The method according to claim 1, wherein the determining the access point category corresponding to each network identifier category according to the access point category of the sample access point corresponding to at least one network identifier included in each network identifier category comprises:

determining the mobile access point occupation ratio of each network identification type according to the access point type of the sample access point corresponding to at least one network identification included in each network identification type, wherein the access point occupation ratio refers to the occupation ratio of the mobile access point in the sample access point corresponding to at least one network identification included in each network identification type;

and determining the access point category corresponding to each network identification category according to the mobile access point proportion of each network identification category.

4. The method of claim 3, wherein determining the access point category corresponding to each network identifier category according to the mobile access point proportion of each network identifier category comprises:

if the proportion of the mobile access points in the reference network identification category is greater than a preset threshold value, determining that the access point category corresponding to the reference network identification category is the mobile access point, wherein the reference network identification is any one of the multiple network identification categories;

and if the proportion of the mobile access points of the reference network identifier category is less than or equal to a preset threshold value, determining that the access point category corresponding to the reference network identifier category is a non-mobile access point.

5. An apparatus for identifying an access point, the apparatus comprising:

the first acquisition module is used for acquiring a network identifier corresponding to a target access point;

an extraction module, configured to extract key information of the network identifier from the network identifier, where the key information is backbone information extracted from the network identifier and used for indicating core content of the network identifier;

a determining module, configured to determine, according to the key information of the network identifier, an access point category of the target access point through an access point classification model, where the access point category is a mobile access point or a non-mobile access point, and the access point classification model is used to identify an access point category of any access point;

the determining module comprises:

a first determining unit, configured to determine, according to the key information of the network identifier, a probability that the target access point is a mobile access point through the access point classification model;

a second determining unit, configured to determine that the target access point is a mobile access point if the probability is greater than a probability threshold;

a third determining unit, configured to determine that the target access point is a non-mobile access point if the probability is less than or equal to the probability threshold;

optionally, the first determining unit is configured to:

determining a network identification category to which the network identification belongs according to the key information of the network identification and the corresponding relation between the stored key information and the network identification category, taking the network identification category as the input of the access point classification model, and determining the probability that the target access point is a mobile access point through the access point classification model;

optionally, the apparatus further comprises:

the second acquisition module is used for acquiring key information of network identifications corresponding to a plurality of sample access points and access point categories of the plurality of sample access points;

the training module is used for training the classification model of the access point to be trained according to the key information of the network identification corresponding to the plurality of sample access points and the access point categories of the plurality of sample access points to obtain the classification model of the access point;

optionally, the training module comprises:

the clustering unit is used for clustering the network identifications corresponding to the sample access points according to the key information of the network identifications corresponding to the sample access points to obtain various network identification categories;

a fourth determining unit, configured to determine, according to access point categories of sample access points corresponding to at least one network identifier included in each network identifier category, access point categories corresponding to each network identifier category;

and the training unit is used for training the access point classification model to be trained according to the multiple network identification categories and the access point categories corresponding to the multiple network identification categories to obtain the access point classification model.

6. An apparatus for identifying an access point, the apparatus comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to perform the steps of any of the methods of claims 1-4.

7. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the steps of any of the methods of claims 1-4.

Images