Wireless network Wi-Fi® sensing method, computer device, and computer-readable storage medium

Abstract

The present application provides a wireless network WiFi sensing method, system and computer device, and relates to the communication field. [Solution] A wireless network WiFi sensing method includes a step (S100) of acquiring a WiFi signal transmitted by a path, a step (S200) of detecting a scenario state of the coverage area of ​​the WiFi signal in real time, and a step (S300) of performing signal processing on the WiFi signal according to the scenario state and generating a spectrum map.

Description

[Technical Field]

[0001] This application is based on and claims priority from a Chinese patent application bearing application number 202210875975.3 and filed on July 25, 2022, the entire contents of which are hereby incorporated by reference into this application.

[0002] The present application relates to the technical field of communications, and in particular to a wireless network WiFi sensing method, system and computer device. [Background technology]

[0003] All Wi-Fi-based monitoring and sensing relies on the received signal strength indicator (RSSI). In real-world scenarios, when a Wi-Fi signal propagates indoors, it is affected by multiple obstacles and travels multiple paths, including refraction and transmission, to reach the receiver. The signals along different paths experience distortions such as attenuation and delay to different degrees. The signal received by the receiver is a superposition of the distorted signals from the different paths, known as the multipath effect. Due to the multipath effect, the received RSSI is unstable indoors and fluctuates significantly even in static indoor scenarios. Therefore, the indoor multipath effect significantly limits the sensing capabilities of RSSI, making it only suitable for some coarse-grained indoor positioning and other sensing tasks. Summary of the Invention [Problem to be solved by the invention]

[0004] The present application provides a wireless network WiFi sensing method, system and computer device. [Means for solving the problem]

[0005] In a first aspect, the present application provides a wireless network WiFi sensing method, including: acquiring a WiFi signal transmitted by a path; detecting a scenario state of a coverage area of ​​the WiFi signal in real time; and performing signal processing on the WiFi signal according to the scenario state to generate a spectrum map.

[0006] In a second aspect, the present application provides a wireless network WiFi sensing system, including: a signal acquisition module configured to acquire a WiFi signal transmitted by a path; a detection module configured to detect a scenario state of a coverage area of ​​the WiFi signal in real time; and a signal processing module configured to perform signal processing on the WiFi signal according to the scenario state to generate a spectrum map.

[0007] In a third aspect, the present application provides a computing device comprising a memory and a processor, the memory having computer-readable instructions stored therein that, when executed by one or more of the processors, cause the one or more processors to perform the steps of the method of any one of the first aspects above.

[0008] In a fourth aspect, the present application further provides a computer-readable storage medium readable and writable by a processor, having computer instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform the steps of the method of any one of the first aspect above. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a structural schematic diagram of a wireless network WiFi sensing system according to an embodiment of the present application; [Figure 2] 2 is a flowchart of a wireless network WiFi sensing method according to an embodiment of the present application; [Figure 3]3 is a flowchart of sub-steps of step S300 in FIG. 2. [Figure 4] 4 is a flowchart of sub-steps of step S310 in FIG. 3. [Figure 5] 5 is a flowchart of a sub-step of step S311 in FIG. 4. [Figure 6] 5 is a flowchart of a sub-step of step S313 in FIG. 4. [Figure 7] 4 is a flowchart of sub-steps of step S320 in FIG. 3. [Figure 8] 3 is an overall flowchart of a wireless network WiFi sensing method according to another embodiment of the present application; [Figure 9] 1 is a structural schematic diagram of a computer device according to an embodiment of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0010] In order to clarify the purpose, technical solution and advantages of the present application, the present application will be described in more detail below with reference to the drawings and examples. It should be understood that the specific examples described herein are only used to interpret the present application and do not limit the present application.

[0011] It should be noted that although a logical order is depicted in the flowcharts, in some cases the steps shown or described may be performed in an order different from that depicted in the flowcharts. The terms "first," "second," etc. in the specification, claims, and drawings are used to distinguish between similar objects and do not necessarily describe a particular order or sequence.

[0012] The present embodiment provides a wireless network WiFi sensing method, system, and computer device. The present embodiment is advantageous in that it first acquires WiFi signals transmitted through paths and then processes the WiFi signals transmitted through paths. The scenario state of the WiFi signal coverage area can be detected in real time to obtain dynamic changes within the area at different times. The WiFi signals are processed according to the scenario state to generate a spectrum map, thereby achieving multidimensional and high-precision WiFi sensing. The spectrum map can reflect the mapping relationship between spatial changes and signal changes. The WiFi signals are recognized according to the spectrum map, thereby achieving coarse-grained and fine-grained sensing tasks. In other words, the technical solution of the present embodiment processes multipath WiFi signals according to the scenario state detected in real time to obtain a spectrum map, thereby achieving multidimensional and high-precision WiFi sensing, thereby achieving coarse-grained and fine-grained sensing tasks. Compared to related technologies, the problem of WiFi sensing performance degradation due to multipath effects can be alleviated, and multidimensional and high-precision WiFi sensing can be achieved, enabling not only coarse-grained sensing tasks but also fine-grained sensing tasks.

[0013] The embodiments of the present invention will be further described below with reference to the drawings.

[0014] Referring to Fig. 1, Fig. 1 shows a structural schematic diagram of a wireless network WiFi sensing system according to an embodiment of the present application. In the example of Fig. 1, the wireless network WiFi sensing system first acquires WiFi signals transmitted through paths using a signal acquisition module, and then processes the WiFi signals transmitted through paths. The detection module detects the scenario state of the WiFi signal coverage area in real time, thereby obtaining dynamic changes within the area at different times. The signal processing module performs signal processing on the WiFi signals according to the scenario state, generates a spectrum map, and recognizes the WiFi signals according to the spectrum map, thereby alleviating the problem of WiFi sensing capability degradation caused by multipath effects. This realizes multi-dimensional and high-precision WiFi sensing, and can realize not only coarse-grained sensing tasks but also fine-grained sensing tasks.

[0015] In one embodiment, the signal acquisition module is connected to the detection module, and the detection module is connected to the signal processing module. The signal acquisition module can acquire signals using a WiFi chip, and only needs to support baseband signal acquisition, and detailed description thereof will be omitted here. The wireless network WiFi sensing system can be applied to a WiFi chip in a transceiver and support acquiring all items for collecting channel state information (CSI) or passive WiFi radar (PWR) information.

[0016] In one embodiment, the WiFi signal may be a WiFi signal transmitted by multiple paths or a WiFi signal transmitted by a single path. For the transmitted WiFi signal, the wireless network WiFi sensing system is adapted to process wireless signals transmitted using orthogonal frequency division multiplexing, and also adapted to process wireless signals transmitted using time division multiplexing, and also adapted to process other wireless signals transmitted using modulation and demodulation techniques, and detailed description thereof will be omitted here.

[0017] The devices and application scenarios described in the embodiments of the present application are intended to more clearly explain the technical solutions of the embodiments of the present application, and are not intended to limit the technical solutions of the embodiments of the present application. As those skilled in the art will appreciate, with the emergence of new application scenarios, the technical solutions of the embodiments of the present application can be similarly applied to similar technical problems.

[0018] As will be appreciated by those skilled in the art, the wireless network WiFi sensing system shown in FIG. 1 is not intended to limit the scope of the present application and may include more or fewer modules than those shown, combine some components, or have a different component arrangement.

[0019] Based on the above wireless network WiFi sensing system, various embodiments of the wireless network WiFi sensing method of the present application will be described below.

[0020] 2, which shows a flowchart of a wireless network WiFi sensing method according to an embodiment of the present application, which is applied to a wireless network WiFi sensing system, includes, but is not limited to, steps S100, S200, and S300.

[0021] Step S100: Obtain a WiFi signal transmitted by a path.

[0022] In one embodiment, the WiFi signal may be transmitted through multiple paths or through a single path. If there are multiple available antennas, the multiple antennas can transmit the WiFi signal through multiple paths. Using frequency division multiplexing or time division multiplexing technology, the WiFi signals can be prevented from interfering with each other during transmission along each path, thereby improving channel utilization. It is advantageous to use a hardware front end to collect the WiFi signals transmitted along the paths, or a front end of an RF device to collect the WiFi radar signals transmitted along the paths to obtain the WiFi signals, and then perform subsequent signal processing according to the acquired WiFi signals transmitted along the paths.

[0023] Step S200: Detect the scenario state of the WiFi signal coverage area in real time.

[0024] In one embodiment, in an actual signal propagation environment, wireless signals are affected by multiple obstacles and reach a receiver along multiple paths, including refraction and transmission, and signals along different paths experience distortions such as attenuation and delay to different degrees. Therefore, WiFi signals have distance and accuracy limitations. By detecting the scenario state of the WiFi signal coverage area in real time, the scenario state, which is the dynamically changing situation within the area at different times, can be obtained. Subsequent signal processing according to the scenario state is advantageous in alleviating the distance and accuracy limitations.

[0025] Step S300: Perform signal processing on the WiFi signal according to the scenario state to generate a spectrum map.

[0026] In one embodiment, the scenario state may be a motion recognition, gesture recognition, or fall detection scenario, or may be a change in the relative distance and speed between the object and the antenna. Signal processing is performed on the WiFi signal according to the above different scenario states, and a spectrum map is generated, thereby realizing multi-dimensional and high-precision WiFi sensing. The spectrum map can reflect the mapping relationship between spatial changes and signal changes. By recognizing the WiFi signal according to the spectrum map, coarse-grained and fine-grained sensing tasks can be realized.

[0027] In one embodiment, CSI is an extension of WiFi communication. CSI is used to estimate the communication channel between the transmitter and receiver and also provides amplitude and phase information. The phase angle and amplitude difference can be improved with appropriate radio hardware. PWR information is based on radar principles. PWR information correlates the transmitted signal from the access point with the transmitted signal from the monitored area. WiFi radar positioning is relatively rough. Therefore, CSI has better performance in line-of-sight configurations and can process large amounts of data offline, while PWR information has better performance and real-time capabilities in spatial configurations of WiFi access points and radar receivers. By combining the two and selecting appropriate CSI and PWR information for signal processing according to different detection scenarios, the real-time capabilities and accuracy of WiFi sensing can be improved.

[0028] In one embodiment, the WiFi signal is a multipath WiFi signal, and as shown in FIG. 3, the steps of performing signal processing on the WiFi signal according to the scenario state and generating a spectrum map include, but are not limited to, steps S310 and S320.

[0029] Step S310: If the scenario state is a line-of-sight configuration, perform signal processing on the WiFi signal according to the channel state information to generate a spectrum map.

[0030] In one embodiment, the line-of-sight configuration includes human movement recognition, gesture recognition, or fall detection that occurs in a scenario, and the sensing range and accuracy are limited due to the physical separation between the transmitter and receiver. Therefore, by performing signal processing on the WiFi signal using channel state information, a wider sensing range and higher sensing accuracy can be achieved, and a large amount of data can be processed.

[0031] In one embodiment, the channel state information can be used to calculate channel information for each subcarrier of frequency division multiplexing, and can also be used to calculate channel information for each subcarrier of time division multiplexing. Hereinafter, the process of using channel state information to process WiFi signals and generate a spectrum map will be described using orthogonal frequency division multiplexing as an example.

[0032] As shown in FIG. 4, when the scenario state is a line-of-sight configuration, the step of performing signal processing on the WiFi signal according to the channel state information and generating a spectrum map includes, but is not limited to, the following steps:

[0033] Step S311: Perform noise reduction processing on the WiFi signal of each path to obtain multiple noise-reduced signals.

[0034] In one embodiment, the data signal collected by the hardware front end is usually noisy, and first the peaks of a total of 56 orthogonal frequency division multiplexing subcarriers are uniformly sampled, and then noise reduction processing is performed on the WiFi signal of each path after sampling to obtain multiple noise-reduced signals, thereby providing a basic signal with a high signal-to-noise ratio for detection.

[0035] In one embodiment, in the case of multiple antennas, as shown in FIG. 5, the step of performing noise reduction processing on the WiFi signal of each path to obtain multiple noise-reduced signals includes, but is not limited to, the following steps:

[0036] Step S3111: Obtain a channel state information signal according to the WiFi signal of each path.

[0037] In one embodiment, Orthogonal Frequency Division Multiplexing (OFDM) is widely used in various WiFi standards, and bandwidth in an OFDM system is shared among multiple overlapping orthogonal subcarriers. An OFDM signal is defined according to the following equation:

[0038]

number

[0039] In one embodiment, the matrix symbol sequence may be Quadrature Phase Shift Keying (QPSK) or Quadrature Amplitude Modulation (QAM), and j is a coefficient that can be adjusted according to actual circumstances.

[0040] In one embodiment, the received signal includes multipath reflected and direct signals, and the signals including delays and phase shifts in the reflected signals are from moving people and stationary objects, and the received signal is defined according to the following equation:

[0041]

number

[0042] In one embodiment, the received signal includes WiFi signals of multiple paths, and it is advantageous to obtain a channel state information signal, or CSI signal, by superimposing the WiFi signals of each path, and then perform noise reduction processing on the signal.

[0043] Step S3112: Calculate the ratio of the channel state information signals of two adjacent antennas to obtain multiple noise-reduced signals.

[0044] In one embodiment, the channel condition signal obtained in step S3111 is noisy due to changes in the power and data rate of the WiFi wireless access point. According to the division law of two complex numbers, the ratio of CSI signals is still a complex value, so the amplitude is the quotient of the amplitudes of the CSI signals, and the phase is the phase difference between two adjacent CSI signals. Regarding amplitude, pulse noise is a scaling noise that amplifies the power of each antenna at the same level in the same receiver. That is, power scaling varies over time, but is consistent between different antennas in the same receiver. Therefore, the noise can be removed by calculating the amplitude coefficients of the two antennas. Regarding phase, since different antennas in the receiver share the same clock, the phase shift (e.g., carrier) is the same as the frequency offset and sampling frequency offset. Although the phase frequency offset is random and time-varying, since they are the same antennas, it can be effectively canceled out by calculating the phase difference between the two antennas. Therefore, by calculating the ratio of the channel state information signals of two adjacent antennas and obtaining multiple noise-reduced signals, most of the noise in the amplitude and time-varying phase shift of the CSI signal can be removed, and a basic signal with a high signal-to-noise ratio can be provided for detection. In addition, by obtaining multiple CSI signals according to the Multiple Input Multiple Output (MIMO) technology, a wider detection range and higher detection accuracy can be achieved.

[0045] In one embodiment, the carrier frequency f c The CSI signal at c , t), and calculate the ratio of the channel state information of two adjacent antennas in the same receiver to obtain the noise-reduced signal, which is expressed as:

[0046]

number

[0047] The above formula can be expanded to be expressed as follows:

[0048]

number

[0049] The above formula is optimized to obtain the following formula:

[0050]

number

[0051] Step S312: Perform time-varying correlation analysis on each noise-reduced signal to obtain multiple principal component signals.

[0052] In one embodiment, the amount of data of the WiFi signal collected by the front end of the hardware device is large, so the amount of data of the obtained channel state information signal is also very large. For example, the same transceiver may have one transmit antenna and three receive antennas, with a power of 1 kHz, and there are 1 × 3 × 1k = 3k complex CSI signals per second. More transceivers may be included, and each transceiver may have multiple antennas. Therefore, the amount of data of the obtained noise-reduced signal is large, and dimensionality reduction is required to reduce the overall computational complexity. A principal component analysis (PCA) algorithm is used to identify time-varying correlations between the CSI signal flows of each noise-reduced signal, and then these time-varying correlations are combined to extract components representing CSI signal measurement changes. Other dimensionality reduction algorithms may also be used, as long as they can extract principal components from large amounts of data, and detailed descriptions are omitted here. The number of principal components selected must balance classification performance and computational complexity. For example, two or three principal components may capture 70% or 60% of the signal variance, and six principal parts of the CSI signal may be extracted according to the proportion of variance. If the first principal part contains noise due to reflections from stationary objects, the first principal part may be discarded and only five principal parts may be used. The above algorithm can obtain principal component signals of CSI signals from large amounts of data, ensuring classification performance, while also reducing computational complexity, which is advantageous for performing subsequent processing according to the principal component signals.

[0053] Step S313: Generate a spectral map according to the plurality of principal component signals.

[0054] As shown in FIG. 6, generating a spectral map according to a plurality of principal component signals includes, but is not limited to, the following steps:

[0055] Step S3131: Divide each principal component signal into a plurality of signal segments of the same length, and perform a Fourier transform on each signal segment to obtain a spectrogram corresponding to each principal component signal.

[0056] In one embodiment, because CSI signals are highly sensitive to the surrounding environment and RF reflections from the human body exhibit different frequencies when performing different movements, a calibration process of scanning the background is usually required. In this embodiment, a short-term Fourier transform (STFT) is used to perform a spectrogram transformation on each principal component signal. In one embodiment, the STFT uses a sliding window to divide the principal component signal into multiple signal segments of equal length, and then performs a fast Fourier transform (FFT) on samples in each segment to obtain a spectrogram corresponding to each principal component signal. The spectrogram transformation may also be performed using a wavelet transform algorithm; as long as spectrogram transformation is possible, a detailed description will be omitted here. The spectrogram includes three dimensions of FFT: time, frequency, and amplitude. Obtaining the spectrogram is advantageous for subsequently calculating a spectral map according to the spectrogram.

[0057] The STFT algorithm is expressed by the following equation:

[0058]

number

[0059] Step S3132: Arithmetic calculations are performed on each spectrogram to generate a spectrum map.

[0060] For example, five main parts are obtained in step S312, a spectrogram is generated from the five main parts, and then an average arithmetic calculation is performed on the five main parts corresponding to the spectrogram to generate a spectrum map. The spectrum map can reflect the mapping relationship between spatial variation and signal variation, thereby sensing and recognizing WiFi signals. The arithmetic calculation can also be a maximum or minimum value calculation, which can improve sensing accuracy.

[0061] Step S320: if the scenario state is a spatial configuration, perform signal processing on the WiFi signal according to the passive WiFi radar information to generate a spectrum map.

[0062] In one embodiment, the channel state information can be calculated as channel information for each subcarrier of frequency division multiplexing, or can be calculated as channel information for each subcarrier of time division multiplexing. Hereinafter, we will use orthogonal frequency division multiplexing as an example to describe the process of using passive WiFi radar information to process WiFi signals and generate a spectrum map.

[0063] In one embodiment, the PWR information typically captures signals much longer than the CSI duration to ensure a sufficient number of WiFi signals. Therefore, the PWR information uses the entire WiFi signal, i.e., the PWR information does not process the signal of each subcarrier but treats the entire OFDM as one signal, and the PWR information does not have access to information within each subcarrier. The spatial configuration involves a rough calculation of the distance between the transceiver and an object in the area or the object's movement. Therefore, instead of focusing on information within each subcarrier, the PWR information is used to perform real-time signal processing on the entire WiFi signal to generate a spectrum map. The spectrum map can reflect the mapping relationship between spatial changes and overall signal changes, which is advantageous for sensing and recognizing WiFi signals.

[0064] In one embodiment, the WiFi signal is a multipath WiFi radar signal, and when the scenario state is a spatial configuration as shown in FIG. 7 , the step of performing signal processing on the WiFi signal according to passive WiFi radar information to generate a spectrum map includes, but is not limited to, the following steps:

[0065] Step S321: Perform ambiguity measurement processing on the WiFi radar signal of each path to obtain each measurement signal.

[0066] In one embodiment, a cross-ambiguity function (CAF) is used to perform ambiguity measurement processing on the WiFi signal of each path to obtain each measurement signal, which can effectively extract the signals collected by the radar and is advantageous for subsequent rapid processing of the measurement signals. The cross-ambiguity function may be a low-complexity cross-ambiguity function, or other versions of the cross-ambiguity function may be used as long as they can effectively extract range and Doppler information, and detailed descriptions are omitted here. CAF is an effective tool for extracting target range and Doppler information in the field of passive radar. It requires two channels: a monitoring channel to collect signals from the monitored area and a reference channel to directly measure signals from the transmitter.

[0067] Step S322: An interference signal removal process is performed on each measurement signal to obtain each interference-removed signal.

[0068] In one embodiment, the main source of interference for the PWR information is the signal of other WiFi hotspots directly entering the monitoring channel, i.e., direct interference information. The direct interference information has higher energy than the signal reflected from a moving target and can block the Doppler pulse of the CAF surface. The improved CLEAN algorithm can be used to perform direct interference signal removal processing on each measurement signal to obtain an interference-removed signal, thereby improving the signal-to-noise ratio of the target signal. The improved CLEAN algorithm can be the CLEAN-PSF algorithm or the CLEAN-SC algorithm. The improved CLEAN algorithm shares a similar structure with the CAF process and generates a self-ambiguity surface from only the reference channel, which is expressed as follows:

[0069]

number

[0070] Step S323: Noise removal processing is performed on each interference-removed signal to obtain each Doppler pulse.

[0071] In one embodiment, due to correlation within a time slot, residual noise exists after the CLEAN algorithm. After removing the interference signal from the signal in step S322, the noise in the CAF plane is further reduced. A constant false-alarm rate (CFAR) is used to estimate the background noise distribution of the interference-removed signal, which is then applied to the CAF plane to obtain each Doppler pulse. Obtaining the Doppler pulse is advantageous for subsequently generating a spectrum map according to the Doppler pulse.

[0072] Applying a constant false alarm probability to the CAF surface is expressed as follows:

[0073]

number

[0074] In one embodiment, a strong pulse above a threshold indicates human movement, otherwise no movement is occurring, and thus human movement can be measured.

[0075] Step S324: Select the maximum Doppler pulse to generate a spectrum map.

[0076] In one embodiment, in step S323, multiple Doppler pulses are obtained, and the largest Doppler pulse is selected from each Doppler in the CAF plane and combined with the series of measurements to generate a spectrum map. The spectrum map is a Dopplergram of PWR information. The Dopplergram can reflect the mapping relationship between spatial variation and overall signal variation, thereby sensing and recognizing WiFi signals.

[0077] As shown in FIG. 8, the overall process is as follows: first, a WiFi signal transmitted through a path is acquired, which may be a multi-path WiFi signal or a single-path WiFi signal. Taking a multi-path WiFi signal as an example, the WiFi signal can be acquired by a hardware front end, or a multi-path WiFi radar signal can be acquired by an RF equipment front end. Depending on the detected scenario state, if the scenario state is a line-of-sight configuration, for example, gesture recognition or fall recognition can be performed. The multi-path WiFi signal acquired by the hardware front end is processed using channel state information. The CSI signals of each antenna of the same transmitter and receiver are first calculated, and then the quotient of the CSI signals of two adjacent antennas of the same receiver is calculated according to the obtained CSI signals to obtain a noise-reduced signal. Next, a PCA algorithm is used to perform a correlation analysis on the noise-reduced signal to extract principal components. Next, spectral maps corresponding to each principal component are obtained according to the phase and amplitude of the principal component signals. Then, the average of each spectral map is calculated to generate a final spectral map. This allows the WiFi signal changes to be observed and the WiFi signal to be recognized, thereby achieving high-precision WiFi sensing. When the scenario state is a spatial configuration, for example, the distance between the transceiver and objects in the area is calculated, and the movement of the objects is roughly calculated. Passive WiFi radar information is used to process the multipath WiFi radar signals acquired by the front end of the RF equipment. First, each measurement signal is obtained using an ambiguity function, and interference signals on the measurement signal plane are removed to obtain an interference-free signal. Next, noise is removed from the interference-free signal to obtain multiple Doppler pulses, and the maximum values ​​are selected from the Doppler pulses to generate a spectrum map. This allows changes in the WiFi signal to be observed and the WiFi signal to be recognized. By combining this with channel state information, multidimensional WiFi sensing tasks can be realized.Regarding the above step of detecting the scenario state in real time, one of the channel state information and the passive WiFi radar information is selected according to the scenario state at different times to process the WiFi signal, and a spectrum map reflecting the changing state of the signal is generated. By mutually applying the channel state information and the passive WiFi radar information in different scenarios to process the signal, multi-dimensional and high-precision WiFi sensing can be realized.

[0078] In one embodiment, the wireless network WiFi sensing method can be applied to fine-grained sensing tasks such as fall detection, gesture recognition, and motion detection, as well as coarse-grained tasks such as distance detection, and has a wide range of applications.

[0079] Referring to Figure 9, Figure 9 shows a computer device 900 according to an embodiment of the present application. The computer device 900 may be a server or a terminal, and the internal structure of the computer device 900 is as follows: a memory 910 configured to store a program; and a processor 920 configured to execute a program stored in the memory 910, and configured to perform the wireless network WiFi sensing method when the program stored in the memory 910 is executed.

[0080] The processor 920 and the memory 910 are connected by a bus or other means.

[0081] The memory 910 may be configured as a non-transitory computer-readable storage medium to store non-transitory software programs and non-transitory computer-executable programs, such as the wireless network WiFi sensing method described in any embodiment of the present application, and the processor 920 executes the non-transitory software programs and instructions stored in the memory 910 to implement the wireless network WiFi sensing method.

[0082] The memory 910 may include a program storage area capable of storing an operating system, an application program required for at least one function, and a data storage area capable of storing and executing the wireless network WiFi sensing method. The memory 910 may also include high-speed random access memory and may further include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 910 includes memory located remotely from the processor 920, and the remote memory may be connected to the processor 920 via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0083] The non-transitory software programs and instructions necessary to implement the above wireless network WiFi sensing method are stored in memory 910 and, when executed by one or more processors 920, perform the wireless network WiFi sensing method according to any embodiment of the present application.

[0084] An embodiment of the present application further provides a computer-readable storage medium having stored thereon computer-executable instructions for performing the above wireless network WiFi sensing method.

[0085] In one embodiment, the storage medium stores computer-executable instructions that, when executed by one or more control processors 920, for example, by one processor 920 of the computer device 900, can cause the one or more processors 920 to perform a wireless network WiFi sensing method according to any embodiment of the present application.

[0086] The embodiments of the present application are advantageous in that they first acquire WiFi signals transmitted by paths and then process the WiFi signals transmitted by the paths. The scenario state of the WiFi signal coverage area can be detected in real time to obtain dynamic changes within the area at different times. Signal processing is performed on the WiFi signals according to the scenario state to generate a spectrum map, thereby achieving multidimensional and high-precision WiFi sensing. The spectrum map can reflect the mapping relationship between spatial changes and signal changes. The WiFi signals are recognized according to the spectrum map, thereby achieving coarse-grained and fine-grained sensing tasks. In other words, the technical solution of the embodiments of the present application processes multipath WiFi signals according to the scenario state detected in real time to obtain a spectrum map, thereby achieving multidimensional and high-precision WiFi sensing, thereby achieving coarse-grained and fine-grained sensing tasks. Compared to related technologies, the problem of WiFi sensing performance degradation due to multipath effects can be alleviated, and multidimensional and high-precision WiFi sensing can be achieved, enabling not only coarse-grained sensing tasks but also fine-grained sensing tasks.

[0087] The above-described embodiments are merely illustrative, and the units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the objectives of the technical solutions of the embodiments.

[0088] As will be appreciated by those skilled in the art, all or some steps of the above-disclosed methods and systems may be implemented as software, firmware, hardware, or any suitable combination thereof. Some or all of the physical components may be implemented as software running on a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on computer-readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). As known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (e.g., computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVDs) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium used to store the desired information and accessible by a computer. Also, as known to those skilled in the art, communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as other transport mechanism and may include any information delivery media.

Claims

1. A wireless network WiFi sensing method, comprising: acquiring a WiFi signal transmitted by the path; Detecting a scenario state of the WiFi signal coverage area in real time; performing signal processing on the WiFi signal according to the scenario state to generate a spectrum map.

2. The step of performing signal processing on the WiFi signal according to the scenario state and generating a spectrum map includes: The method of claim 1 , further comprising: if the scenario state is a line-of-sight configuration, performing signal processing on the WiFi signal according to channel state information to generate the spectrum map.

3. the WiFi signal is a multipath WiFi signal; When the scenario state is a line-of-sight configuration, performing signal processing on the WiFi signal according to channel state information to generate the spectrum map includes: performing noise reduction processing on the WiFi signal of each path to obtain a plurality of noise-reduced signals; performing a time-varying correlation analysis on each of the noise-reduced signals to obtain a plurality of principal component signals; and generating the spectral map in response to a plurality of the principal component signals.

4. In the case of a multi-antenna, the step of performing noise reduction processing on the Wi-Fi signal of each path to obtain a plurality of noise-reduced signals includes: obtaining a channel state information signal in response to the WiFi signal of each path; and calculating a ratio of the channel state information signals of two adjacent antennas to obtain a plurality of the noise-reduced signals.

5. The step of generating the spectral map in response to a plurality of the principal component signals includes: Dividing each of the principal component signals into a plurality of signal segments of the same length, and performing a Fourier transform on each of the signal segments to obtain a spectrogram corresponding to each of the principal component signals; and performing an arithmetic calculation on each of the spectrograms to generate the spectral map.

6. The step of performing signal processing on the WiFi signal according to the scenario state and generating a spectrum map includes: The method of claim 1 , further comprising: when the scenario state is a spatial configuration, performing signal processing on the WiFi signal according to passive WiFi radar information to generate the spectrum map.

7. the WiFi signal is a multipath WiFi radar signal; When the scenario state is a spatial configuration, performing signal processing on the WiFi signal according to passive WiFi radar information to generate the spectrum map includes: performing an ambiguity measure process on the WiFi radar signal of each path to obtain each measure signal; performing an interference signal removal process on each of the measurement signals to obtain each interference-removed signal; performing noise removal processing on each of the interference-removed signals to obtain each Doppler pulse; and selecting the largest Doppler pulse to generate the spectral map.

8. A wireless network WiFi sensing system, comprising: a signal acquisition module configured to acquire a WiFi signal transmitted by the path; a detection module configured to detect a scenario state of the WiFi signal coverage area in real time; a signal processing module configured to perform signal processing on the WiFi signal according to the scenario state to generate a spectrum map.

9. A computing device comprising a memory and a processor, wherein the memory stores computer-readable instructions that, when executed by one or more of the processors, cause the one or more processors to perform the steps of the method of any one of claims 1 to 7.

10. 8. A computer-readable storage medium that is readable and writable by a processor and that stores computer instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the method of any one of claims 1 to 7.

Images