Access direction determination method and device, electronic equipment and storage medium

By constructing a direction perception model based on antenna pairs and using channel state information to determine the entry and exit direction, the problem of low accuracy in the prior art determination of entry and exit direction is solved, and higher accuracy and robustness are achieved.

CN119004161APending Publication Date: 2024-11-22CHINA MOBILE COMM LTD RES INST +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310564620.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-18
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The prior art output results are relatively accurate when determining the entry and exit direction and are susceptible to environmental changes and abnormal data.

Method used

By obtaining channel state information for the entry and exit periods, a direction perception model based on antenna pairs is constructed, and amplitude and phase data are used to perform physical model analysis, determine the entry and exit direction of the target object, and avoid the influence of the degree of realization of the training set and the classifier accuracy.

Benefits of technology

Improve the accuracy and reliability of entry and exit directions, enhance robustness, and reduce sensitivity to environmental changes and abnormal data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119004161A_ABST
    Figure CN119004161A_ABST
Patent Text Reader

Abstract

The invention provides an access direction determination method and device, electronic equipment and a storage medium, and relates to the technical field of communication, the method comprises the following steps: obtaining first channel state information corresponding to an access time period, the access time period being a time period when a target object enters and exits a sensing area corresponding to a transmit-receive antenna array; according to at least one group of target parameters of at least one antenna pair in the first channel state information, constructing at least one group of direction sensing models which are physical models; and determining an access direction based on at least one group of direction sensing models. Wherein the direction sensing model is used for representing the change condition of the signal transmission path of the receiving and transmitting link corresponding to the target object access antenna pair, and the access direction of the target object in the sensing area can be determined by analyzing the change condition. Therefore, the influence of the training set simulation degree and the classifier precision can be avoided, and the determined access direction of the target object is more accurate and reliable.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a method, device, electronic device and storage medium for determining an entry and exit direction. Background Art

[0002] In recent years, the integrated technology of communication and perception has been widely studied. Among them, Wi-Fi-based entry and exit direction detection can continuously monitor the environment without infringing privacy, which can significantly save security expenses and effectively protect the life and health of users. It has shown great application value in special scenarios such as homes, shopping malls, and factories.

[0003] At present, in order to perceive specific objects in the environment, related technologies usually adopt machine learning classification solutions. The accuracy of the output results obtained by this solution is greatly affected by the accuracy of the training data and the degree of fit between the classifier and the actual application scenario. In addition, it is easily affected by environmental changes and abnormal data in application, which makes the accuracy of the entry and exit directions determined based on related technologies low. Summary of the invention

[0004] The purpose of the embodiments of the present disclosure is to provide a method, device, electronic device and storage medium for determining an entry and exit direction, so as to solve the technical problem of low accuracy of output results when determining the entry and exit directions in the related art.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for determining an entry and exit direction, including:

[0006] Acquire first channel state information corresponding to an entry and exit period, wherein the entry and exit period is a period during which the target object enters and exits a sensing area corresponding to the transceiver antenna array;

[0007] Constructing at least one set of direction perception models according to at least one set of target parameters of at least one antenna pair in the first channel state information, wherein the antenna pair includes two antennas in the transceiver antenna array whose connection direction is parallel to the entry and exit direction of the target object, the target parameter includes at least one of amplitude data and phase data, the at least one antenna pair corresponds to the at least one set of target parameters in one-to-one correspondence, the at least one antenna pair corresponds to the at least one set of direction perception models in one-to-one correspondence, and the direction perception model is a physical model;

[0008] The entry and exit directions of the target object are determined based on the at least one set of direction perception models.

[0009] In one embodiment, the acquiring the first channel state information corresponding to the entry and exit time period includes:

[0010] Acquire second channel state information generated by the sensing area in the whole time period;

[0011] Performing delay estimation on the second channel state information to obtain a shortest delay sequence for indicating a minimum signal transmission delay of the transceiver antenna array at each moment;

[0012] The entry and exit time period and the first channel state information generated by the entry and exit time period are determined according to the shortest delay sequence and a preset delay threshold, wherein the signal transmission delay corresponding to any moment in the entry and exit time period is greater than or equal to the delay threshold.

[0013] In one embodiment, determining the entry and exit direction of the target object based on the at least one set of direction perception models includes:

[0014] Normalizing at least one set of target parameters of the first channel state information of the at least one antenna pair to obtain at least one set of normalized parameters;

[0015] Obtaining a weight coefficient for each antenna pair in the at least one antenna pair according to the at least one set of normalized parameters;

[0016] The entry and exit direction of the target object is obtained according to the weight coefficient of each antenna pair in the at least one antenna pair and the at least one set of direction perception models.

[0017] In one embodiment, obtaining a weight coefficient of each antenna pair in the at least one antenna pair according to the at least one set of normalized parameters includes:

[0018] Calculating the difference degree of each group of normalized parameters in the at least one group of normalized parameters to obtain the difference parameter of each group of normalized parameters in the at least one group of normalized parameters;

[0019] A weight coefficient of each antenna pair in the at least one antenna pair is determined based on a difference parameter of each group of normalized parameters in the at least one group of normalized parameters, wherein the difference parameter and the weight coefficient are negatively correlated.

[0020] In one embodiment, the normalizing at least one set of target parameters of the first channel state information of the at least one antenna pair to obtain at least one set of normalized parameters includes:

[0021] Obtaining a first target parameter, a second target parameter, a minimum target parameter, and a maximum target parameter, wherein the first target parameter is a target parameter of one of the antennas in the target antenna pair, the second target parameter is a target parameter of the other antenna in the target antenna pair, the minimum target parameter is a target parameter with the smallest value in a set of target parameters associated with the target antenna pair, the maximum target parameter is a target parameter with the largest value in a set of target parameters associated with the target antenna pair, and the target antenna pair is any antenna pair in the at least one antenna pair;

[0022] A first normalized parameter and a second normalized parameter are calculated according to the first target parameter, the second target parameter, the minimum target parameter and the maximum target parameter, wherein the first normalized parameter is a ratio of a first parameter difference to a target parameter difference, the first parameter difference is a difference between the first target parameter and the minimum target parameter, the target parameter difference is a difference between the maximum target parameter and the minimum target parameter, the second normalized parameter is a ratio of a second parameter difference to the target parameter difference, and the second parameter difference is a difference between the second target parameter and the minimum target parameter;

[0023] A set of normalized parameters associated with the target antenna pair is generated according to the first normalized parameter and the second normalized parameter.

[0024] In one embodiment, determining the entry and exit time period and the first channel state information generated by the entry and exit time period according to the shortest delay sequence and a preset delay threshold includes:

[0025] Obtaining sliding variance data according to the shortest time delay sequence;

[0026] The entry and exit time period and the first channel state information generated by the entry and exit time period are determined according to the sliding variance data and the delay threshold.

[0027] In one embodiment, obtaining sliding variance data according to the shortest delay sequence includes:

[0028] Perform high-frequency filtering on the shortest time delay sequence to obtain a filtered time delay sequence;

[0029] The sliding variance data is obtained according to the filtered time delay sequence.

[0030] In a second aspect, an embodiment of the present disclosure further provides a device for determining an entry and exit direction, the device comprising:

[0031] An acquisition module, used to acquire first channel state information corresponding to an entry and exit period, wherein the entry and exit period is a period when a target object enters and exits a sensing area corresponding to a transceiver antenna array;

[0032] a model building module, configured to build at least one set of direction perception models according to at least one set of target parameters of at least one antenna pair in the first channel state information, wherein the antenna pair includes two antennas in the transceiver antenna array whose connection direction is parallel to the entry and exit direction of the target object, the target parameters include at least one of amplitude data and phase data, the at least one antenna pair corresponds to the at least one set of target parameters in one-to-one correspondence, the at least one antenna pair corresponds to the at least one set of direction perception models in one-to-one correspondence, and the direction perception model is a physical model;

[0033] A direction determination module is used to determine the entry and exit direction of the target object based on the at least one set of direction perception models.

[0034] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the above-mentioned method for determining the entry and exit direction when executed by the processor.

[0035] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned method for determining the entry and exit direction are implemented.

[0036] In an embodiment of the present disclosure, by obtaining first channel state information corresponding to an entry and exit time period, and constructing at least one set of direction perception models based on at least one set of target parameters of at least one antenna pair in the first channel state information, the direction perception model is used to characterize changes in a signal transmission path of a transceiver link corresponding to an antenna pair of a target object entering and exiting the antenna pair. By analyzing the above changes, the entry and exit direction of the target object within the perception area can be determined. Since the direction perception model is a physical model, it can avoid the influence of the degree of simulation of the training set and the accuracy of the classifier, so that the determined entry and exit direction of the target object is more accurate and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a flow chart of a method for determining an entry and exit direction provided by an embodiment of the present disclosure;

[0038] Figure 2a is a schematic diagram of an FFZ model of one of the antennas in an antenna pair provided in an embodiment of the present disclosure;

[0039] Figure 2b is a schematic diagram of an FFZ model of another antenna in an antenna pair provided by an embodiment of the present disclosure;

[0040] Figure 3a is a schematic diagram of a PD model of an antenna pair provided by an embodiment of the present disclosure;

[0041] Figure 3b is another schematic diagram of a PD model of an antenna pair provided by an embodiment of the present disclosure;

[0042] Figure 4 is a structural schematic diagram of a device for determining an entry and exit direction provided by an embodiment of the present disclosure;

[0043] Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0045] The present disclosure provides a method for determining an entry and exit direction. Figure 1 , Figure 1 is a flow chart of determining the direction of the entry and exit directions provided by an embodiment of the present disclosure, such as Figure 1 As shown, the following steps are included:

[0046] Step 101: Acquire first channel state information corresponding to an entry and exit time period.

[0047] The entry and exit time period is the time period when the target object enters and exits the sensing area corresponding to the transceiver antenna array.

[0048] In the present disclosure, the target object can be understood as an object with the ability to move, such as a person, a transport robot, etc.

[0049] The method for determining the entry and exit direction disclosed in the present invention can be applied to entry and exit sensing scenarios, such as: family member entry and exit detection scenarios, shopping mall pedestrian entry and exit detection scenarios, factory worker entry and exit detection scenarios, etc.; the aforementioned transceiver antenna array can be an antenna array arranged at the entrance and exit of the entry and exit sensing scene and having signal transceiver functions.

[0050] Exemplarily, the aforementioned transceiver antenna array can be a one-to-many mode or a many-to-many mode, wherein the one-to-many mode can be a single antenna at the signal transmitting end corresponding to at least two antennas at the signal receiving end, and the one-to-many mode can be at least two antennas at the signal transmitting end corresponding to a single antenna at the signal receiving end; the many-to-many mode can be at least two antennas at the signal transmitting end corresponding to at least two antennas at the signal receiving end, and the number of antennas at the signal transmitting end and the number of antennas at the signal receiving end in the many-to-many mode can be the same or different.

[0051] Exemplarily, the aforementioned entry and exit time period can be determined by acquiring the second channel state information (CSI) generated by the sensing area during the entire time period and extracting the variance of the amplitude of the second CSI at each moment in the entire time period, wherein the variance of the amplitude in the target object entry and exit scenario is significantly greater than the variance of the amplitude in the static scenario.

[0052] It should be emphasized that the above example is only used to illustrate a possible method for determining the entry and exit time period. The entry and exit time period corresponding to the target object entering and exiting the scene can also be determined based on other methods in the application. The present disclosure does not limit the specific method for determining the entry and exit time period.

[0053] Step 102: Construct at least one set of direction perception models according to at least one set of target parameters of at least one antenna pair in the first channel state information.

[0054] Among them, the antenna pair includes two antennas in the transceiver antenna array, the connection direction of which is parallel to the entry and exit direction of the target object, the target parameter includes at least one of amplitude data and phase data, the at least one antenna pair corresponds to the at least one group of target parameters in a one-to-one manner, the at least one antenna pair corresponds to the at least one group of direction perception models in a one-to-one manner, and the direction perception model is a physical model.

[0055] The first channel state information may be a channel state information matrix corresponding to the transmitting and receiving antenna array.

[0056] As described above, after determining at least one antenna pair in the transceiver antenna array, target parameters of two channel state information corresponding to each antenna pair can be extracted from the channel state information matrix to obtain a set of target parameters corresponding to each antenna pair.

[0057] Exemplarily, the above-mentioned direction perception model can be a First Fresnel Zone (FFZ) model and / or a phase difference (PD) model. It should be noted that, when the target parameter only includes amplitude data, the obtained direction perception model is the FFZ model; when the target parameter only includes phase data, the obtained direction perception model is the PD model; when the target parameter includes amplitude data and phase data, the FFZ model can be obtained based on the amplitude data in the target parameter, and the PD model can be obtained based on the phase data in the target parameter.

[0058] Step 103: Determine the entry and exit direction of the target object based on the at least one set of direction perception models.

[0059] For each set of direction perception models, the entry and exit movements of the target object will cause corresponding changes in amplitude and phase on the two signal receiving and transmitting links of the corresponding antenna pair. By analyzing the time domain characteristics of the amplitude or phase in the direction perception model, the entry and exit direction of the target object can be determined accordingly.

[0060] For example, see Figure 2a and Figure 2b ,in, Figure 2a It can be understood as a schematic diagram of the amplitude modulation fluctuation when the target object passes through the Fresnel zone of one of the antennas in a certain antenna pair (which can be called antenna 1). Figure 2b It can be understood as a schematic diagram of the amplitude modulation fluctuation when the target object passes through the Fresnel zone of another antenna in the antenna pair (which can be called antenna 2), as shown in FIG. Figure 2a It can be seen that the time when the target object crosses the boundary of the first Fresnel zone of the antenna 1 is 1.49 seconds and 1.99 seconds respectively; Figure 2b It can be seen that the time when the target object crosses the first Fresnel zone boundary of the antenna 2 is 1.51 seconds and 2.01 seconds respectively. In summary, it can be seen that the target object Figure 2a and Figure 2b In a corresponding entry and exit action, the entry and exit direction is from antenna 1 to antenna 2.

[0061] For example, see Figure 3a and Figure 3b ,in, Figure 3a It can be understood as a schematic diagram of the fluctuation of the phase difference between the two antennas in a certain antenna pair during an entry and exit action. Figure 3b It can be understood as a schematic diagram of the fluctuation of the phase difference between the two antennas in the antenna pair during another entry and exit action. Figure 3a Indicator entry and exit directions and Figure 3b Indications are in opposite directions; assuming Figure 3a and Figure 3b The phase differences shown in are the phase differences between antenna 3 and antenna 4 (i.e., the phase of antenna 4 minus the phase of antenna 3), so Figure 3a It can be seen that the phase difference between antenna 3 and antenna 4 has a trend of increasing first and then decreasing in the period separated by the dotted line, that is, Figure 3a The indicated in and out direction is from antenna 3 to antenna 4; Figure 3b It can be seen that the phase difference between antenna 3 and antenna 4 has a trend of decreasing first and then increasing in the period separated by the dotted line, that is, Figure 3b The indicated ingress and egress direction is the direction from antenna 4 to antenna 3.

[0062] In an embodiment of the present disclosure, by obtaining first channel state information corresponding to an entry and exit time period, and constructing at least one set of direction perception models based on at least one set of target parameters of at least one antenna pair in the first channel state information, the direction perception model is used to characterize changes in a signal transmission path of a transceiver link corresponding to an antenna pair of a target object entering and exiting the antenna pair. By analyzing the above changes, the entry and exit direction of the target object within the perception area can be determined. Since the direction perception model is a physical model, it can avoid the influence of the degree of simulation of the training set and the accuracy of the classifier, so that the determined entry and exit direction of the target object is more accurate and reliable.

[0063] In one embodiment, the acquiring the first channel state information corresponding to the entry and exit time period includes:

[0064] Acquire second channel state information generated by the sensing area in the whole time period;

[0065] Performing delay estimation on the second channel state information to obtain a shortest delay sequence for indicating a minimum signal transmission delay of the transceiver antenna array at each moment;

[0066] The entry and exit time period and the first channel state information generated by the entry and exit time period are determined according to the shortest delay sequence and a preset delay threshold, wherein the signal transmission delay corresponding to any moment in the entry and exit time period is greater than or equal to the delay threshold.

[0067] In this embodiment, by performing delay estimation on the second channel state information to replace the aforementioned variance calculation method, the entry and exit time periods are determined based on the shortest delay sequence of the physical side characteristics of the corresponding signal transceiver link, which can improve the accuracy of the determined entry and exit time periods and make the method described in the present disclosure more robust.

[0068] For example, in a static scenario, the direct path (Light of Sight, LoS) delay of the transceiver antenna array is the shortest delay; in an entry and exit scenario, the LoS of the transceiver antenna array is blocked, and the shortest delay is changed to the delay of the projection path or the diffraction path. Compared with the LoS delay, the delay of the projection path or the diffraction path is larger. Therefore, after constructing the shortest delay sequence, the entry and exit time periods can be quickly and accurately obtained by comparing the shortest moment at each moment and the numerical value of the delay threshold.

[0069] In one embodiment, determining the entry and exit time period and the first channel state information generated by the entry and exit time period according to the shortest delay sequence and a preset delay threshold includes:

[0070] Obtaining sliding variance data according to the shortest time delay sequence;

[0071] The entry and exit time period and the first channel state information generated by the entry and exit time period are determined according to the sliding variance data and the delay threshold.

[0072] In this embodiment, by calculating the sliding variance data of the aforementioned shortest delay sequence and distinguishing the entry and exit time periods based on the sliding variance data and the delay threshold, the reliability of the determined entry and exit time periods can be further improved.

[0073] In one embodiment, obtaining sliding variance data according to the shortest delay sequence includes:

[0074] Perform high-frequency filtering on the shortest time delay sequence to obtain a filtered time delay sequence;

[0075] The sliding variance data is obtained according to the filtered time delay sequence.

[0076] In this embodiment, after the sliding variance data is calculated, the shortest delay sequence is subjected to high-frequency filtering to filter out the high-frequency noise interference introduced into the shortest delay sequence by the noise contained in the signal transceiver link itself, so that the sliding variance data calculated subsequently is more accurate and reliable, that is, the determined entry and exit time periods are more accurate and reliable.

[0077] Exemplarily, a wavelet filter may be used to perform the aforementioned high-frequency filtering process.

[0078] In one embodiment, determining the entry and exit direction of the target object based on the at least one set of direction perception models includes:

[0079] Normalizing at least one set of target parameters of the first channel state information of the at least one antenna pair to obtain at least one set of normalized parameters;

[0080] Obtaining a weight coefficient for each antenna pair in the at least one antenna pair according to the at least one set of normalized parameters;

[0081] The entry and exit direction of the target object is obtained according to the weight coefficient of each antenna pair in the at least one antenna pair and the at least one set of direction perception models.

[0082] In this embodiment, in the case where there are two or more antenna pairs in the transceiver antenna array, the output results of the direction perception model corresponding to each antenna pair are weighted, so that the final entry and exit direction of the target object can be made more reliable.

[0083] Among them, the normalization processing of each set of target parameters is to eliminate the signal differences caused by hardware differences between different antennas in each antenna pair, as well as to eliminate the dimensional differences of amplitude differences and / or phases, so that the subsequently obtained weight coefficients are more accurate and reliable.

[0084] In one embodiment, the normalizing at least one set of target parameters of the first channel state information of the at least one antenna pair to obtain at least one set of normalized parameters includes:

[0085] Obtaining a first target parameter, a second target parameter, a minimum target parameter, and a maximum target parameter, wherein the first target parameter is a target parameter of one of the antennas in the target antenna pair, the second target parameter is a target parameter of the other antenna in the target antenna pair, the minimum target parameter is a target parameter with the smallest value in a set of target parameters associated with the target antenna pair, the maximum target parameter is a target parameter with the largest value in a set of target parameters associated with the target antenna pair, and the target antenna pair is any antenna pair in the at least one antenna pair;

[0086] A first normalized parameter and a second normalized parameter are calculated according to the first target parameter, the second target parameter, the minimum target parameter and the maximum target parameter, wherein the first normalized parameter is a ratio of a first parameter difference to a target parameter difference, the first parameter difference is a difference between the first target parameter and the minimum target parameter, the target parameter difference is a difference between the maximum target parameter and the minimum target parameter, the second normalized parameter is a ratio of a second parameter difference to the target parameter difference, and the second parameter difference is a difference between the second target parameter and the minimum target parameter;

[0087] A set of normalized parameters associated with the target antenna pair is generated according to the first normalized parameter and the second normalized parameter.

[0088] In this embodiment, a first normalized parameter and a second normalized parameter are calculated based on the first target parameter, the second target parameter, the minimum target parameter and the maximum target parameter, and a calculation method for a set of normalized parameters associated with the target antenna pair is generated accordingly. This can improve the calculation efficiency of each set of normalized parameters in at least one set of normalized parameters while eliminating signal differences caused by hardware differences between different antennas in the antenna pair.

[0089] For example, as shown in formula (1):

[0090]

[0091] Among them, signal i It represents the signal of antenna i in a certain antenna pair (which can be understood as the first target parameter or the second target parameter mentioned above), that is, amplitude data or phase data, min (which can be understood as the minimum target parameter mentioned above) and max (which can be understood as the maximum target parameter mentioned above) respectively represent the minimum and maximum values ​​of the signals of the two antennas in the time domain.

[0092] In one embodiment, obtaining a weight coefficient of each antenna pair in the at least one antenna pair according to the at least one set of normalized parameters includes:

[0093] Calculating the difference degree of each group of normalized parameters in the at least one group of normalized parameters to obtain the difference parameter of each group of normalized parameters in the at least one group of normalized parameters;

[0094] A weight coefficient of each antenna pair in the at least one antenna pair is determined based on a difference parameter of each group of normalized parameters in the at least one group of normalized parameters, wherein the difference parameter and the weight coefficient are negatively correlated.

[0095] In this embodiment, the difference parameter of each group of normalized parameters is calculated to determine the degree of signal difference between different antennas in the antenna pair corresponding to each group of normalized parameters, and the weight coefficient of each antenna pair is determined accordingly. By limiting the difference parameter and the weight coefficient to be negatively correlated, the entry and exit direction of the target object finally output can be made more accurate and reliable.

[0096] Exemplarily, the difference parameter of each group of normalized parameters may be a dynamic time warping (DTW) distance of each group of normalized parameters, as shown in formula (2):

[0097] DTW=L(M,N) (2)

[0098] Wherein, M and N are the lengths of signal signal1 (which can be understood as the normalized target parameter of one antenna in an antenna pair) and signal2 (which can be understood as the normalized target parameter of the other antenna in the antenna pair), respectively. L(M, N) represents the shortest path length of the two signals, which can be calculated by the following recursive formula (3):

[0099] L(1,1)=|signal1(1)-signal2(1)|

[0100]

[0101] It should be noted that, in this embodiment, the sum of the weight coefficients of each antenna pair in at least one antenna pair is 1.

[0102] For example, the weight coefficient of each antenna pair may be calculated as shown in formula (4):

[0103]

[0104] Wherein, when the target parameter includes only amplitude data or phase data, N is the number of antenna pairs of at least one antenna pair; when the target parameter includes amplitude data and phase data, N is twice the number of antenna pairs of at least one antenna pair.

[0105] For ease of understanding, the following examples are provided:

[0106] In the embodiment of the present invention, the transmission waveform of the transceiver link is an IEEE 802.11ac format waveform, the receiving end is a uniform array arranged in unit wavelengths, and the physical models used are the Fresnel zone model and the phase difference model. In this example, the transceiver devices are placed on both sides of the hall corridor, and the parameter configurations are shown in Table 1:

[0107] Carrier frequency Signal bandwidth Receiving antenna spacing Send and receive interval Signal transmission rate 5.4GHz 80MHz 5.4cm 2.9m 100Hz

[0108] Table 1

[0109] This example provides a method for joint identification of ingress and egress directions of wireless local area network communication and perception integration based on dynamic time warping, which includes the following steps:

[0110] Step 1: Place the sensing signal transceiver on both sides of the channel to be detected. The wireless signal transmitter continuously sends the 802.11ac waveform as both a communication and sensing signal to the wireless LAN access point antenna array at a certain signal transmission rate. The receiving end is in the form of a 4-source uniform linear array with a spacing of about one wavelength. After receiving the signal, the receiving antenna array unpacks the preamble code in the signal protocol physical layer frame structure to obtain the channel state information matrix and saves it to the server side.

[0111] It should be noted that the receiving end in actual applications may be in the form of other uniform arrays commonly found in commercial access points (APs) and routers, and the present disclosure does not limit this.

[0112] Step 2: After receiving the channel state information matrix of continuous perception signal frames, the server uses the frequency domain forward and backward smoothed Multiple Signal Classification (MUSIC) algorithm (or the Estimating Signal Parameters Viarotational Invariance Techniques (ESPRIT) algorithm) to estimate the delay parameters, and searches for the peak in each signal delay spectrum to extract the shortest arrival delay to construct the shortest delay sequence. The sequence reflects the change of the shortest path of the transmission signal between the transceiver links during the detection process. The principle is: when the scene is in a static state, the delay is the signal flight time of the direct path; when there is a crossing action (i.e., the entry and exit action of the target object), the diffraction phenomenon caused by the moving object on the transmitted electromagnetic wave will have a significant impact on the signal flight time.

[0113] By using the threshold-based detection method, we can capture the period when the moving object causes significant fluctuations in the shortest delay sequence, that is, the period corresponding to the crossing action; then extract the amplitude and phase of the channel state information in this period for subsequent processing.

[0114] Step 3: Divide the 4 antennas into two groups of antenna pairs, where the antenna intervals within the groups are all unit wavelengths, and the signals of each antenna pair are the CSI amplitude and phase extracted in step 2, for a total of 4 groups of detection data, i.e., the amplitude or phase sequences of the two antennas. In order to uniformly measure the similarity of the signal sequences corresponding to the two models between different antennas and retain the differences between the two groups of sequences, it is necessary to uniformly normalize each group of detection data. For the specific normalization method, please refer to the above formula (1).

[0115] Step 4: In order to measure the similarity between the two antenna signals in the antenna pair, the DTW distance of the normalized signals signal1 and signal2 of any antenna pair is calculated. The DTW distance can reflect the similarity between the two groups of signals in terms of value and time.

[0116] Step 5: Assign weights to each group of data according to the DTW distances of the four groups of detection data in step 4. The weight assignment criterion is that the smaller the DTW distance, the larger the corresponding weight, and the sum of all weights is guaranteed to be 1. For the specific weight calculation formula, see the aforementioned formula (4).

[0117] Step 6: According to the four groups of CSI amplitude and phase sequences extracted in step 3, the Fresnel zone model and phase difference model of the antenna pair are established respectively, and the direction prediction results of different antenna pairs and different models are obtained. The corresponding weights calculated in step 5 are assigned to these prediction results to determine the final entry and exit direction judgment results.

[0118] Step 7: The server feeds back the access information identified in step 6 to the receiving wireless LAN access point, which then sends it to the user terminal or other smart device to provide real-time perception information to the target user.

[0119] Table 2 shows the results of the present invention in the hall corridor scene entry and exit detection, a total of 339 groups of test data including continuous flow of people and multiple people entering and exiting at the same time were tested, and the results are presented as follows:

[0120] Missed detection rate: the probability that there is entry and exit behavior but the system fails to correctly identify the time period;

[0121] Accuracy: The probability that there is entry and exit behavior and the system can correctly determine the entry and exit direction;

[0122] Single-person scenario: There is entry and exit behavior, and only one person passes through the sending and receiving link;

[0123] Multi-person scenario: There is entry and exit, and more than one person passes through the send and receive link at the same time;

[0124] Continuous scenario: There is in-and-out behavior, and the transmission and reception links are passed more than once at intervals.

[0125] Missed detection number (rate) Accuracy Single scene Multiplayer scene Continuous scenes FFZ Model 2(0.59%) 93.16% 94.74% 87.88% 93.94% PD Model 9(3.24%) 93.94% 96% 95.23% 85.19% Joint testing 0 97.05% 98.68% 95.45% 95.45%

[0126] Table 2

[0127] According to Table 2, the joint identification method for the integrated access direction of wireless LAN communication and perception based on dynamic time warping in this example has no missed detection in the detection of 339 groups of test data; the number of groups with accurate direction judgment is 329, and the total accuracy rate reaches 97.05%; the accuracy rates for single-person scene, multi-person scene and continuous scene are 98.68%, 95.45% and 95.45% respectively. Moreover, compared with the detection results using a single model, the joint identification method provided in this example has a lower missed detection rate and higher detection accuracy for various scenes.

[0128] In addition, the method provided in this example only requires the use of two antennas arranged parallel to the entry and exit paths in the existing AP and a wireless device as a sensing signal transmitter. The entry and exit detection system based on the wireless LAN can use the channel state information provided by the commercial AP to detect and identify entry and exit actions, thereby realizing the integration of communication and perception and eliminating the cost of deploying transceiver equipment. In addition, the entry and exit detection system based on the wireless LAN can detect any entry and exit behavior at any time in a contactless and non-invasive manner, and does not require additional hardware requirements, so it is more cost-effective and has better adaptability.

[0129] like Figure 4As shown, the embodiment of the present disclosure further provides an entry / exit direction determining device 400, and the entry / exit direction determining device 400 includes:

[0130] The acquisition module 401 is used to acquire first channel state information corresponding to an entry and exit period, wherein the entry and exit period is a period when the target object enters and exits the sensing area corresponding to the transceiver antenna array;

[0131] A model building module 402 is used to build at least one set of direction perception models according to at least one set of target parameters of at least one antenna pair in the first channel state information, wherein the antenna pair includes two antennas in the transceiver antenna array whose connection direction is parallel to the entry and exit direction of the target object, the target parameter includes at least one of amplitude data and phase data, the at least one antenna pair and the at least one set of target parameters have a one-to-one correspondence, the at least one antenna pair and the at least one set of direction perception models have a one-to-one correspondence, and the direction perception model is a physical model;

[0132] The direction determination module 403 is used to determine the entry and exit direction of the target object based on the at least one set of direction perception models.

[0133] In one embodiment, the acquisition module 401 includes:

[0134] An information acquisition unit, used to acquire the second channel state information generated by the sensing area in the whole time period;

[0135] A delay estimation unit, used to perform delay estimation on the second channel state information to obtain a shortest delay sequence indicating a minimum signal transmission delay of the transceiver antenna array at each moment;

[0136] A time period determination unit is used to determine the entry and exit time period and the first channel state information generated by the entry and exit time period according to the shortest delay sequence and a preset delay threshold, wherein the signal transmission delay corresponding to any moment in the entry and exit time period is greater than or equal to the delay threshold.

[0137] In one embodiment, the time period determination unit includes:

[0138] A sliding variance calculation subunit, used for obtaining sliding variance data according to the shortest delay sequence;

[0139] The time period determination subunit is used to determine the entry and exit time period and the first channel state information generated by the entry and exit time period according to the sliding variance data and the delay threshold.

[0140] In one embodiment, the sliding variance calculation subunit is specifically used for:

[0141] Perform high-frequency filtering on the shortest time delay sequence to obtain a filtered time delay sequence;

[0142] The sliding variance data is obtained according to the filtered time delay sequence.

[0143] In one embodiment, the direction determination module 403 includes:

[0144] a normalization unit, configured to perform normalization processing on at least one set of target parameters of the first channel state information of the at least one antenna pair to obtain at least one set of normalized parameters;

[0145] A weight calculation unit, configured to obtain a weight coefficient of each antenna pair in the at least one antenna pair according to the at least one set of normalized parameters;

[0146] The direction determination unit is used to obtain the entry and exit direction of the target object according to the weight coefficient of each antenna pair in the at least one antenna pair and the at least one group of direction perception models.

[0147] In one embodiment, the weight calculation unit is specifically used to:

[0148] Calculating the difference degree of each group of normalized parameters in the at least one group of normalized parameters to obtain the difference parameter of each group of normalized parameters in the at least one group of normalized parameters;

[0149] A weight coefficient of each antenna pair in the at least one antenna pair is determined based on a difference parameter of each group of normalized parameters in the at least one group of normalized parameters, wherein the difference parameter and the weight coefficient are negatively correlated.

[0150] In one embodiment, the normalization unit is specifically used to:

[0151] Obtaining a first target parameter, a second target parameter, a minimum target parameter, and a maximum target parameter, wherein the first target parameter is a target parameter of one of the antennas in the target antenna pair, the second target parameter is a target parameter of the other antenna in the target antenna pair, the minimum target parameter is a target parameter with the smallest value in a set of target parameters associated with the target antenna pair, the maximum target parameter is a target parameter with the largest value in a set of target parameters associated with the target antenna pair, and the target antenna pair is any antenna pair in the at least one antenna pair;

[0152] A first normalized parameter and a second normalized parameter are calculated according to the first target parameter, the second target parameter, the minimum target parameter and the maximum target parameter, wherein the first normalized parameter is a ratio of a first parameter difference to a target parameter difference, the first parameter difference is a difference between the first target parameter and the minimum target parameter, the target parameter difference is a difference between the maximum target parameter and the minimum target parameter, the second normalized parameter is a ratio of a second parameter difference to the target parameter difference, and the second parameter difference is a difference between the second target parameter and the minimum target parameter;

[0153] A set of normalized parameters associated with the target antenna pair is generated according to the first normalized parameter and the second normalized parameter.

[0154] The device 400 for determining the entry and exit direction provided in the embodiment of the present disclosure can implement each process in the above method embodiment, and will not be described again here to avoid repetition.

[0155] See also Figure 5 , Figure 5 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure, such as Figure 5 As shown, the electronic device includes: a processor 501 , a memory 502 , and a program 5021 stored in the memory 502 and executable on the processor 501 .

[0156] When the program 5021 is executed by the processor 501, it can achieve Figure 1 Any steps in the corresponding method embodiments and achieving the same beneficial effects will not be repeated here.

[0157] Those skilled in the art will appreciate that all or part of the steps of implementing the above-mentioned embodiment method can be completed by hardware associated with program instructions, and the program can be stored in a readable medium.

[0158] The present disclosure also provides a readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned Figure 1 Any steps in the corresponding method embodiments can achieve the same technical effect and will not be repeated here to avoid repetition.

[0159] The computer-readable storage medium of the embodiment of the present disclosure may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it.

[0160] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0161] The program code contained on the storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0162] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0163] The above is a preferred implementation of the embodiment of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present disclosure. These improvements and modifications should also be regarded as the scope of protection of the present disclosure.

Claims

1. A method for determining an entry and exit direction, characterized in that: The method comprises: Acquire first channel state information corresponding to an entry and exit period, wherein the entry and exit period is a period during which the target object enters and exits a sensing area corresponding to the transceiver antenna array; Constructing at least one set of direction perception models according to at least one set of target parameters of at least one antenna pair in the first channel state information, wherein the antenna pair includes two antennas in the transceiver antenna array whose connection direction is parallel to the entry and exit direction of the target object, the target parameter includes at least one of amplitude data and phase data, the at least one antenna pair corresponds to the at least one set of target parameters in one-to-one correspondence, the at least one antenna pair corresponds to the at least one set of direction perception models in one-to-one correspondence, and the direction perception model is a physical model; The entry and exit directions of the target object are determined based on the at least one set of direction perception models.

2. The method according to claim 1, characterized in that: The obtaining of first channel state information corresponding to the entry and exit time period includes: Acquire second channel state information generated by the sensing area in the whole time period; Performing delay estimation on the second channel state information to obtain a shortest delay sequence for indicating a minimum signal transmission delay of the transceiver antenna array at each moment; The entry and exit time period and the first channel state information generated by the entry and exit time period are determined according to the shortest delay sequence and a preset delay threshold, wherein the signal transmission delay corresponding to any moment in the entry and exit time period is greater than or equal to the delay threshold.

3. The method according to claim 1, characterized in that: The determining the entry and exit direction of the target object based on the at least one set of direction perception models includes: Normalizing at least one set of target parameters of the first channel state information of the at least one antenna pair to obtain at least one set of normalized parameters; Obtaining a weight coefficient for each antenna pair in the at least one antenna pair according to the at least one set of normalized parameters; The entry and exit direction of the target object is obtained according to the weight coefficient of each antenna pair in the at least one antenna pair and the at least one set of direction perception models.

4. The method according to claim 3, characterized in that The obtaining, according to the at least one set of normalized parameters, a weight coefficient of each antenna pair in the at least one antenna pair comprises: Calculating the difference degree of each group of normalized parameters in the at least one group of normalized parameters to obtain the difference parameter of each group of normalized parameters in the at least one group of normalized parameters; A weight coefficient of each antenna pair in the at least one antenna pair is determined based on a difference parameter of each group of normalized parameters in the at least one group of normalized parameters, wherein the difference parameter and the weight coefficient are negatively correlated.

5. The method according to claim 3, characterized in that: The normalizing at least one set of target parameters of the first channel state information of the at least one antenna pair to obtain at least one set of normalized parameters includes: Obtaining a first target parameter, a second target parameter, a minimum target parameter, and a maximum target parameter, wherein the first target parameter is a target parameter of one of the antennas in the target antenna pair, the second target parameter is a target parameter of the other antenna in the target antenna pair, the minimum target parameter is a target parameter with the smallest value in a set of target parameters associated with the target antenna pair, the maximum target parameter is a target parameter with the largest value in a set of target parameters associated with the target antenna pair, and the target antenna pair is any antenna pair in the at least one antenna pair; A first normalized parameter and a second normalized parameter are calculated according to the first target parameter, the second target parameter, the minimum target parameter and the maximum target parameter, wherein the first normalized parameter is a ratio of a first parameter difference to a target parameter difference, the first parameter difference is a difference between the first target parameter and the minimum target parameter, the target parameter difference is a difference between the maximum target parameter and the minimum target parameter, the second normalized parameter is a ratio of a second parameter difference to the target parameter difference, and the second parameter difference is a difference between the second target parameter and the minimum target parameter; A set of normalized parameters associated with the target antenna pair is generated according to the first normalized parameter and the second normalized parameter.

6. The method according to claim 2, characterized in that The determining the entry and exit time period and the first channel state information generated by the entry and exit time period according to the shortest delay sequence and a preset delay threshold comprises: According to the shortest time delay sequence, sliding variance data is obtained; The entry and exit time period and the first channel state information generated by the entry and exit time period are determined according to the sliding variance data and the delay threshold.

7. The method according to claim 6, characterized in that The step of obtaining sliding variance data according to the shortest delay sequence includes: Perform high-frequency filtering on the shortest time delay sequence to obtain a filtered time delay sequence; The sliding variance data is obtained according to the filtered time delay sequence.

8. A device for determining an entry and exit direction, characterized in that: The device comprises: An acquisition module, used to acquire first channel state information corresponding to an entry and exit period, wherein the entry and exit period is a period when a target object enters and exits a sensing area corresponding to a transceiver antenna array; a model building module, configured to build at least one set of direction perception models according to at least one set of target parameters of at least one antenna pair in the first channel state information, wherein the antenna pair includes two antennas in the transceiver antenna array whose connection direction is parallel to the entry and exit direction of the target object, the target parameters include at least one of amplitude data and phase data, the at least one antenna pair corresponds to the at least one set of target parameters in one-to-one correspondence, the at least one antenna pair corresponds to the at least one set of direction perception models in one-to-one correspondence, and the direction perception model is a physical model; A direction determination module is used to determine the entry and exit direction of the target object based on the at least one set of direction perception models.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the method for determining the entry and exit direction according to any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for determining an entry and exit direction according to any one of claims 1 to 7 are implemented.