CN115988609B

CN115988609B - Equipment classification method and device, electronic equipment and storage medium

Info

Publication number: CN115988609B
Application number: CN202211697902.6A
Authority: CN
Inventors: 唐舟进; 杨艳; 吴海峰; 冯亚辉; 郭树盛
Original assignee: Beijing Digital City Research Center
Current assignee: Beijing Digital City Research Center
Priority date: 2022-12-28
Filing date: 2022-12-28
Publication date: 2023-12-19
Anticipated expiration: 2042-12-28
Also published as: CN115988609A

Abstract

The invention provides a device classifying method, a device, an electronic device and a storage medium, wherein the device classifying method comprises the following steps: the gateway equipment acquires detection request frame information acquired by the acquisition equipment, and the detection request frame information is sent by at least one mobile equipment; the gateway equipment analyzes the detection request frame information to obtain an analysis result, wherein the analysis result comprises first information and second information; the gateway equipment updates the first virtual equipment sequence set according to the first information and the second information to obtain a second virtual equipment sequence set; the gateway device classifies the at least one mobile device according to the second set of virtual device sequences. The method and the device can classify the equipment, thereby improving the effect of randomizing the Wi-Fi MAC address.

Description

Equipment classification method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of communications technologies, and in particular, to a device classification method, a device, an electronic device, and a storage medium.

Background

With the continuous development of science and technology, mobile devices are also becoming popular comprehensively, operators are accelerating deployment of wireless fidelity (Wireless Fidelity, wi-Fi) hotspots, a good foundation is laid for Wi-Fi positioning-based research and application, and in addition, wi-Fi-enabled mobile devices can periodically search for nearby available networks through a broadcast Probe Request (Probe Request) frame and connect with the networks. The media Access control (Medium Access Control, MAC) address carried by the Probe Request frame is a unique identifier of the device, and by using the MAC address, communication can be quickly established between the device and an Access Point (AP), and by combining Probe Request frame data with time information with a positioning technology, the track of the user of the mobile device can be tracked.

In the prior art, in order to protect user privacy, a mobile device introduces a MAC address randomization mechanism, so that the discontinuity of Wi-Fi uplink signals of the mobile device identified under a non-cooperative condition cannot be realized, association between a user and the device is also not realized, and a deep learning method is generally adopted to remove the MAC address randomization of Wi-Fi, but prior knowledge which is difficult to acquire is required to be acquired, so that a certain limitation is brought.

Therefore, the problem of poor randomization effect on Wi-Fi MAC addresses exists in the prior art.

Disclosure of Invention

The embodiment of the invention provides a device classifying method, a device, electronic equipment and a storage medium, which are used for solving the problem of poor randomization effect on Wi-Fi MAC addresses in the prior art.

In a first aspect, an embodiment of the present invention provides a device classifying method, including:

the gateway equipment acquires detection request frame information acquired by the acquisition equipment, and the detection request frame information is sent by at least one mobile equipment;

the gateway equipment analyzes the detection request frame information to obtain an analysis result, wherein the analysis result comprises first information and second information;

the gateway device updates a first virtual device sequence set according to the first information and the second information to obtain a second virtual device sequence set, wherein the first virtual device sequence set comprises at least one virtual device sequence, each virtual device sequence comprises at least one Media Access Control (MAC) group, the second virtual device sequence set comprises at least one virtual device sequence, and each virtual device sequence comprises at least one MAC group;

The gateway device classifies the at least one mobile device according to the second set of virtual device sequences.

Optionally, the first information includes a target field, and the second information includes a MAC address, a signal strength value, a timestamp, and a frame sequence number;

the gateway device updates the first virtual sequence device set according to the first information and the second information to obtain a second virtual device sequence set, and the method comprises the following steps:

under the condition that a target MAC address meets a first preset condition, the gateway equipment updates a target signal strength value, a target timestamp and a target frame sequence number which are associated with the target MAC address to the first virtual equipment sequence set so as to obtain the second virtual equipment sequence set;

the target MAC address is any one MAC address in the probe request frame information, and the first preset condition indicates that a MAC address matching the target MAC address exists in the first virtual device sequence set.

Optionally, the gateway device updates the first virtual device sequence set according to the first information and the second information to obtain a second virtual device sequence set, and further includes:

Under the condition that the target MAC address does not meet the first preset condition and the target field meets the second preset condition, the gateway equipment calculates a similarity score associated with the target MAC address according to the target field;

the gateway device updates the target signal strength value, the target timestamp and the target frame sequence number associated with the target MAC address to the first virtual device sequence set according to the similarity score to obtain the second virtual device sequence set;

the target MAC address indicates any one MAC address in the probe request frame information, and the second preset condition indicates that a target field matched with the target field exists in the first virtual device sequence set.

Optionally, in the case that the target MAC address does not meet the first preset condition and the target field meets the second preset condition, the gateway device calculates, according to the target field, a similarity score associated with the target MAC address, including:

the gateway device calculates a time difference value set of a target time stamp and a time stamp in at least one target virtual device sequence, and calculates a sequence number difference value set of a target frame sequence number and a frame sequence number in the at least one target virtual device, wherein the target time stamp represents a time stamp matched with the target MAC address, and the target virtual device sequence represents any virtual device sequence in the first virtual device sequence set;

And the gateway equipment determines the similarity score of the at least one target virtual equipment sequence according to the time difference value group and the serial number difference value group.

Optionally, in the case that the target field does not meet the second preset condition, the gateway device creates a newly added virtual device sequence, and adds target first information and target second information to the newly added virtual device sequence;

the target first information represents first information of the target MAC address matching, and the target second information represents second information of the target MAC address matching.

Optionally, the gateway device updates the first virtual device sequence set according to the following rule:

the gateway device splices the target MAC address, the target timestamp, the target signal strength value, the target frame sequence number and the target field to the last position of the matched virtual device sequence;

the target timestamp represents a timestamp of the target MAC address match, the target signal strength value represents a signal strength value of the target MAC address match, and the target frame sequence number represents a frame sequence number of the target MAC address match.

Optionally, after the gateway device classifies the at least one mobile device according to the second set of virtual device sequences, the method further comprises:

the gateway device sends the second set of virtual device sequences to a server.

In a second aspect, an embodiment of the present invention further provides a device classifying method, including:

the method comprises the steps that a server obtains a second virtual device sequence set and detection request frame information sent by gateway devices, wherein the detection request frame information is sent by at least one gateway device;

the server constructs a feature matrix according to the second virtual equipment sequence set;

the server performs clustering processing on the feature matrix to obtain identification features for distinguishing different mobile devices;

the server classifies the mobile device according to the identification feature and the detection request frame information.

Optionally, the server constructs a feature matrix according to the second virtual device sequence set, including:

the server determines feature information and statistical information according to the second virtual device sequence set, wherein the feature information comprises at least one of the following: field information, signal strength value, timestamp and frame sequence number, wherein the statistical information comprises at least one of the following: standard deviation and average value of signal intensity values and standard deviation and average value of time intervals;

And constructing a feature matrix according to the feature information and the statistical information.

Optionally, the server classifies the mobile device according to the identification feature and the probe request frame information, including:

the server calculates the Euclidean distance corresponding to the detection request frame information according to the identification characteristics;

and the server determines the type of the mobile equipment corresponding to the detection request frame information according to the Euclidean distance and classifies the mobile equipment.

In a third aspect, an embodiment of the present invention provides an apparatus for classifying devices, including:

the acquisition module is used for acquiring the detection request frame information acquired by the acquisition equipment, wherein the detection request frame information is sent by at least one mobile equipment;

the analysis module is used for carrying out analysis processing on the detection request frame information to obtain an analysis result, wherein the analysis result comprises first information and second information;

an updating module, configured to update a first virtual device sequence set according to the first information and the second information to obtain a second virtual device sequence set, where the first virtual device sequence set includes at least one virtual device sequence, each virtual device sequence includes at least one media access control MAC group, and the second virtual device sequence set includes at least one virtual device sequence, and each virtual device sequence includes at least one MAC group;

And the classifying module is used for classifying the at least one mobile device according to the second virtual device sequence set.

Optionally, the updating module includes:

a first updating unit, configured to update, when a target MAC address meets a first preset condition, a target signal strength value, a target timestamp, and a target frame sequence number associated with the target MAC address to the first virtual device sequence set, so as to obtain the second virtual device sequence set;

Optionally, the updating module further includes:

a calculating unit, configured to calculate, according to the target field, a similarity score associated with the target MAC address when the target MAC address does not satisfy the first preset condition and the target field satisfies a second preset condition;

a second updating unit, configured to update the target signal strength value, the target timestamp, and the target frame sequence number associated with the target MAC address to the first virtual device sequence set according to the similarity score, so as to obtain the second virtual device sequence set;

Optionally, the computing unit includes:

the device classifying device calculates a time difference value group of a target time stamp and a time stamp in at least one target virtual device sequence, and calculates a sequence number difference value group of a target frame sequence number and a frame sequence number in the at least one target virtual device, wherein the target time stamp represents a time stamp matched with the target MAC address, and the target virtual device sequence represents any virtual device sequence in the first virtual device sequence set;

the device classifying means determines a similarity score for the at least one target virtual device sequence based on the set of time differences and the set of sequence number differences.

Optionally, in the case that the target field does not meet the second preset condition, the device classifying device creates an added virtual device sequence, and adds target first information and target second information to the added virtual device sequence;

Optionally, the device classifying means updates the first virtual device sequence set according to the following rule:

splicing the target MAC address, the target timestamp, the target signal strength value, the target frame sequence number and the target field to the last position of the matched virtual device sequence;

Optionally, the device classifying apparatus further includes:

and the sending module is used for sending the second virtual equipment sequence set to a server.

In a fourth aspect, an embodiment of the present invention further provides an apparatus for classifying devices, including:

the acquisition module is used for acquiring a second virtual device sequence set and detection request frame information sent by gateway equipment, wherein the detection request frame information is sent by at least one gateway equipment;

The construction module is used for constructing a feature matrix according to the second virtual equipment sequence set;

the processing module is used for carrying out clustering processing on the feature matrix to obtain identification features for distinguishing different mobile devices;

and the classifying module is used for classifying the mobile equipment according to the identification characteristics and the detection request frame information.

Optionally, the building module includes:

the first determining unit is configured to determine feature information and statistical information according to the second virtual device sequence set, where the feature information includes at least one of the following: field information, signal strength value, timestamp and frame sequence number, wherein the statistical information comprises at least one of the following: standard deviation and average value of signal intensity values and standard deviation and average value of time intervals;

and the construction unit is used for constructing a feature matrix according to the feature information and the statistical information.

Optionally, the classifying module includes:

the calculating unit is used for calculating the Euclidean distance corresponding to the detection request frame information according to the identification characteristics;

and the second determining unit is used for determining the type of the mobile equipment corresponding to the detection request frame information according to the Euclidean distance and classifying the mobile equipment.

In a fifth aspect, an embodiment of the present invention provides an electronic device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the device classification method of the first aspect.

In a sixth aspect, an embodiment of the present invention provides an electronic device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the device classification method of the second aspect.

In a seventh aspect, embodiments of the present invention provide a non-transitory computer readable storage medium storing computer instructions comprising:

the computer instructions are for causing the computer to perform the device classification method according to the first aspect or the computer instructions are for causing the computer to perform the device classification method according to the second aspect.

In this embodiment, the gateway device first obtains the probe request frame information collected by the collection device, then, the gateway device analyzes the probe request frame information to obtain an analysis result including first information and second information, the gateway device updates the first virtual device sequence set according to the first information and the second information, that is, adds the first information and the second information meeting the conditions to the first virtual device sequence set to obtain a second virtual device sequence set, the second virtual device sequence set includes at least one virtual device sequence, each virtual device sequence represents a device type, and finally, the gateway device classifies the mobile device according to the second virtual device sequence set.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of a device classifying method according to an embodiment of the present invention;

FIG. 2 is a second flow chart of a method for classifying devices according to the embodiment of the present invention;

FIG. 3 is a third flow chart of a method for classifying devices according to an embodiment of the present invention;

FIG. 4 is a flowchart of a method for classifying devices according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a method for classifying devices according to an embodiment of the present invention;

FIG. 6 is a flowchart of a method for classifying devices according to an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of a device classifying apparatus according to an embodiment of the present invention;

FIG. 8 is a second schematic diagram of a device classifying apparatus according to an embodiment of the present invention;

Fig. 9 is a block diagram of an electronic device for implementing a device classification method according to an embodiment of the invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The terms "first," "second," and the like in embodiments of the present invention are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Referring to fig. 1, fig. 1 is a flow chart of a device classifying method according to an embodiment of the present invention, as shown in fig. 1, including the following steps:

Step 101, gateway equipment acquires detection request frame information acquired by acquisition equipment, wherein the detection request frame information is sent by at least one mobile equipment;

102, the gateway equipment analyzes the detection request frame information to obtain an analysis result, wherein the analysis result comprises first information and second information;

step 103, the gateway device updates a first virtual device sequence set according to the first information and the second information to obtain a second virtual device sequence set, wherein the first virtual device sequence set comprises at least one virtual device sequence, each virtual device sequence comprises at least one media access control MAC group, the second virtual device sequence set comprises at least one virtual device sequence, and each virtual device sequence comprises at least one MAC group;

step 104, the gateway device classifies the at least one mobile device according to the second virtual device sequence set.

The steps 101, 102, 103, and 104 included in the device classifying method may be performed by the gateway device, which is not limited to the embodiment of the present invention.

In step 101, the collecting device may collect probe request frame information broadcast by all mobile devices in a coverage area, for example: the acquisition device may be a Wi-Fi sniffer or a Wi-Fi identifier, where the Wi-Fi sniffer or the Wi-Fi identifier may operate in a monitoring mode, collect probe request frame information broadcast by all mobile devices within a coverage area of the Wi-Fi sniffer or the Wi-Fi identifier, and send the collected probe request frame information to the gateway device.

It should be noted that, the mobile device may be a device configured with a Wi-Fi module, that is, a device having a Wi-Fi function, which is not limited to the embodiment of the present invention.

In addition, the Wi-Fi sniffer or the Wi-Fi identifier may collect probe request frame information sent by at least one mobile device in a coverage area in a monitoring mode, and in a case where there are a plurality of mobile devices in the coverage area broadcasting the probe request frame information, the Wi-Fi sniffer or the Wi-Fi identifier may collect all the probe request frame information in the coverage area.

In step 102, the gateway device analyzes the acquired probe request frame information to obtain the first information and the second information, where the first information may be represented by information such as a target field of the probe request frame information, and the second information may be represented by information such as a media access control (Medium Access Control, MAC) address carried by the probe request frame information or a signal strength corresponding to the probe request frame information.

In step 103, the first set of virtual device sequences includes at least one virtual device sequence, each virtual device sequence includes at least one media access control MAC group, where one virtual device sequence may be understood as a device type, and one virtual device sequence may include at least one MAC group, which may be understood as data related to a device type.

It should be understood that, the gateway device may splice the second information into one of the virtual device sequences in the first virtual device sequence set based on the first information, so as to complete updating the first virtual device sequence set to obtain the second virtual device sequence set, and the process may also be understood as splicing the probe request frame information acquired by the acquisition device into the virtual device sequence corresponding to the same device or different devices.

In step 104, the gateway device classifies the mobile device sending the probe request frame information according to the second virtual device sequence set, where the gateway device may determine whether a plurality of probe request frame information is sent by the same device, thereby establishing an association relationship between the same mobile device and different MAC addresses, and further improving the effect of randomizing the Wi-Fi MAC addresses.

In this embodiment, the gateway device first obtains the probe request frame information collected by the collecting device, then, the gateway device analyzes the probe request frame information to obtain an analysis result including first information and second information, the gateway device updates the first virtual device sequence set according to the first information and the second information, that is, adds the first information and the second information meeting the conditions to the first virtual device sequence set, thereby obtaining a second virtual device sequence set, the second virtual device sequence set includes at least one virtual device sequence, each virtual device sequence represents a device type, and finally, the gateway device classifies the mobile device according to the second virtual device sequence set.

The gateway device may locally maintain a virtual device set, that is, the first virtual device sequence set, where the first virtual device sequence set may be information recorded in a table form, and the first column of the first virtual device sequence set is a virtual device number after performing MAC address concatenation, that is, the virtual device sequence.

It should be understood that, as information is continuously collected and acquired, the number of virtual devices represented in the first set of virtual device sequences also varies continuously, and the MAC group included in each virtual device sequence also increases continuously, that is, the MAC groups spliced after each virtual device sequence may increase continuously.

In this embodiment, the probe request frame information may include the first information and the second information, and the second information may include a MAC address, a signal strength value, a timestamp, and a frame sequence number, where in the case that there is a MAC address matching the target MAC address in the first virtual device sequence set, the gateway device may update the target field, the target signal strength value, the target timestamp, and the target frame sequence number associated with the target MAC address to the first virtual device sequence set to obtain the second virtual device sequence set, by using this method, an association relationship between the same mobile device and different MAC addresses may be established, thereby improving an effect of removing Wi-Fi MAC address randomization, and laying a foundation for further solving continuous positioning and track tracing of the mobile device under non-cooperative conditions.

It should be appreciated that the MAC address randomization mechanism introduced by the mobile device may break the Wi-Fi uplink signal, i.e. the continuity and semantics of the probe request frame, resulting in fragmentation of data collection and analysis, such that the Wi-Fi uplink signal of the mobile device is discontinuous under non-cooperative conditions, in embodiments of the present invention, the continuity of information is exploited, for example: the gateway device splices the related data of the MAC address, which can be understood as splicing the related data of different MAC addresses of the same device together, thereby realizing the purpose of randomizing the MAC address.

The relevant data of the MAC address, namely, the target field, the target signal strength value, the target timestamp, and the target frame sequence number.

In addition, the MAC groups may be composed of various MAC address related data, each MAC group including but not limited to:

1. a MAC address.

2. The timestamp of the last piece of data associated with the MAC address.

3. The signal strength value of the last piece of data associated with the MAC address.

4. The frame sequence number of the last piece of data associated with the MAC address.

5. The destination field of the last piece of data associated with the MAC address.

In this embodiment, when there is no MAC address matching the target MAC address in the first virtual device sequence set and there is a target field matching the target field in the first virtual device sequence set, the gateway device calculates a similarity score associated with the target MAC address, and then splices the first information and the second information corresponding to the target MAC address into a virtual device sequence with the highest matching degree according to the similarity score, thereby completing updating the first virtual device sequence set and obtaining the second virtual device sequence set. By the method, the association relation between the same mobile equipment and different MAC addresses can be established, so that the effect of randomizing the Wi-Fi MAC addresses is improved, and a foundation is laid for further solving the continuous positioning and track tracking of the mobile equipment under the non-cooperative condition.

The target field may be an HT Capabilities field or a VHT Capabilities field, that is, the gateway device may distinguish different terminals according to the HT Capabilities field or the VHT Capabilities field, or may distinguish different models under the same brand of terminal.

It should be noted that, the embodiment of the present invention may be based on Wi-Fi4, wi-Fi5 or Wi-Fi6 versions, so that the embodiment of the present invention supports both 802.11n and 802.11ac protocols, and the target field may be found to have a certain effect on distinguishing brand models by comparing the VHT Capabilities field under the 802.11ac protocol with the HT Capabilities field under the 802.11n protocol.

In this embodiment, the gateway device calculates the similarity score of the second information corresponding to the target MAC address, where a time difference set between a target timestamp and a timestamp in at least one target virtual device sequence is calculated, and a sequence number difference set between a target frame sequence number and a frame sequence number in the at least one target virtual device is calculated, so as to determine the similarity score of the at least one target virtual device sequence.

The similarity score may be calculated as follows:

1. the time difference between the timestamp of the current data and the last associated timestamp of the jth MAC group (MAC-j) of device k is calculated.

2. The difference between the frame sequence number of the current data and the last associated frame sequence number of the j-th MAC group (MAC-j) of device k is calculated.

3. The similarity score for the current data and the j-th MAC group (MAC-j) of device k is calculated.

4. And calculating the similarity score of the current data and the device k.

And classifying the current data into the devices (the virtual device sequence is n) according to the principle of maximum similarity score (the sequence number where the maximum similarity score is located is set as n), and updating the last timestamp, the last frame sequence number and the last target field associated with the target MAC group in the first virtual device sequence set to obtain the second virtual device sequence set.

In this embodiment, in the case that the MAC address matching the target MAC address does not exist in the first set of virtual device sequences and the target field matching the target field does not exist in the first set of virtual device sequences, the gateway device may create a new virtual device sequence, and add the target first information and the target second information to the new virtual device sequence.

In some optional implementations, please refer to fig. 2, fig. 2 is a flow chart of another device classifying method provided by the embodiment of the present invention, as shown in fig. 2, the current data is first parsed in the gateway device, where the current data is Wi-Fi data, and the Wi-Fi data may be understood as uplink data sent by the mobile device, that is, probe request frame information, so as to obtain a MAC address of the current data, a signal strength value of the current data, a target field of the current data, a timestamp of the current data, and a frame sequence number of the current data.

Then traversing according to the virtual device sequences in the virtual device sequence set, judging whether the MAC address which is the same as the MAC address of the current data exists in the virtual device sequence set, if so, assigning the number corresponding to the 5 virtual device sequences to the current data, namely updating the current data in the virtual device sequence set; if the target field of the current data does not exist in the virtual device sequence set, judging whether the target field of the current data exists in the virtual device sequence set, and judging whether the absolute time corresponding to the current data timestamp is larger than the time in the virtual device sequence set.

Under the condition that the target field of the current data exists in the virtual equipment sequence set and the absolute time corresponding to the current data timestamp is larger than the time in the virtual equipment sequence set, the following four items are calculated in sequence: 0 1. The time difference between the absolute time of the current data and the last association time of the MAC group in the target device.

2. The difference between the frame sequence number of the current data and the last associated frame sequence number of the MAC group in the target device.

3. The current data has a similarity score to the MAC group in the target device.

4. The similarity score of the current data to the target device.

And classifying the current data into the target equipment meeting the conditions according to the principle of maximum similarity score.

And 5, adding a new virtual device in the virtual device sequence set under the condition that the target field of the current data does not exist in the virtual device sequence set or the absolute time corresponding to the current data timestamp is smaller than or equal to the time in the virtual device sequence set, wherein the new virtual device comprises the virtual device sequence, the non-repeated MAC address, the last absolute time associated with the MAC address, the last frame serial number associated with the MAC address and the last target field associated with the MAC address.

0 optionally, after the gateway device classifies the at least one mobile device according to the second set of virtual device sequences, the method further comprises:

Referring to fig. 3, fig. 3 is a flow chart of another device classifying method provided by the embodiment of the present invention, referring to fig. 3, wi-Fi data is firstly obtained by a sniffer, the Wi-Fi data can be understood as uplink data sent by 5 mobile devices, namely, probe request frame information, then the sniffer sends the Wi-Fi data to a gateway end, the gateway end analyzes the Wi-Fi data, and then carries out first MAC address removal randomization processing on the Wi-Fi data to obtain a first processing result, the gateway end transmits the first processing result to a server end, and the server end carries out second MAC address removal randomization processing according to the first processing result to obtain a second processing result, thereby completing classification of the mobile devices, and further positioning the mobile devices according to the second processing result.

Referring to fig. 4, fig. 4 is a flow chart of another device classifying method according to an embodiment of the present invention, as shown in fig. 4, including the following steps:

Step 401, a server acquires a second virtual device sequence set and probe request frame information sent by gateway devices, wherein the probe request frame information is sent by at least one gateway device;

step 402, the server builds a feature matrix according to the second virtual device sequence set;

step 403, the server performs clustering processing on the feature matrix to obtain identification features for distinguishing different mobile devices;

step 404, the server classifies the mobile device according to the identification feature and the probe request frame information.

In this embodiment, the server first obtains the first set of virtual device sequences sent by the gateway device, then uses information in the second virtual device sequence to construct the feature matrix, clusters the feature matrix to generate unique identification features capable of distinguishing different devices, and when the server recognizes new data, classifies mobile devices corresponding to the data according to the unique identification features. By the method, the detection request frame information is further classified, so that the classification accuracy is improved, the effect of randomizing Wi-Fi MAC addresses is improved, and a foundation is laid for further solving the continuous positioning and track tracking of the mobile equipment under the non-cooperative condition.

In this embodiment, firstly framing Wi-Fi signals, calculating statistical information including standard deviation and mean of signal intensity and standard deviation and mean of time interval for intra-group signals within the frame window length, and secondly combining information elements (including but not limited to HT Capabilities field or VHT Capabilities field in case of the information elements being target fields) in the parsed probe request frame information and statistical information of Wi-Fi signals (including but not limited to standard deviation and mean of signal intensity and standard deviation and mean of time interval) into a feature matrix. By means of the method, the device classification is carried out by utilizing the feature matrix, accuracy of the embodiment of the invention when the first virtual device sequence set is updated is improved, and therefore effect of randomizing Wi-Fi MAC addresses is improved.

After the feature matrix is obtained, a normalization method can be adopted to process the data, and the number is changed into the decimal between (0 and 1), namely, the data is mapped to the range of 0 to 1 for processing, so that the data processing is more convenient and rapid, and the processing efficiency is improved.

Optionally, the classifying, by the server, the mobile device according to the identification feature and the probe request frame information includes:

In some optional implementations, please refer to fig. 5, fig. 5 is a schematic diagram of a device classifying method provided by an embodiment of the present invention, as shown in fig. 5, a Wi-Fi sniffer may collect probe request frame information sent by all mobile devices in a coverage area and transmit the probe request frame information to a data analysis gateway, perform a first device classifying process in the data analysis gateway, then the data analysis gateway transmits a result of the first device classifying process to a passive positioning server, and the passive positioning server performs a second device classifying process, thereby obtaining a result of the second device classifying process, completing classifying mobile devices based on a result of the second device classifying process, and also completing positioning of the mobile devices.

In other optional implementations, please refer to fig. 6, fig. 6 is a schematic diagram of a device classifying method provided by the embodiment of the present invention, as shown in fig. 6, a feature matrix is first constructed at a server according to feature information and statistical information, where the statistical information may be standard deviation and mean of signal intensity values obtained by framing calculation and standard deviation and mean of inter-frame time intervals in the group, then normalization processing is performed on the data (0.1), device features are obtained by updating the clustering algorithm, and new data are classified according to the device features by adopting euclidean distance, so as to complete classification of mobile devices.

Referring to fig. 7, fig. 7 is a schematic structural diagram of a device classifying apparatus according to an embodiment of the present invention, and as shown in fig. 7, a device classifying apparatus 700 includes:

an acquiring module 701, configured to acquire probe request frame information acquired by an acquisition device, where the probe request frame information is sent by at least one mobile device;

the parsing module 702 is configured to parse the probe request frame information to obtain a parsing result, where the parsing result includes first information and second information;

an updating module 703, configured to update a first set of virtual device sequences according to the first information and the second information to obtain a second set of virtual device sequences, where the first set of virtual device sequences includes at least one virtual device sequence, each virtual device sequence includes at least one media access control MAC group, and the second set of virtual device sequences includes at least one virtual device sequence, each virtual device sequence includes at least one MAC group;

A categorizing module 704, configured to categorize the at least one mobile device according to the second virtual device sequence set.

Optionally, the updating module 703 includes:

Optionally, the updating module 703 further includes:

Optionally, the computing unit includes:

the device classifying device calculates a time difference value group of a target time stamp and a time 5 stamp in at least one target virtual device sequence, and calculates a sequence number difference value group of a target frame sequence number and a frame sequence number in the at least one target virtual device, wherein the target time stamp represents a time stamp matched with the target MAC address, and the target virtual device sequence represents any virtual device sequence in the first virtual device sequence set;

Wherein the target first information represents first information of the target MAC address match, and the 5 target second information represents second information of the target MAC address match.

splicing the target MAC address, the target timestamp, the target signal strength value, the target frame sequence number and the target field to the last position of the matched virtual device sequence; 0, wherein the target timestamp represents a timestamp of the target MAC address match, the target signal strength value represents a signal strength value of the target MAC address match, and the target frame sequence number represents a frame sequence number of the target MAC address match.

Optionally, the device classifying apparatus further includes:

Fig. 8 is a schematic structural diagram of another device classifying apparatus according to an embodiment of the present invention, and as shown in fig. 8, the device classifying apparatus 800 includes:

an obtaining module 801, configured to obtain a second virtual device sequence set and probe request frame information sent by a gateway device, where the probe request frame information is sent by at least one gateway device;

A construction module 802, configured to construct a feature matrix according to the second virtual device sequence set;

a processing module 803, configured to perform clustering processing on the feature matrix to obtain identification features for distinguishing different mobile devices;

a classifying module 804, configured to classify the mobile device according to the identification feature and the probe request frame information.

Optionally, the building block 802 includes:

Optionally, the categorizing module 804 includes:

According to an embodiment of the invention, the invention further provides an electronic device and a readable storage medium.

FIG. 9 illustrates a schematic block diagram of an example electronic device 900 that may be used to implement an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 9, the apparatus 900 includes a computing unit 901 that can perform various appropriate actions and processes according to a computer program stored in a Read-Only Memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access Memory (Random Access Memory, RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other by a bus 904. An Input/Output (I/O) interface 905 is also connected to bus 904.

Various components in device 900 are connected to I/O interface 905, including: an input unit 906 such as a keyboard, a mouse, or the like; an output unit 907 such as various types of displays, speakers, and the like; a storage unit 908 such as a magnetic disk, an optical disk, or the like; and a communication unit 909 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 909 allows the device 900 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunications networks.

The computing unit 901 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 901 include, but are not limited to, a central processing unit (Central processing unit, CPU), a graphics processing unit (Graphics processing unit, GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processors, controllers, microcontrollers, etc. The computing unit 901 performs the respective methods and processes described above, such as the device classifying method.

Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuitry, field programmable gate arrays (Field Programmable Gate Array, FPGAs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), application specific standard products (Application Specific Standard Parts, ASSPs), system On Chip (SOC), complex programmable logic devices (Complex Programmable logic device, CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present invention may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read-Only Memory) or flash Memory), an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: display means for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area networks, wide area networks, and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method of classifying devices, comprising:

the first information comprises a target field, and the second information comprises a MAC address, a signal strength value, a time stamp and a frame sequence number;

the target MAC address is any one MAC address in the probe request frame information, and the first preset condition indicates that an MAC address matched with the target MAC address exists in the first virtual equipment sequence set;

the gateway device classifies the at least one mobile device according to the second virtual device sequence set;

the gateway device updates the first virtual device sequence set according to the first information and the second information to obtain a second virtual device sequence set, and the method further comprises the following steps:

The target MAC address represents any one MAC address in the detection request frame information, and the second preset condition represents that a target field matched with the target field exists in the first virtual equipment sequence set;

and under the condition that the target MAC address does not meet the first preset condition and the target field meets the second preset condition, calculating, by the gateway device, a similarity score associated with the target MAC address according to the target field, including:

2. The device classification method according to claim 1, wherein in case the target field does not satisfy the second preset condition, the gateway device creates a new virtual device sequence and adds target first information and target second information to the new virtual device sequence;

3. The device classification method according to claim 1, wherein the gateway device updates the first set of virtual device sequences according to the following rules:

4. A device categorization method according to any of claims 1 to 3, characterized in that after the gateway device categorizes the at least one mobile device according to the second set of virtual device sequences, the method further comprises:

5. A method of classifying devices, comprising:

the method comprises the steps that a server acquires a second virtual device sequence set and detection request frame information, wherein the second virtual device sequence set and the detection request frame information are sent by gateway equipment, and the detection request frame information is sent by at least one gateway equipment, wherein the second virtual device sequence set is obtained by updating a first virtual device sequence set through the gateway equipment according to the method of claim 1;

the server builds a feature matrix according to the second virtual device sequence set, and the method comprises the following steps:

constructing a feature matrix according to the feature information and the statistical information;

The server classifies the mobile equipment according to the identification characteristics and the detection request frame information;

the server classifies the mobile device according to the identification feature and the detection request frame information, and comprises the following steps:

6. A device classifying apparatus, comprising:

the updating module comprises:

the classifying module is used for classifying the at least one mobile device according to the second virtual device sequence set;

the update module further includes:

the calculation unit includes:

7. The device classification apparatus according to claim 6, wherein in a case where the target field does not satisfy the second preset condition, the device classification apparatus creates an added virtual device sequence, and adds target first information and target second information to the added virtual device sequence;

8. The device classification apparatus of claim 6, wherein the device classification apparatus updates the first set of virtual device sequences according to the following rules:

9. The equipment classification device according to any one of claims 6 to 8, further comprising:

10. A device classifying apparatus, comprising:

the acquisition module is used for acquiring a second virtual device sequence set and detection request frame information sent by gateway equipment, wherein the detection request frame information is sent by at least one gateway equipment, and the second virtual device sequence set is obtained by updating a first virtual device sequence set through the gateway equipment according to the method of claim 1;

the construction module comprises:

the construction unit is used for constructing a feature matrix according to the feature information and the statistical information;

the classifying module is used for classifying the mobile equipment according to the identification characteristics and the detection request frame information;

the classifying module comprises:

11. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the device classification method of any one of claims 1 to 4.

12. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the device classification method of claim 5.

13. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the device classification method according to any one of claims 1 to 4, or for causing the computer to perform the device classification method according to claim 5.