Identification method and device of wireless communication equipment, equipment and storage medium

Abstract

The invention discloses a wireless communication equipment identification method and device, equipment and a storage medium. The method comprises the following steps: acquiring first information and a first classifier corresponding to a first channel condition; the first channel condition represents a channel condition for the wireless communication device to send a wireless signal; the first information can reflect radio frequency fingerprint characteristics of the wireless communication equipment; and identifying the first information by using the first classifier to obtain a first identification result of the wireless communication equipment.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a method, apparatus, device, and storage medium for identifying a wireless communication device. Background Art

[0002] Radio frequency fingerprint technology is a technology for identifying wireless devices, which identifies wireless devices by extracting unique structures in the electromagnetic waves emitted by transmitters. In the process of radio frequency fingerprint identification, it is necessary to extract unique features from different parts of the signal, construct a device fingerprint library, and use the data samples in this fingerprint library for training to obtain a classifier, and finally realize the radio frequency fingerprint authentication of the device through an inference process. In the existing security authentication schemes for radio frequency fingerprint technology, when selecting features, usually only the discrimination of the features themselves in the training set is concerned, while ignoring the influence of channel conditions on signal features, resulting in low device identification accuracy. Summary of the Invention

[0003] Embodiments of the present application provide a method, apparatus, device, and storage medium for identifying a wireless communication device, which solve the problem in the related art that the device identification accuracy is not high due to ignoring the influence of channel conditions on signal features.

[0004] To achieve the above object, the technical solution of the present application is realized as follows:

[0005] A method for identifying a wireless communication device, the method includes:

[0006] Obtain first information and a first classifier corresponding to a first channel condition; the first channel condition characterizes the channel condition for a wireless communication device to send a wireless signal; the first information can reflect the radio frequency fingerprint characteristics of the wireless communication device;

[0007] Use the first classifier to identify the first information to obtain a first identification result of the wireless communication device.

[0008] An identification apparatus for a wireless communication device, the identification apparatus includes:

[0009] An acquisition unit, configured to obtain first information and a first classifier corresponding to a first channel condition; the first channel condition characterizes the channel condition for a wireless communication device to send a wireless signal; the first information can reflect the radio frequency fingerprint characteristics of the wireless communication device;

[0010] A processing unit, configured to use the first classifier to identify the first information to obtain a first identification result of the wireless communication device.

[0011] An electronic device, characterized in that the electronic device includes:

[0012] A memory for storing executable instructions;

[0013] A processor, when executing the executable instructions stored in the memory, implements the steps in the identification method of the wireless communication device as described in any one of the above.

[0014] A storage medium stores computer-executable instructions, and the computer-executable instructions are configured to execute the identification method of the wireless communication device provided in any one of the above.

[0015] The identification method, device, equipment, and storage medium of the wireless communication device provided by the embodiments of the present application obtain first information and a first classifier corresponding to a first channel condition; the first channel condition characterizes the channel condition for the wireless communication device to send a wireless signal; the first information can reflect the radio frequency fingerprint characteristics of the wireless communication device; use the first classifier to identify the first information to obtain a first identification result of the wireless communication device. That is to say, in the embodiments of the present application, by obtaining the first information and the first classifier corresponding to the first channel condition, and using the first classifier to process the first information, the identification result of the wireless communication device is obtained, which solves the problem in the related art that the device identification accuracy is not high due to ignoring the influence of the channel condition on the signal characteristics, realizes the purpose of device identification under different channel conditions, and improves the identification accuracy under different channel conditions. Description of the Drawings

[0016] Figure 1 It is a schematic flowchart of an identification method of a wireless communication device provided by an embodiment of the present application;

[0017] Figure 2 It is a schematic flowchart of constructing a lookup table provided by an embodiment of the present application;

[0018] Figure 3 It is a schematic flowchart of another identification method of a wireless communication device provided by an embodiment of the present application;

[0019] Figure 4 It is a schematic structural diagram of an identification device of a wireless communication device provided by an embodiment of the present application;

[0020] Figure 5 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application. Detailed Embodiments

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be further elaborated in detail below in conjunction with the accompanying drawings and embodiments. The described embodiments should not be construed as limiting this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0022] In the following description, reference is made to "some embodiments", which describe subsets of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and they can be combined with each other without conflict.

[0023] The terms "first / second / third" involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence under allowable circumstances, so that the embodiments of this application described here can be implemented in an order other than that illustrated or described here.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0025] The following further elaborates on this application in detail in conjunction with the accompanying drawings and specific embodiments.

[0026] An embodiment of this application provides a method for identifying a wireless communication device. Referring to Figure 1 as shown, the method includes the following steps:

[0027] Step S101: Obtain first information and a first classifier corresponding to a first channel condition.

[0028] Among them, the first channel condition characterizes the channel condition for the wireless communication device to transmit a wireless signal; the first information can reflect the radio frequency fingerprint characteristics of the wireless communication device.

[0029] It can be understood that the indicators of the channel condition can include but are not limited to signal-to-noise ratio, channel gain, phase, delay, line-of-sight signal transmission (LOS), and non-line-of-sight signal transmission (NLOS) scenarios; the first channel condition can include one or more of the foregoing channel condition indicators, and this application does not make specific limitations thereto. The transmitting end of the wireless communication device transmits a wireless signal to a receiving device under the first channel condition, and the receiving device can be a receiver.

[0030] After receiving a wireless signal, the receiver can process the signal to complete channel condition estimation and radio frequency fingerprint feature extraction. The wireless signals in the embodiments of the present application can be transient signals or steady-state signals. The radio frequency fingerprint features include, but are not limited to, carrier frequency offset, amplitude and phase error, deviation of the origin point in the in-phase / quadrature (I / Q) complex plane, and correlation results of synchronous domain signals. The first information can include one or more of the foregoing features.

[0031] Step S102: Use the first classifier to identify the first information to obtain the first identification result of the wireless communication device.

[0032] It can be understood that based on the radio frequency fingerprint-based security authentication scheme, after radio frequency fingerprint feature extraction and channel condition estimation are performed on multiple transmitters, a device fingerprint database can be constructed, and the classifier can be trained with the data samples in the fingerprint database. Exemplarily, wireless signals sent by multiple wireless communication devices under corresponding channel conditions can be collected, the wireless signals can be processed to complete channel condition estimation and feature extraction, different features can be selected according to different channel conditions and sent to the classifier for training, and a lookup table of radio frequency fingerprint features and classifiers under different channel conditions can be established. The first information can be understood as the radio frequency fingerprint features extracted from the wireless signal of the transmitter.

[0033] After receiving the wireless signal, the receiver processes the signal to complete channel condition estimation and radio frequency fingerprint feature extraction. Under the known first channel condition, radio frequency fingerprint feature selection and classifier selection are performed according to the lookup table, and the radio frequency fingerprint features are input into the corresponding classifier for identification to complete the identification of the wireless communication device.

[0034] As can be seen from the above, in the embodiments of the present application, by obtaining the first information and the first classifier corresponding to the first channel condition, and using the first classifier to process the first information, the identification result of the wireless communication device is obtained. Considering that in the actual communication environment, due to the different access positions and times of the devices, the channel conditions change, which affects the radio frequency fingerprint features. It solves the problem in the related art that due to ignoring the influence of channel conditions on signal features, the device identification accuracy is not high, realizes the purpose of device identification under different channel conditions, and improves the identification accuracy under different channel conditions.

[0035] In some embodiments of the present application, step S101 of obtaining the first information and the first classifier corresponding to the first channel condition can be implemented in the following manner:

[0036] Obtain a lookup table of radio frequency fingerprint features and classifiers under different channel conditions;

[0037] Based on the lookup table, determine the first information and the first classifier corresponding to the first channel condition.

[0038] Among them, the first information includes at least one of the following:

[0039] Carrier frequency offset;

[0040] Amplitude and phase error;

[0041] Deviation of the in-phase component / quadrature component complex plane origin;

[0042] Synchronization domain signal correlation result.

[0043] It can be understood that the first information can be understood as the radio frequency fingerprint features extracted from the wireless signals at the transmitting end, and can include but are not limited to carrier frequency offset, amplitude and phase error, deviation of the in-phase component / quadrature component complex plane origin, and synchronization domain signal correlation result; different radio frequency fingerprint features have different sensitivities to the channel.

[0044] The features extracted in radio frequency fingerprint recognition include but are not limited to carrier frequency offset, I / Q offset, and constellation trajectory graph offset. After feature extraction is completed, different features can be selected according to different channel conditions and sent to the classifier to establish a look-up table of radio frequency fingerprint features and classifiers under different channel conditions.

[0045] In practical applications, the wireless signals sent by multiple wireless communication devices under corresponding channel conditions can be preprocessed. The preprocessing can specifically include four steps: filtering, power normalization, timing synchronization, and target signal interception; estimating the channel conditions and extracting features based on the preprocessed signals; the indicators of the channel conditions can include but are not limited to signal-to-noise ratio, channel gain, phase, delay, LOS and NLOS scenarios; the extracted features include but are not limited to carrier frequency offset, I / Q offset, and constellation trajectory graph offset; after feature extraction is completed, different features are selected according to different channel conditions and sent to the classifier to establish a look-up table of radio frequency fingerprint features and classifiers under different channel conditions.

[0046] According to the look-up table, select the corresponding radio frequency fingerprint features and classifiers under the known first channel condition, and identify the radio frequency fingerprint features through the classifier to obtain the device identification result.

[0047] In some embodiments of the present application, obtaining the look-up table of radio frequency fingerprint features and classifiers under different channel conditions includes:

[0048] Obtaining the wireless signals sent by multiple wireless communication devices under corresponding channel conditions;

[0049] Processing the wireless signals to determine each radio frequency fingerprint feature corresponding to each channel condition;

[0050] Based on each RF fingerprint feature corresponding to each channel condition, a lookup table of RF fingerprint features and classifiers under different channel conditions is constructed.

[0051] It can be understood that wireless signals sent by multiple wireless communication devices under corresponding channel conditions can be preprocessed, the channel condition estimation and feature extraction are completed according to the preprocessed signals, and different features are selected for different channel conditions and sent to the classifier for training.

[0052] In practical applications, if all features are directly used to train the classifier, it will inevitably reduce the accuracy and increase the time cost. The feature screening can be completed through the Feature weighting algorithms, RELIEF algorithm, and the calculation process is as follows:

[0053] Given the training set {(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x 1 ,y 1 ), find the nearest neighbor x i guessed correctly and the nearest neighbor x i,nh guessed wrongly for each instance x i,nm ,x i,nh is the sample of the same category closest to x i , x i,nm is the sample of a different category closest to x i . Then the component of the relevant statistic corresponding to attribute j can be obtained through Formula 1:

[0054]

[0055] where i is the sample subscript, represents the value of sample x i on data j,

[0056] In the embodiments of the present application, the recognition accuracy rate of each individual feature under different channel conditions is tested, and the test results are sorted into a table and saved; since there are many indicators of channel conditions, the embodiments of the present application take the signal-to-noise ratio and whether it is a LOS scenario as examples of channel conditions.

[0057] Table 1 shows the recognition accuracy rates based on carrier frequency offset, I / Q offset, and constellation offset at different signal-to-noise ratios. The test can use a Universal Software Radio Peripheral (USRP) to implement signal transmission and reception, and use Matlab to add Gaussian white noise of different magnitudes to achieve the effect of changing the signal-to-noise ratio (SNR). Table 1 shows that the carrier frequency offset is the most powerful among all features. Even at very low SNR, the correct recognition rate can reach 97%, while the channel propagation has a greater impact on I / Q offset and constellation offset.

[0058] SNR (dB) Carrier frequency offset (%) I / Q offset (%) Constellation diagram offset (%) 25 99.78 98.89 99.89 20 98.67 96.33 98.89 15 98.44 89.44 91.89 10 97.44 89.44 85.44

[0059] Table 1 Recognition accuracy rates of different signal features at different signal-to-noise ratios

[0060] Table 2 shows the recognition accuracy rates based on carrier frequency offset, in-phase / quadrature offset, and constellation offset at different signal-to-noise ratios in LOS and NLOS scenarios; it can be seen from Table 2 that the carrier frequency offset is the most powerful among all features.

[0061] Test scenario Carrier frequency offset (%) I / Q offset (%) Constellation diagram offset (%) LOS (short range) 98.67 97.33 96.89 LOS (long range) 97.33 93.56 91.44 NLOS 96.89 87.56 84.67

[0062] Table 2 Recognition accuracy rates of different signal features in LOS and NLOS scenarios

[0063] Based on obtaining the relevant statistic R of different features in the training set, the R value can be further corrected using the data in the recognition accuracy rate table. The correction methods include but are not limited to multiplying by the probability of the corresponding feature to obtain the updated weights of different features. For example: when the channel SNR is between 17.5 - 22.5 dB, the weight of the I / Q offset feature at this time is the relevant statistic R obtained by the Relief algorithm multiplied by 96.33%. Finally, perform normalization and sorting operations on the updated weight vector, and use the top K features as the features for classifier training under the current training set and current channel conditions. After selecting the features required for classifier training, the classifier can be trained. The types of classifiers include but are not limited to decision trees and support vector machines; establish a lookup table with the trained classifier, channel conditions, and selected features.

[0064] As can be seen from the above, the identification method of the wireless communication device provided by the embodiment of the present application, on the basis of integrated feature selection, takes into account the influence of the change of the channel condition on the radio frequency fingerprint feature due to the different access positions and times of the device in the actual communication environment, selects different features for training by the classifier for different channel conditions, and constructs a look-up table of the radio frequency fingerprint feature and the classifier under different channel conditions, improving the robustness and identification accuracy of device identification under different channel conditions.

[0065] In an implementable scenario, referring to Figure 2 as shown, the process of constructing the look-up table of the radio frequency fingerprint feature and the classifier under different channel conditions can be implemented through the following steps:

[0066] Step S201: Collect the transmission signals of different devices.

[0067] Step S202: Complete channel estimation and preprocess according to the transmission signal.

[0068] Step S203: Signal feature extraction.

[0069] Step S204: Combine the single-feature recognition accuracy rate tables under different channel conditions, and perform feature selection under the given channel conditions.

[0070] Step S205: Select different features for different channel conditions and send them into the classifier for training.

[0071] Step S206: Establish a look-up table of the radio frequency fingerprint feature and the classifier under different channel conditions.

[0072] As can be seen from the above, the embodiment of the present application selects different features for training by the classifier for different channel conditions, and constructs a look-up table of the radio frequency fingerprint feature and the classifier under different channel conditions. The corresponding radio frequency fingerprint feature and classifier can be selected through the look-up table according to the known channel condition to complete the identification of the device; the robustness and identification accuracy of device identification under different channel conditions are improved.

[0073] In some embodiments of the present application, after step S102 uses the first classifier to identify the first information and obtains the first identification result of the wireless communication device, the method further includes:

[0074] Obtain the first access condition; the first access condition can reflect the external conditions when the wireless communication device accesses the network;

[0075] Modify the first identification result based on the first access condition and output the second identification result. Among them, the external conditions include at least one of the following:

[0076] The device access time;

[0077] Device working status.

[0078] It can be understood that in a dedicated network, due to different user usage habits and task scheduling times, the probabilities of different devices in the whitelist accessing the network may be different under different conditions. For example, during different time periods, the probabilities of different devices accessing the private network are different. Based on the established lookup table, a preliminary identification result of the device is obtained according to the classifier, and then combined with the historical access data of the device to estimate the prior probability of the device accessing under a certain external condition, and the preliminary identification result is corrected, that is, post-processing is performed on the identification result of the classifier; the identification accuracy of the device can be improved.

[0079] The external conditions when a wireless communication device accesses the network may include but are not limited to the device access time and the device working status. Among them, the device working status may include the status of the device being used. For example, when a staff member is on duty, a certain type of device is carried and used; the device access time can be understood as the time when the sending signal of the device is received.

[0080] In the embodiments of the present application, historical access data of multiple devices can be collected according to external conditions, and the prior probabilities of different devices accessing under a certain access condition can be estimated based on the historical access data; in the case of a known first access condition, the probabilities of different devices accessing are estimated according to the prior probabilities to adjust the first identification result and output a second identification result.

[0081] In some embodiments of the present application, correcting the first identification result based on the first access condition and outputting a second identification result includes:

[0082] Obtaining the prior probabilities of each wireless communication device among multiple wireless communication devices accessing the network under different external conditions;

[0083] Estimating the wireless communication device corresponding to the first access condition based on the prior probabilities to obtain an estimation result;

[0084] Adjusting the confidence level of the first identification result based on the estimation result and outputting a second identification result.

[0085] In the embodiments of the present application, historical access data of different devices accessing the network under different external conditions can be collected. When the network receives a new sending signal, the prior probabilities of different devices accessing under the current external conditions can be estimated according to the historical access data of the devices.

[0086] On the premise of a known first access condition, the wireless communication device accessing can be estimated according to the historical access data to adjust the confidence level of the first identification result and output a second identification result. The first identification result can be understood as a preliminary identification result.

[0087] Suppose there are m types of devices and N received signals whose categories need to be predicted. For the i-th received signal, the probability distribution of its preliminary recognition result is set as P pre,i =(P’ i,1 ,P’ i,2 ,…,P’ i,m ). At this time, there should be N probability distributions P pre,1 ,P pre,2 ,…,P pre,N for all prediction results. The confidence of the preliminary recognition results can be adjusted to select the top n results with higher confidence. Exemplarily, the confidence of the recognition results can be judged according to the following two schemes. The first is to select the recognition results of received signals with better channel conditions; for example: received signals with a higher signal-to-noise ratio. The second scheme is for the recognition of the i-th received signal, to judge whether there is P’ pre,i in P i,k (k∈{1,2,…,m}) greater than a certain threshold τ.

[0088] The adjustment of the confidence of the first recognition result can be combined with the processing algorithm, and the specific steps are as follows:

[0089] The first step: Preparation stage.

[0090] If the top n prediction results with higher confidence are P pre,1 ,P pre,2 ,…,P pre,n , they can be used as a standard reference system to correct the low-confidence part. The above result vectors are combined into an n×m probability matrix A 0 :

[0091]

[0092] Let the k-th prediction result P pre,k (k>n = 1) to be corrected be b 0 ∈R 1×m , and let:

[0093]

[0094] The second step: Iteration stage.

[0095] First, define the diagonalization operation D(v): convert the column vector v∈R n into an n×n diagonal matrix, and the diagonal elements are the original vector elements. If the current is the d-th iteration, first perform column normalization:

[0096]

[0097] where e∈R n+1 is a column vector of all 1s.

[0098] S d = L d-1 γ s -1

[0099] Then perform row normalization:

[0100]

[0101] Among them, P i is the prior probability obtained according to historical access data.

[0102]

[0103] L d = γ L -1 S d Q

[0104] Step 3: Output the result.

[0105] After multiple iterations of the second step, the last row of L d can be taken as the corrected k-th prediction result. Through the above operations, a prior probability distribution more in line with that obtained from historical data can be obtained, thereby effectively improving the recognition accuracy rate.

[0106] As can be seen from the above, after obtaining the preliminary recognition result through the classifier in the embodiment of the present application, the prior probability of access of different devices under different external conditions is judged in combination with historical access data, and the recognition result of the classifier is post-processed, further improving the recognition accuracy rate of the device and enhancing the classification performance of multiple devices.

[0107] In some embodiments of the present application, obtaining the prior probability of each wireless communication device among multiple wireless communication devices accessing the network under different external conditions includes:

[0108] Obtaining the access times of each wireless communication device within the first time period and the total access times of multiple wireless communication devices within the first time period;

[0109] Based on the access times and the total access times, determining the prior probability corresponding to each wireless communication device.

[0110] In the embodiment of the present application, assuming there are m types of devices, the prior probability is denoted as (P 1 , P 2 , …, P m)。Taking time as an example, the following illustrates how to determine the prior probability: Taking the current time period from 9:00 to 10:00 in the morning as an example, the solution can query the access situations of different devices from 9:00 to 10:00 every day in the historical time period. After obtaining the access times of each type of device in the historical time period, the prior probability can be calculated by the following formula:

[0111]

[0112] P i1 is the prior probability of the access of the i-th type of device.

[0113] In some embodiments of the present application, obtaining the prior probability of each wireless communication device among multiple wireless communication devices accessing the network under different external conditions includes:

[0114] Obtaining the usage times of each wireless communication device used within the first time period and the total usage times of multiple wireless communication devices used within the first time period;

[0115] Based on the usage times and the total usage times, determining the prior probability corresponding to each wireless communication device.

[0116] In the embodiments of the present application, assuming there are m types of devices, the prior probability is denoted as (P 1 , P 2 , …, P m ). Taking the personnel attendance situation as an example, the following illustrates how to determine the prior probability:

[0117] Assuming there are a total of n employees carrying these m types of devices, we can obtain the probability that an employee i uses the k-th type of device through historical data

[0118]

[0119] Then the prior probability of access for each device can be expressed as:

[0120]

[0121] When employee k is present today, n(k) = 1; otherwise n(k) = 0.

[0122] In practical applications, the access time and the personnel attendance situation can be comprehensively considered to count the probability that an employee i uses the k-th type of device within a time period After obtaining , P i2 can be calculated according to formula 2. In some embodiments of the present application, the prior probability of the access of the i-th type of device can also be obtained by comprehensively considering P i1 and P i2 , for example, P i1 and P i2The sum is the prior probability of the access of the i-th type of device.

[0123] In practical applications, for the radio frequency fingerprint security authentication based on the 5th Generation Mobile Communication Technology (5G) secure private network, signal feature extraction can be performed based on the 5G radio frequency front-end circuit or the quadrature I / Q data after digital down-conversion, a fingerprint library of terminal devices can be constructed, and the data sample group of the fingerprint library can be used for training to achieve the radio frequency fingerprint identity authentication of 5G Internet of Things devices. At the same time, the main authentication and authorization identity International Mobile Subscriber Identity (IMSI) of the 5G core network can be integrated based on security authentication to meet the requirements of sensitive users for the non-tamperability and uniqueness of access authentication, create a security authentication system, and enhance network security.

[0124] In an achievable scenario, referring to Figure 3 as shown, the identification method of the wireless communication device can also be implemented through the following steps:

[0125] Step S301: Collect the transmission signal of the device.

[0126] Step S302: Complete channel estimation and perform preprocessing according to the transmission signal.

[0127] Step S303: Signal feature extraction.

[0128] Step S304: Perform feature selection and classifier selection under the given channel conditions.

[0129] Step S305: Device identification and classification.

[0130] Step S306: Query historical access data.

[0131] Step S307: Perform post-processing after classification and output the classification result.

[0132] As can be seen from the above, the embodiment of the present application selects different features according to different channel conditions and sends them to the classifier for training to construct a lookup table of radio frequency fingerprint features and classifiers under different channel conditions. According to the known channel conditions, the corresponding radio frequency fingerprint features and classifiers are selected through the lookup table to complete the identification of the device; the robustness and identification accuracy of the device identification under different channel conditions are improved; secondly, after obtaining the preliminary identification result through the classifier, the prior probability of access of different devices under different external conditions is judged by combining historical access data, and the identification result of the classifier is post-processed, further improving the identification accuracy of the device and enhancing the classification performance of multiple devices.

[0133] Based on the same inventive concept as described above, Figure 4 FIG. Figure 4 is a schematic structural diagram of an identification device for a wireless communication device provided by an embodiment of the present invention. The identification device 400 includes:

[0134] An acquisition unit 401, configured to acquire first information and a first classifier corresponding to a first channel condition; the first channel condition characterizes the channel condition for the wireless communication device to send a wireless signal; the first information can reflect the radio frequency fingerprint characteristics of the wireless communication device;

[0135] A processing unit 402, configured to identify the first information by using the first classifier to obtain a first identification result of the wireless communication device.

[0136] In some embodiments of the present application, the acquisition unit 401 is further configured to acquire a look-up table of radio frequency fingerprint characteristics and classifiers under different channel conditions; the processing unit 402 is further configured to determine the first information and the first classifier corresponding to the first channel condition based on the look-up table;

[0137] Wherein, the first information includes at least one of the following:

[0138] Carrier frequency offset;

[0139] Amplitude and phase error;

[0140] In-phase component / quadrature component complex plane origin deviation;

[0141] Synchronization domain signal correlation result.

[0142] In some embodiments of the present application, the acquisition unit 401 is further configured to acquire wireless signals sent by multiple wireless communication devices under corresponding channel conditions; the processing unit 402 is further configured to process the wireless signals to determine each radio frequency fingerprint characteristic corresponding to each channel condition; based on each radio frequency fingerprint characteristic corresponding to each channel condition, construct a look-up table of radio frequency fingerprint characteristics and classifiers under different channel conditions.

[0143] In some embodiments of the present application, the acquisition unit 401 is further configured to acquire a first access condition; the first access condition can reflect the external conditions when the wireless communication device accesses the network; the processing unit 402 is further configured to correct the first identification result based on the first access condition and output a second identification result;

[0144] Wherein, the external conditions include at least one of the following:

[0145] Device access time;

[0146] Device working state.

[0147] In some embodiments of the present application, the obtaining unit 401 is further configured to obtain the prior probability of each wireless communication device among a plurality of wireless communication devices accessing the network under different external conditions; the processing unit 402 is further configured to estimate the wireless communication device corresponding to the first access condition based on the prior probability to obtain an estimation result;

[0148] Adjust the confidence level of the first recognition result based on the estimation result, and output a second recognition result.

[0149] In some embodiments of the present application, the obtaining unit 401 is further configured to obtain the access times of each wireless communication device within a first time period and the total access times of the plurality of wireless communication devices within the first time period; determine the prior probability corresponding to each wireless communication device based on the access times and the total access times.

[0150] In some embodiments of the present application, the obtaining unit 401 is further configured to obtain the usage times of each wireless communication device used within a first time period and the total usage times of the plurality of wireless communication devices used within the first time period; determine the prior probability corresponding to each wireless communication device based on the usage times and the total usage times.

[0151] Based on the foregoing embodiments, an embodiment of the present application provides an electronic device, Figure 5 FIG. is a schematic hardware structure diagram of the electronic device according to the embodiment of the present invention. The electronic device 500 includes: at least one processor 501, a memory 502. Optionally, the electronic device 500 may further include at least one communication interface 503. Each component in the electronic device 500 is coupled together through a bus system 504. It can be understood that the bus system 504 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 504 further includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in Figure 5 all kinds of buses are labeled as the bus system 504.

[0152] It can be understood that the memory 502 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), sync link dynamic random access memory (SLDRAM), direct rambus random access memory (DRRAM).The memory 502 described in the embodiments of the present invention is intended to include but not limited to these and any other suitable types of memories.

[0153] The memory 502 in the embodiments of the present invention is used to store various types of data to support the operation of the electronic device 500. Examples of such data include: any computer programs for operating on the electronic device 500, and the programs implementing the methods of the embodiments of the present invention may be included in the memory 502.

[0154] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by the processor 501. The processor may be an integrated circuit chip with the ability to process signals. In the implementation process, the steps of the above methods can be completed by the integrated logic circuit in the hardware of the processor or instructions in the form of software. The above processor may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor, etc. Combining the steps of the methods disclosed in the embodiments of the present invention, it can be directly embodied as being executed by the hardware decoding processor, or executed by the combination of the hardware and software modules in the decoding processor. The software module may be located in the storage medium, which is located in the memory. The processor reads the information in the memory and combines its hardware to complete the steps of the foregoing methods.

[0155] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontroller units (MCUs), microprocessors, or other electronic components, and is used to execute the above methods.

[0156] Based on the foregoing embodiments, an embodiment of the present application provides a storage medium, in which computer-executable instructions are stored, and the computer-executable instructions are configured to execute Figure 1 the identification method of the wireless communication device provided by the corresponding embodiment.

[0157] It should be noted that the above computer storage medium may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM), etc.; it may also be various electronic devices including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, etc.

[0158] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including that element.

[0159] The serial numbers of the above embodiments of the present application are only for description and do not represent the superiority or inferiority of the embodiments.

[0160] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0161] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0162] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0163] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0164] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for identifying a wireless communication device, characterized in that, the method includes: obtaining first information and a first classifier corresponding to a first channel condition; the first channel condition characterizes the channel condition for the wireless communication device to send a wireless signal; the first information can reflect the radio frequency fingerprint characteristics of the wireless communication device; using the first classifier to identify the first information to obtain a first identification result of the wireless communication device.

2. The method according to claim 1, characterized in that, the obtaining of the first information and the first classifier corresponding to the first channel condition includes: obtaining a look-up table of radio frequency fingerprint characteristics and classifiers under different channel conditions; based on the look-up table, determining the first information and the first classifier corresponding to the first channel condition; wherein, the first information includes at least one of the following: carrier frequency offset; amplitude and phase error; in-phase component / quadrature component complex plane far point deviation; synchronization domain signal correlation result.

3. The method according to claim 2, characterized in that, the obtaining of the look-up table of radio frequency fingerprint characteristics and classifiers under different channel conditions includes: obtaining wireless signals sent by multiple wireless communication devices under corresponding channel conditions; processing the wireless signals to determine each radio frequency fingerprint characteristic corresponding to each channel condition; based on each radio frequency fingerprint characteristic corresponding to each channel condition, constructing a look-up table of radio frequency fingerprint characteristics and classifiers under different channel conditions.

4. The method according to claim 1, characterized in that, after using the first classifier to identify the first information to obtain the first identification result of the wireless communication device, the method further includes: obtaining a first access condition; the first access condition can reflect the external conditions when the wireless communication device accesses the network; correcting the first identification result based on the first access condition and outputting a second identification result; wherein, the external conditions include at least one of the following: device access time; device working state.

5. The method according to claim 4, characterized in that, the correcting the first identification result based on the first access condition and outputting a second identification result includes: obtaining the prior probability of each wireless communication device among multiple wireless communication devices accessing the network under different external conditions; estimating the wireless communication device corresponding to the first access condition based on the prior probability to obtain an estimation result; adjusting the confidence level of the first identification result based on the estimation result and outputting a second identification result.

6. The method according to claim 5, characterized in that, the obtaining of the prior probability of each wireless communication device among multiple wireless communication devices accessing the network under different external conditions includes: obtaining the access times of each wireless communication device within a first time period and the total access times of the multiple wireless communication devices within the first time period; based on the access times and the total access times, determining the prior probability corresponding to each wireless communication device.

7. The method according to claim 5, characterized in that, Obtaining the prior probability of each of multiple wireless communication devices accessing the network under different external conditions includes: Obtaining the number of times each of the wireless communication devices is used within a first time period and the total number of times the multiple wireless communication devices are used within the first time period; Based on the number of times of use and the total number of times of use, determining the prior probability corresponding to each of the wireless communication devices.

8. An identification device for a wireless communication device, characterized in that, the identification device includes: an obtaining unit, configured to obtain first information and a first classifier corresponding to a first channel condition; the first channel condition characterizes the channel condition for the wireless communication device to send a wireless signal; the first information can reflect the radio frequency fingerprint characteristics of the wireless communication device; a processing unit, configured to use the first classifier to identify the first information to obtain a first identification result of the wireless communication device.

9. An electronic device, characterized in that, the electronic device includes: a memory, configured to store executable instructions; a processor, configured to implement the steps of the identification method of the wireless communication device according to any one of claims 1 to 7 when executing the executable instructions stored in the memory.

10. A storage medium, in which computer-executable instructions are stored, and the computer-executable instructions are configured to execute the identification method of the wireless communication device provided in any one of claims 1 to 7 above.

Images