Wireless network WiFi (registered trademark) sensing method, computer equipment, 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 filed based on a Chinese patent application with an application number of 202210875975.3 and an application date of July 25, 2022, claims the priority of the Chinese patent application, and the entire content of the Chinese patent application is incorporated herein by reference.

[0002] This application relates to the technical field of communications, and in particular, to the wireless network WiFi (Registered trademark) Sensing method ,Ko Computer equipment and computer-readable storage media and related thereto.

Background Art

[0003] Monitoring and sensing based on the wireless network WiFi are all performed by the Received Signal Strength Indicator (RSSI). In the actual scenario, when the WiFi signal of the wireless network propagates in the indoor environment, the WiFi signal is affected by multiple obstacles and reaches the receiver along multiple paths including refraction and transmission. Signals on different paths have distortion phenomena such as different degrees of attenuation and delay, and the signal received by the receiving side is the superposition result of the distorted signals on different paths, that is, the so-called multipath effect. Due to the influence of the multipath effect, the stability of the RSSI received indoors is poor and fluctuates greatly even in static indoor scenarios. Therefore, the indoor multipath effect greatly limits the sensing ability of RSSI and can only be used to realize some coarse-grained indoor positioning and other sensing tasks.

Summary of the Invention

Problems to be Solved by the Invention

[0004] This application provides a wireless network WiFi sensing method, system and computer equipment.

Means for Solving the Problems

[0005] In a first aspect, the present invention provides a wireless network WiFi sensing method comprising the steps of: acquiring a WiFi signal transmitted by a path; detecting the scenario state of the 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 spectral map.

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

[0007] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when one or more of the computer-readable instructions are executed by one or more of the processors, the computer device causes one or more of the processors to perform a step of the method described in any one of the first aspects.

[0008] In a fourth aspect, the present invention further provides a computer-readable storage medium that is readable and writable by a processor, stores computer instructions, and when the computer-readable instructions are executed by one or more processors, causes one or more processors to perform the steps of the method described in any one of the first aspects. [Brief explanation of the drawing]

[0009] [Figure 1] This is a schematic diagram of the structure of a wireless network WiFi sensing system according to one embodiment of the present invention. [Figure 2] This is a flowchart of a wireless network WiFi sensing method according to one embodiment of the present invention. [Figure 3]Figure 2 is a flowchart of the substeps of step S300. [Figure 4] This is a flowchart of the substeps of step S310 in Figure 3. [Figure 5] This is a flowchart of the substeps of step S311 in Figure 4. [Figure 6] This is a flowchart of the substeps of step S313 in Figure 4. [Figure 7] Figure 3 is a flowchart of the substeps of step S320. [Figure 8] This is an overall flowchart of a wireless network WiFi sensing method according to another embodiment of the present invention. [Figure 9] This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. [Modes for carrying out the invention]

[0010] To further clarify the purpose, technical proposal and advantages of this application, the application will be described in more detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are used solely for the purpose of interpreting this application and are not intended to limit it.

[0011] While flowcharts indicate a logical sequence, in some cases, the steps shown or described may be performed in a different order than that shown in the flowchart. The terms "first," "second," etc., used in the specification, claims, and the drawings above are used to distinguish similar objects and do not necessarily describe a specific order or sequence.

[0012] The embodiments of this application provide a wireless network WiFi sensing method, system, and computer equipment. The embodiments of this application are advantageous for processing WiFi signals transmitted by subsequent paths by first acquiring WiFi signals transmitted by paths. By detecting the scenario state of the WiFi signal coverage area in real time, dynamic changes within the area at different times can be obtained. By performing signal processing on the WiFi signal according to the scenario state and generating a spectral map, multidimensional and high-precision WiFi sensing is achieved. The spectral map can reflect the mapping relationship between spatial changes and signal changes. By recognizing the WiFi signal according to the spectral map, coarse-grained and fine-grained sensing tasks can be realized. In other words, the technical solution of the embodiments of this application achieves multidimensional and high-precision WiFi sensing by processing multipath WiFi signals based on the scenario state detected in real time to obtain a spectral map, thereby enabling coarse-grained and fine-grained sensing tasks. Compared to related technologies, it can mitigate the problem of reduced WiFi sensing capability due to multipath effects, achieve multidimensional and high-precision WiFi sensing, and not only can coarse-grained sensing tasks be realized, but fine-grained sensing tasks can also be realized.

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

[0014] As shown in Figure 1, Figure 1 shows a schematic diagram of the structure of a wireless network WiFi sensing system according to an embodiment of the present invention. In the example of Figure 1, the wireless network WiFi sensing system is advantageous for processing subsequent WiFi signals transmitted by paths by first acquiring WiFi signals transmitted by paths using a signal acquisition module, detecting the scenario state of the WiFi signal coverage area in real time using a detection module to obtain dynamic changes within the area at different times, and performing signal processing on the WiFi signals according to the scenario state using a signal processing module to generate a spectral map and recognize the WiFi signals according to the spectral map, thereby mitigating the problem of degradation of WiFi sensing capability due to multipath effects, and enabling multidimensional and high-precision WiFi sensing, which 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 collect signals using a WiFi chip and only needs to support baseband signal acquisition; a detailed explanation is omitted here. The wireless network WiFi sensing system can be applied to the WiFi chips of the transceiver and can support the acquisition of all items that collect channel state information (CSI) or passive WiFi radar (PWR) information.

[0016] In one embodiment, it 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 applicable to processing wireless signals transmitted using orthogonal frequency division multiplexing, is also applicable to processing wireless signals transmitted using time division multiplexing, and is also applicable to processing other wireless signals transmitted using modulation and demodulation techniques. Detailed description here is omitted.

[0017] The devices and application scenarios described in the embodiments of this application are for more clearly explaining the technical solutions of the embodiments of this application, and do not limit the technical solutions related to the embodiments of this application. As those skilled in the art will understand, with the emergence of new application scenarios, the technical solutions related to the embodiments of this application can be similarly applied to similar technical problems.

[0018] As those skilled in the art can understand, the wireless network WiFi sensing system shown in FIG. 1 does not limit the embodiments of this application, and it may include more or fewer modules than shown in the figure, or combine some components, or have different component arrangements.

[0019] Based on the above wireless network WiFi sensing system, each embodiment of the wireless network WiFi sensing method of this application will be described below.

[0020] As shown in FIG. 2, FIG. 2 shows a flowchart of a wireless network WiFi sensing method according to an embodiment of this application, and the wireless network WiFi sensing method is applicable to a wireless network WiFi sensing system. The wireless network WiFi sensing method includes, but is not limited to, step S100, step S200, and step S300.

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

[0022] In one embodiment, the WiFi signal may be transmitted by multipath or by singlepath. If there are multiple available antennas, the multiple antennas perform multipath WiFi signal transmission, and using frequency division multiplexing or time division multiplexing techniques, it is possible to prevent interference between WiFi signals in each path transmission, thereby improving channel utilization. It is advantageous to acquire the WiFi signal transmitted by path by collecting the WiFi signal transmitted by path using a hardware front end, or by collecting the WiFi radar signal transmitted by path using an RF equipment front end, and then perform subsequent signal processing according to the acquired WiFi signal transmitted by path.

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

[0024] In one embodiment, in a real signal propagation environment, wireless signals are affected by multiple obstacles and reach the receiver along multiple paths, including refraction and transmission. Since signals along different paths experience distortions such as attenuation and delay to varying degrees, WiFi signals have distance and accuracy limitations. By detecting the scenario state of the WiFi signal coverage area in real time, it is possible to obtain the scenario state, which is the dynamic change in the area at different times. This is advantageous in mitigating distance and accuracy limitations by subsequently performing signal processing according to the scenario state.

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

[0026] In one embodiment, the scenario state may be a motion recognition, gesture recognition, or fall detection scenario, or it may be a change in the relative distance and velocity between an object and an antenna. By performing signal processing on the WiFi signal according to the above different scenario states and generating a spectral map, multidimensional and high-precision WiFi sensing can be achieved. The spectral map can reflect the mapping relationship between spatial changes and signal changes, and by recognizing the WiFi signal according to the spectral map, coarse-grained and fine-grained sensing tasks can be realized.

[0027] In one embodiment, CSI is an extension of WiFi communication, used to estimate the communication channel between the transmitter and receiver, and simultaneously providing amplitude and phase information, which can be improved by appropriate wireless hardware, enhancing the phase angle and amplitude difference. PWR information is based on the principle of radar, relating the transmitted signal from the access point to the transmitted signal from the monitoring area, and WiFi radar positioning is relatively coarse. Therefore, CSI has better performance in line-of-sight configurations and can process large amounts of data offline, while PWR information has better performance in spatial configurations of WiFi access points and radar receivers, and is real-time. By combining both and selecting the appropriate CSI and PWR information according to different detection scenarios and performing signal processing, the real-time performance and accuracy of WiFi sensing can be improved.

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

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

[0030] In one embodiment, the gaze configuration includes human motion recognition, gesture recognition, or fall detection that occur in the scenario, and is limited in its detection range and accuracy due to the physical separation between transmission and reception. Therefore, by performing signal processing on the WiFi signal using channel state information, a wider detection range and higher detection accuracy can be achieved, and large amounts of data can also be processed.

[0031] In one embodiment, channel state information can be used to calculate the channel information of each subcarrier in frequency division multiplexing, and it can also be used to calculate the channel information of each subcarrier in time division multiplexing. Below, using orthogonal frequency division multiplexing as an example, we will describe a processing process that uses channel state information to perform signal processing on a WiFi signal and generate a spectral map.

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

[0033] Step S311: Noise reduction processing is performed on the WiFi signal for each path to obtain multiple noise-reduced signals.

[0034] In one embodiment, the data signal collected by the hardware front end is typically noisy. First, the peaks of a total of 56 orthogonal frequency division multiplexed subcarriers are uniformly sampled. Then, noise reduction processing is performed on the WiFi signal for each pass 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 a multi-antenna setup, as shown in Figure 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 status information signal according to the WiFi signal for each path.

[0037] In one example, orthogonal frequency division multiplexing (OFDM) is widely used in various WiFi standards, and in an OFDM system, bandwidth is shared among multiple overlapping orthogonal subcarriers. An OFDM signal is defined according to the following formula.

[0038]

number

[0039] In one embodiment, the matrix symbol sequence may be quadrature phase shift keying (QPSK) or quadrature amplitude modulation (QAM). j is a coefficient that can be adjusted according to the actual situation.

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

[0041]

number

[0042] In one embodiment, the received signal includes WiFi signals from multiple paths, and a CSI signal, which is a channel state information signal, is obtained by superimposing the WiFi signals from each path, which is advantageous for subsequent noise reduction processing of the signal.

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

[0044] In one embodiment, due to changes in the power and data rate of the WiFi wireless access point, the channel state signal obtained in step S3111 is noisy. According to the division law of two complex numbers, the ratio of the CSI signals is still a complex value, and consequently, the amplitude is the quotient of the amplitude of that CSI signal, 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, i.e., power scaling changes over time but coincides between different antennas in the same receiver, and the noise can be removed by calculating the amplitude coefficient 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, and although the phase frequency offset is random and time-varying, they are two identical antennas, so they can be effectively canceled out by calculating the phase difference between the two antennas. Therefore, by calculating the ratio of channel state information signals from two adjacent antennas and obtaining multiple noise reduction signals, it is possible to remove most of the noise in the amplitude and time-varying phase shift of the CSI signal, providing a basic signal with a high signal-to-noise ratio for detection. Furthermore, by obtaining multiple CSI signals according to Multi-Input Multi-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 in is H(f c It is expressed as (t), and the ratio of channel state information of two adjacent antennas in the same receiver is calculated to obtain a noise reduction signal, which is expressed by the following formula.

[0046]

number

[0047] Expanding the above formula, we get the following:

[0048]

number

[0049] Optimizing the above equation yields the following equation.

[0050]

number

[0051] Step S312: Time-varying correlation analysis is performed on each noise reduction signal to obtain multiple principal component signals.

[0052] In one embodiment, the amount of data from the WiFi signal collected by the hardware device's front-end is large, resulting in a very large amount of data from the resulting channel status information signal. For example, the same transceiver consists of one transmitting antenna and three receiving antennas, with a power of 1 kHz, and 1 × 3 × 1k = 3k complex CSI signals per second. More transceivers may be included, and each transceiver may have many antennas. Consequently, the amount of data from the resulting noise reduction signal is large, and it is necessary to reduce the overall computational complexity through dimensionality reduction. The Principal Component Analysis (PCA) algorithm is used to recognize the time-varying correlations between the CSI signal flows of each noise reduction signal. These time-varying correlations are then combined to extract components that represent the changes in CSI signal measurement. Other dimensionality reduction algorithms may also be used, as long as the principal components can be extracted from the large amount of data. A detailed explanation is omitted here. The selection of the number of principal components must consider the balance between classification performance and computational complexity. For example, 70% or 60% of the signal's variance can be captured from two or three principal components, and six principal parts of the CSI signal can be extracted according to the proportion of this variance. If the first principal part contains noise due to reflections from stationary objects, the first principal part is discarded, and only five principal parts are 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 subsequent processing based on the principal component signals.

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

[0054] As shown in Figure 6, the steps for generating a spectral map in response to multiple principal component signals include, but are not limited to, the following steps.

[0055] Step S3131: Each principal component signal is divided into multiple signal segments of the same length, a Fourier transform is performed on each signal segment, and a spectrogram corresponding to each principal component signal is obtained.

[0056] In one embodiment, the CSI signal is highly sensitive to the surrounding environment, and since the RF reflection of the human body exhibits different frequencies when performing different movements, a calibration process that scans the background is usually required. In this embodiment, a short-term Fourier transform (STFT) is used to perform a spectrogram transform on each principal component signal. In one embodiment, the STFT divides the principal component signal into multiple signal segments of the same length using a sliding window, and then performs a fast Fourier transform (FFT) on the samples in each segment to obtain a spectrogram corresponding to each principal component signal. A wavelet transform algorithm may also be used to perform the spectrogram transform, as long as the spectrogram transform is possible, and a detailed explanation is omitted here. The spectrogram contains the three dimensions of the FFT: time, frequency, and amplitude, and obtaining the spectrogram is advantageous for subsequently calculating a spectral map based on the spectrogram.

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

[0058]

number

[0059] Step S3132: Perform arithmetic calculations on each spectrogram to generate a spectral map.

[0060] For example, in step S312, five main parts are obtained, a spectrogram is generated from these five main parts, and then an average arithmetic calculation is performed on the five main parts corresponding to the spectrogram to generate a spectral map. The spectral map can reflect the mapping relationship between spatial changes and signal changes, thereby enabling sensing and recognition of WiFi signals. The arithmetic calculation may further involve calculating the maximum or minimum value, provided that it improves the sensing accuracy.

[0061] In step S320, if the scenario state is spatial configuration, signal processing is performed on the WiFi signal according to the passive WiFi radar information to generate a spectral map.

[0062] In one embodiment, channel state information can be used to calculate the channel information of each subcarrier in frequency division multiplexing, and it can also be used to calculate the channel information of each subcarrier in time division multiplexing. Below, using orthogonal frequency division multiplexing as an example, the process of performing signal processing on a WiFi signal using passive WiFi radar information to generate a spectral map will be described.

[0063] In one embodiment, PWR information typically ensures the capture of a sufficient number of WiFi signals by capturing signals that are much longer than the CSI duration. Therefore, PWR information uses the entire WiFi signal; that is, PWR information does not process the signals of each subcarrier, but treats the entire OFDM as a single signal, and PWR information cannot access information within each subcarrier. The spatial configuration includes a rough calculation of the distance between the transceiver and objects in the area, or the movement of objects. Therefore, without focusing on information within each subcarrier, real-time signal processing is performed on the entire WiFi signal using PWR information to generate a spectral map. The spectral 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 as shown in Figure 7, when the scenario state is a spatial configuration, the steps of signal processing the WiFi signal according to passive WiFi radar information and generating a spectral map include, but are not limited to, the following steps.

[0065] Step S321: Ambiguity measure processing is performed on the WiFi radar signal for each path to obtain each measure signal.

[0066] In one embodiment, a cross-ambiguity function (CAF) is used to perform ambiguity measurement processing on the WiFi signal for each path, and by obtaining each measure signal, the signals collected by the radar can be effectively extracted, which is advantageous for rapid processing of the measure signals subsequently. The cross-ambiguity function may be a less complex cross-ambiguity function, or other versions of the cross-ambiguity function may be used, as long as it can effectively extract distance and Doppler information, and a detailed explanation is omitted here. CAF is an effective tool for extracting target distance and Doppler information in the field of passive radar, and requires two channels: a monitoring channel that collects signals from the monitoring area, and a reference channel that directly measures signals from the transmitter.

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

[0068] In one embodiment, the primary source of interference for the PWR information is signals from other WiFi hotspots entering the monitoring channel directly, i.e., direct interference information, which has higher energy than signals reflected from the moving target and can shield the Doppler pulses on the CAF surface. By performing direct interference rejection processing on each measure signal using an improved CLEAN algorithm and obtaining an interference-free signal, an improvement in the signal-to-noise ratio of the target signal can be achieved. The improved CLEAN algorithm may be a CLEAN-PSF algorithm or a CLEAN-SC algorithm, which shares one similar structure with the CAF process, generates a self-ambiguity surface from only the reference channel, and is expressed by the following equation.

[0069]

number

[0070] Step S323: Noise reduction processing is performed on each interference rejection signal to obtain each Doppler pulse.

[0071] In one embodiment, due to correlation within the time slot, residual noise exists after the CLEAN algorithm, and after removing the interfering signal from the signal in step S322, the noise on the CAF surface is further reduced. The background noise distribution of the interference-free signal is estimated using the Constant False-Alarm Rate (CFAR), and this is applied to the CAF surface to obtain each Doppler pulse. Obtaining Doppler pulses is advantageous for subsequently generating spectral maps in response to the Doppler pulses.

[0072] Applying a constant false alarm probability to the CAF surface can be expressed by the following formula.

[0073]

number

[0074] In one embodiment, a strong pulse higher than a threshold represents human movement, while any other pulse indicates that no movement is occurring, thus allowing for the measurement of human movement.

[0075] Step S324: Select the largest Doppler pulse and generate a spectral map.

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

[0077] As shown in Figure 8, the overall process first acquires a WiFi signal transmitted by a path, which may be a multipath WiFi signal or a singlepath WiFi signal. Taking a multipath WiFi signal as an example, the WiFi signal can be acquired by a hardware front-end or 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 detection is performed. Using channel state information, the multipath WiFi signal acquired by the hardware front-end is processed. First, the CSI signal of each antenna of the same transceiver is calculated. Then, the quotient of the CSI signals of two adjacent antennas of the same receiver is calculated based on the obtained CSI signal to obtain a noise reduction signal. Next, correlation analysis is performed on the noise reduction signal using the PCA algorithm to extract the principal components. Then, a spectral map corresponding to each principal component is obtained based on the phase and amplitude of the principal component signals. Subsequently, the average value of each spectral map is calculated to generate a final spectral map, thereby observing changes in the WiFi signal, recognizing the WiFi signal, and thereby achieving a high-precision WiFi sensing task. When the scenario state is a spatial configuration, for example, distance calculations between the transceiver and objects in the area, and rough calculations of the objects' movements are performed. Using passive WiFi radar information, the multipath WiFi radar signal acquired by the RF equipment's front end is processed. First, each measure signal is obtained using an ambiguity function, interference signals on the measure signal plane are removed to obtain an interference-free signal, and then noise reduction processing is performed on the interference-free signal to obtain multiple Doppler pulses. The maximum value is then selected from the Doppler pulses to generate a spectral map. By observing changes in the WiFi signal, recognizing the WiFi signal, and combining this with channel state information, a multidimensional WiFi sensing task can be realized.In the above step of detecting the scenario state in real time, depending on the scenario state at different times, one of the channel state information and passive WiFi radar information is selected to process the WiFi signal, a spectral map reflecting the change in the signal state is generated, and multidimensional and high-precision WiFi sensing can be achieved by mutually applying the channel state information and passive WiFi radar information in different scenarios to process the signal.

[0078] In one embodiment, the above-described 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, demonstrating a wide range of applicability.

[0079] As shown in 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: Memory 910 configured to store the program, The system includes, but is not limited to, a processor 920 configured to execute a program stored in memory 910, and which, when executing the program stored in memory 910, is configured to perform the wireless network WiFi sensing method described above.

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

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

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

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

[0084] Embodiments of the present invention further provide a computer-readable storage medium in which computer-executable instructions for performing the above-described wireless network WiFi sensing method are stored.

[0085] In one embodiment, the storage medium stores computer-executable instructions, and these instructions are executed by one or more control processors 920. For example, when executed by one processor 920 of the computer device 900, the one or more processors 920 can be made to execute the wireless network WiFi sensing method according to any embodiment of the present invention.

[0086] The embodiment of the present application is advantageous for processing subsequent WiFi signals transmitted by paths by first acquiring WiFi signals transmitted by paths, and by detecting the scenario state of the WiFi signal coverage area in real time, it is possible to obtain dynamic changes within the area at different times, and by performing signal processing on the WiFi signal according to the scenario state and generating a spectral map, multidimensional and high-precision WiFi sensing is achieved, the spectral map can reflect the mapping relationship between spatial changes and signal changes, and by recognizing the WiFi signal according to the spectral map, coarse-grained and fine-grained sensing tasks can be realized. In other words, the technical solution of the embodiment of the present application achieves multidimensional and high-precision WiFi sensing by processing multipath WiFi signals based on the scenario state detected in real time to obtain a spectral map, thereby enabling coarse-grained and fine-grained sensing tasks. Compared to related technologies, it is possible to mitigate the problem of reduced WiFi sensing capability due to the multipath effect, achieve multidimensional and high-precision WiFi sensing, and not only can coarse-grained sensing tasks be realized, but fine-grained sensing tasks can also be realized.

[0087] The embodiments described above are merely illustrative, and the units described as separation members may or may not be physically separated; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the technical proposal of this embodiment.

[0088] As a person skilled in the art will understand, all or some steps of the methods and systems disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof. Some or all 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-temporary media) and communication media (or temporary media). As a person skilled in the art will know, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technique for storing information (e.g., computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory, or other memory technologies, CD-ROM, digital multipurpose disc (DVD), or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage, or other magnetic storage devices, or any other media used to store desired information and accessible by a computer. Furthermore, as is well known to those skilled in the art, the communication medium may include any information transmission medium, and may typically include computer-readable instructions, data structures, program modules, or other data within the modulated data signal, such as other transmission mechanisms.

Claims

1. A wireless network Wi-Fi (registered trademark) sensing method, The steps include obtaining the Wi-Fi signal transmitted via the path, The steps include detecting in real time the scenario state, including the dynamic changes within the Wi-Fi signal coverage area at different times, The process includes the step of performing signal processing on the Wi-Fi signal according to the scenario state and generating a spectral map, The step of performing signal processing on the Wi-Fi signal according to the scenario state and generating a spectral map is: If the scenario state is a line-of-sight configuration, the process includes the step of performing signal processing on the Wi-Fi signal according to the channel state information and generating the spectral map. The aforementioned Wi-Fi signal is a multipath Wi-Fi signal. If the scenario state is a line-of-sight configuration, the step of performing signal processing on the Wi-Fi signal according to the channel state information and generating the spectral map is as follows: The steps include: performing noise reduction processing on the Wi-Fi signal of each path to obtain multiple noise-reduced signals; The steps include performing a time-varying correlation analysis on each of the noise reduction signals to obtain multiple principal component signals, The step of generating the spectral map according to a plurality of principal component signals, Wireless network (Wi-Fi) sensing method.

2. In the case of a multi-antenna system, the step of performing noise reduction processing on the Wi-Fi signal of each path to obtain multiple noise-reduced signals is: The steps include obtaining a channel status information signal according to the Wi-Fi signal of each path, A wireless network Wi-Fi sensing method according to claim 1, comprising the step of calculating the ratio of the channel state information signals of two adjacent antennas to obtain a plurality of noise reduction signals.

3. The step of performing a time-varying correlation analysis on each of the noise reduction signals to obtain multiple principal component signals is as follows: The steps include: using a principal component analysis algorithm to recognize the time-varying correlation between the channel state information signal flows of each noise reduction signal; A wireless network Wi-Fi sensing method according to claim 1, comprising the step of extracting the principal component signals representing changes in channel state information signals based on the aforementioned time-varying correlation.

4. The step of generating the spectral map according to the multiple principal component signals is: The steps include dividing each principal component signal into multiple signal segments of the same length, performing a Fourier transform on each signal segment, and obtaining a spectrogram corresponding to each principal component signal. A wireless network Wi-Fi sensing method according to claim 1, comprising the step of performing arithmetic calculations on each of the spectrograms to generate the spectral map.

5. The step of performing signal processing on the Wi-Fi signal according to the scenario state and generating a spectral map is: The wireless network Wi-Fi sensing method according to claim 1, comprising the step of performing signal processing on the Wi-Fi signal in accordance with passive Wi-Fi radar information and generating the spectral map when the scenario state is a spatial configuration.

6. The aforementioned Wi-Fi signal is a multipath Wi-Fi radar signal. If the scenario state is a spatial configuration, the step of performing signal processing on the Wi-Fi signal according to passive Wi-Fi radar information and generating the spectral map is as follows: The steps include performing ambiguity measurement processing on the Wi-Fi radar signal of each path to obtain each measurement signal, The steps include performing interference signal removal processing on each of the aforementioned measurement signals to obtain each interference-removed signal, The steps include: performing noise reduction processing on each of the aforementioned interference rejection signals to obtain each Doppler pulse; A wireless network Wi-Fi sensing method according to claim 5, comprising the step of selecting the largest Doppler pulse to generate the spectral map.

7. A computer device comprising memory and a processor, wherein the memory stores computer-readable instructions, and when one or more of the computer-readable instructions are executed by the processor, the computer device causes one or more of the processors to perform the steps of the wireless network Wi-Fi sensing method described in any one of claims 1 to 6.

8. A computer-readable storage medium that is readable and writable by a processor, stores computer-readable instructions, and when one or more processors execute the computer-readable instructions, causes one or more processors to execute the steps of the wireless network Wi-Fi sensing method described in any one of claims 1 to 6.

Images