Methods and devices for detecting the presence of living beings inside a vehicle, storage media, and electronic devices.

Abstract

This invention provides a method, apparatus, storage medium, and electronic device for detecting the presence of a living being inside a vehicle. The method includes: activating the vehicle's StarFlash communication module to collect first static initial information about the vehicle's interior in basic SLB mode and second static initial information about the vehicle's interior in low-power SLE mode; determining whether a target living being exists inside the vehicle based on the first and second static initial information; if a target living being exists inside the vehicle, controlling the StarFlash communication module to locate the living being's position in SLE mode; and controlling the StarFlash communication module to identify the living being's type in SLB mode. This embodiment achieves the detection of the location and type of a living being inside the vehicle, improving the detection accuracy of living beings inside the vehicle and avoiding false alarms when an adult is inside.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and more specifically, to a method and apparatus for detecting the presence of living beings inside a vehicle, a storage medium, and an electronic device. Background Technology

[0002] In related technologies, cases of danger posed by children and pets in enclosed, oxygen-deprived environments inside cars have garnered increasing attention, and child presence detection (CPD) is gradually becoming a mandatory requirement for automakers. Early CPDs primarily used sensors (pressure / infrared / thermal / visual sensors, etc.) for detection, but these methods are limited in terms of detection range and interference resistance. In recent years, methods utilizing wireless sensing to improve CPD accuracy have emerged, such as millimeter-wave radar sensing and channel information sensing. However, millimeter-wave radar is not easily deployed in most mass-market vehicles due to its hardware cost disadvantages.

[0003] Channel information-based CPD methods primarily utilize the dynamic characteristics of wireless channels (such as Channel State Information (CSI), Received Signal Strength Index (RSSI), Doppler shift, multipath energy entropy, etc.) for biological detection. This information is used to extract micro-movement characteristics of living organisms (such as heartbeat and respiration) to determine their presence. SparkLink, as a novel communication technology, offers SLE (SparkLink Low Energy) and SLB (SparkLink Basic) modes, and has attracted widespread attention due to its ultra-low latency, ultra-high reliability, precise synchronization, flexible networking, and high-density connectivity. By flexibly utilizing SparkLink's two unique networking modes for transmitting and receiving wireless communication signals for in-vehicle biological presence detection, system power consumption can be minimized while ensuring detection accuracy, making it more suitable for electric-powered new energy vehicles.

[0004] No efficient and accurate solution has yet been found to address the aforementioned issues in the relevant technologies. Summary of the Invention

[0005] This invention provides a method and apparatus for detecting the presence of living beings inside a vehicle, a storage medium, and an electronic device, in order to solve the technical problems in related technologies.

[0006] According to an embodiment of the present invention, a method for detecting the presence of a living being inside a vehicle is provided, comprising: calling the vehicle's StarSignal Communication Module to collect first static initial information inside the vehicle in basic SLB mode and second static initial information inside the vehicle in low-power SLE mode; determining whether a target living being exists inside the vehicle based on the first static initial information and the second static initial information; if a target living being exists inside the vehicle, controlling the StarSignal Communication Module to locate the living being's position in SLE mode; increasing the signal power of the StarSignal Communication Module, controlling the StarSignal Communication Module to activate a beamforming focusing signal towards the living being's position in SLB mode, and extracting target feature information from the received signal; extracting biometrics from the target feature information; and using the biometrics to identify the living being's type.

[0007] Optionally, determining whether a target living being exists inside the vehicle based on the second static initial information includes: extracting the initial received signal strength index (RSSI) sequence from the second static initial information; performing a moving average filter on the initial RSSI sequence to obtain an intermediate RSSI sequence; calculating the mean and standard deviation of the intermediate RSSI sequence; constructing a baseline RSSI threshold for the static environment using the mean and standard deviation; continuing to collect real-time RSSI values ​​inside the vehicle in the SLE mode; and determining whether a target living being exists inside the vehicle based on the baseline RSSI threshold and the real-time RSSI values.

[0008] Optionally, determining whether a target living being exists inside the vehicle based on the baseline RSSI threshold and the real-time RSSI value includes: determining whether the baseline RSSI threshold and the real-time RSSI value satisfy the following relationship: ; This is the real-time RSSI value. The mean, The standard deviation, the benchmark RSSI threshold includes , If the criteria are met, it is confirmed that a living target is present inside the vehicle.

[0009] Optionally, determining whether a target living being exists inside the vehicle based on the first static initial information includes: extracting the Channel State Information (CSI) signal from the first static initial information and calculating the subcarrier energy of the CSI signal; calculating the multipath energy entropy of all subcarrier energies; and determining whether a target living being exists inside the vehicle based on the multipath energy entropy.

[0010] Optionally, determining whether a target living being exists inside the vehicle based on the multipath energy entropy includes: determining the material type of the vehicle's interior material, wherein the material type is used to characterize the degree of energy reflection on the material surface; finding a correction coefficient that matches the material type; updating the energy entropy threshold based on the correction coefficient; determining whether the multipath energy entropy is greater than the energy entropy threshold; and if the multipath energy entropy is greater than the energy entropy threshold, determining that a target living being exists inside the vehicle.

[0011] Optionally, controlling the star-flash communication module to locate the live position of the target living body in SLE mode includes: controlling the vehicle to collect the received power and CSI signal of the sampling points inside the vehicle in SLE mode; calculating the RSSI variance of the received power and extracting the ultra-low frequency component from the CSI signal, wherein the frequency range of the ultra-low frequency component corresponds to the body movement frequency of the living organism; calculating the signal periodicity index of the ultra-low frequency component; using the RSSI variance and the signal periodicity index to determine whether there is a target living body inside the vehicle; if there is a target living body inside the vehicle, locating the live position of the target living body.

[0012] Optionally, determining whether there is a moving object inside the vehicle using the RSSI variance and the signal periodicity index includes: determining whether the RSSI variance is an abnormal abrupt change value based on a benchmark RSSI threshold, and determining whether the signal periodicity index is greater than a preset threshold; if the RSSI variance is an abnormal abrupt change value, it is determined that there is a moving living object inside the vehicle; if the signal periodicity index is greater than the preset threshold, it is determined that there is a silent living object inside the vehicle.

[0013] Optionally, locating the live position of the target live body includes: if the target live body is a moving live body, controlling one node of the star-flash communication module as a transmitter and the other three nodes as receivers, acquiring a first set of communication signals between the transmitter and the receivers, and performing triangulation on the target live body based on the RSSI signal of the first set of communication signals to obtain a first live position of the target live body, wherein the star-flash communication module includes at least four nodes; if the target live body is a silent live body, controlling one node of the star-flash communication module as a transmitter and the other three nodes as receivers, acquiring a second set of communication signals between the transmitter and the receivers, and performing triangulation on the target live body based on the CSI signal of the second set of communication signals to obtain a second live position of the target live body.

[0014] Optionally, the target feature information includes CSI phase difference sequence, multipath delay spectrum, and Doppler spectrum information. Extracting biometric features from the target feature information includes: extracting first energy information of the CSI phase difference sequence in a first frequency band and second energy information in a second frequency band; calculating the periodicity exponent and harmonic components of the CSI phase difference sequence; calculating the standard deviation and multipath reflection energy entropy of the multipath delay spectrum; and calculating the peak power and spectral entropy of the Doppler spectrum information. The first energy information is determined as a first respiratory feature, the second energy information is determined as a first heartbeat feature, the periodicity exponent is determined as a second respiratory feature, the harmonic components are determined as a second heartbeat feature, the standard deviation and the multipath reflection energy entropy are determined as body shape features, and the peak power and the spectral entropy are determined as movement features. The biometric features include physiological features, body shape features, and movement features, and the physiological features include heartbeat features and respiratory features.

[0015] Optionally, identifying the liveness type of the target live body using the biometrics includes: for each target live body, inputting the corresponding biometrics into a decision tree logic, and using the decision tree logic to identify the liveness type of the target live body, wherein the liveness type includes: adult, child, and pet; if the decision tree logic fails to identify the live body, inputting the biometrics into a pre-trained neural network model, and using the neural network model to output the liveness type of the target live body.

[0016] Optionally, before invoking the vehicle's StarSignal communication module to collect the first static initial information inside the vehicle in SLB mode and the second static initial information inside the vehicle in low-power SLE mode, the method further includes: detecting the vehicle's state information; determining whether the vehicle is in a preset state based on the state information; if the vehicle is in a preset state, determining to invoke the vehicle's StarSignal communication module to collect the first static initial information inside the vehicle in SLB mode and the second static initial information inside the vehicle in low-power SLE mode.

[0017] Optionally, determining whether the vehicle is in a preset state based on the state information includes: determining whether the vehicle is in a parked state based on the gear position and handbrake position; if the vehicle is in a parked state, determining whether the vehicle is in a turned-off state based on the power signal; if the vehicle is in a turned-off state, determining whether the vehicle is in a closed state based on the door lock position; if the vehicle is in a closed state, determining whether the vehicle is in a sealed state based on the air conditioning and window positions; if the vehicle is in a sealed state, determining that the vehicle is in a preset state, wherein the state information includes: gear position, handbrake position, power signal, door lock position, air conditioning position, and window position.

[0018] Optionally, after controlling the Star Flash Communication module to identify the liveness type of the target live body in SLE mode, the method further includes: if the liveness type is a child and there is no adult, sending an alarm message to the remote terminal of the vehicle and starting the air conditioning system of the vehicle.

[0019] According to another embodiment of the present invention, a device for detecting the presence of a living person inside a vehicle is provided, comprising: a data acquisition module, configured to invoke the vehicle's StarSignal Communication Module to acquire first static initial information inside the vehicle in a basic SLB mode and second static initial information inside the vehicle in a low-power SLE mode; a first judgment module, configured to determine whether a target living person exists inside the vehicle based on the first static initial information and the second static initial information; a positioning module, configured to, if a target living person exists inside the vehicle, control the StarSignal Communication Module to locate the living person's position in SLE mode; and an identification module, configured to enhance the signal power of the StarSignal Communication Module, control the StarSignal Communication Module to activate a beamforming focusing signal towards the living person's position in SLB mode, and extract target feature information from the received signal; extract biometrics from the target feature information; and use the biometrics to identify the living person type of the target living person.

[0020] Optionally, the first judgment module includes: a first extraction unit, used to extract the initial received signal strength indicator (RSSI) sequence from the second static initial information; a filtering unit, used to perform a moving average filter on the initial RSSI sequence to obtain an intermediate RSSI sequence; a calculation unit, used to calculate the mean and standard deviation of the intermediate RSSI sequence; a construction unit, used to construct a baseline RSSI threshold for the static environment using the mean and the standard deviation; a collection unit, used to continue collecting real-time RSSI values ​​inside the vehicle in the SLE mode; and a first judgment unit, used to determine whether a target living being exists inside the vehicle based on the baseline RSSI threshold and the real-time RSSI values.

[0021] Optionally, the first determination unit includes: a determination subunit, used to determine whether the reference RSSI threshold and the real-time RSSI value meet the following relationship: ; This is the real-time RSSI value. The mean, The standard deviation, the benchmark RSSI threshold includes , If the criteria are met, it is confirmed that a living target is present inside the vehicle.

[0022] Optionally, the first judgment module includes: a first extraction unit, used to extract the Channel State Information (CSI) signal from the first static initial information and calculate the subcarrier energy of the CSI signal; a calculation unit, used to calculate the multipath energy entropy of all subcarrier energies; and a second judgment unit, used to determine whether there is a target living body inside the vehicle based on the multipath energy entropy.

[0023] Optionally, the second determination unit includes: a determination subunit, used to determine the material type of the interior material of the vehicle, wherein the material type is used to characterize the degree of energy reflection of the material surface; a search subunit, used to search for a correction coefficient matching the material type; an update subunit, used to update the energy entropy threshold based on the correction coefficient; a determination subunit, used to determine whether the multipath energy entropy is greater than the energy entropy threshold; and a determination subunit, used to determine that a target living body exists inside the vehicle if the multipath energy entropy is greater than the energy entropy threshold.

[0024] Optionally, the positioning module includes: a control unit for controlling the vehicle to collect the received power and CSI signal of the sampling points inside the vehicle in SLE mode; a first calculation unit for calculating the RSSI variance of the received power and extracting the ultra-low frequency component from the CSI signal, wherein the frequency range of the ultra-low frequency component corresponds to the body movement frequency of a living organism; a second calculation unit for calculating the signal periodicity index of the ultra-low frequency component; a first judgment unit for using the RSSI variance and the signal periodicity index to determine whether there is a target living body inside the vehicle; and a positioning unit for locating the living position of the target living body if it exists inside the vehicle.

[0025] Optionally, the first determination unit is further configured to: determine whether the RSSI variance is an abnormal abrupt change value based on a benchmark RSSI threshold, and determine whether the signal periodicity index is greater than a preset threshold; if the RSSI variance is an abnormal abrupt change value, determine that there is a moving living body in the vehicle; if the signal periodicity index is greater than the preset threshold, determine that there is a silent living body in the vehicle.

[0026] Optionally, the positioning unit is further configured to: if the target living body is a moving living body, control one node of the star-flash communication module as a transmitter and the other three nodes as receivers, acquire a first set of communication signals between the transmitter and the receiver, and perform triangulation positioning on the target living body based on the RSSI signal of the first set of communication signals to obtain a first living body position of the target living body, wherein the star-flash communication module includes at least four nodes; if the target living body is a stationary living body, control one node of the star-flash communication module as a transmitter and the other three nodes as receivers, acquire a second set of communication signals between the transmitter and the receiver, and perform triangulation positioning on the target living body based on the CSI signal of the second set of communication signals to obtain a second living body position of the target living body.

[0027] Optionally, the target feature information includes CSI phase difference sequence, multipath delay spectrum, and Doppler spectrum information. The extraction unit is further configured to: extract first energy information of the CSI phase difference sequence in a first frequency band and second energy information in a second frequency band; calculate the periodicity exponent and harmonic components of the CSI phase difference sequence; calculate the standard deviation and multipath reflection energy entropy of the multipath delay spectrum; and calculate the peak power and spectral entropy of the Doppler spectrum information; determine the first energy information as a first respiratory feature, the second energy information as a first heartbeat feature, the periodicity exponent as a second respiratory feature, the harmonic components as a second heartbeat feature, the standard deviation and the multipath reflection energy entropy as body shape features, and the peak power and the spectral entropy as motion features, wherein the biological features include physiological features, body shape features, and motion features, and the physiological features include heartbeat features and respiratory features.

[0028] Optionally, the identification unit is further configured to: for each target living organism, input the corresponding biometric features into a decision tree logic, and use the decision tree logic to identify the living organism type of the target living organism, wherein the living organism type includes: adult, child, pet; if the decision tree logic identification fails, input the biometric features into a pre-trained neural network model, and use the neural network model to output the living organism type of the target living organism.

[0029] Optionally, the device further includes: a detection module, configured to detect vehicle status information before the acquisition module calls the vehicle's StarSignal Communication module to acquire first static initial information inside the vehicle in SLB mode and second static initial information inside the vehicle in low-power SLE mode; a second judgment module, configured to determine whether the vehicle is in a preset state based on the status information; and a determination module, configured to determine, if the vehicle is in a preset state, to call the vehicle's StarSignal Communication module to acquire first static initial information inside the vehicle in SLB mode and second static initial information inside the vehicle in low-power SLE mode.

[0030] Optionally, the second determination module is further configured to: determine whether the vehicle is in a parked state based on the gear position and handbrake position; if the vehicle is in a parked state, determine whether the vehicle is in a turned-off state based on the power signal; if the vehicle is in a turned-off state, determine whether the vehicle is in a closed state based on the door lock position; if the vehicle is in a closed state, determine whether the vehicle is in a sealed state based on the air conditioning position and window position; if the vehicle is in a sealed state, determine that the vehicle is in a preset state, wherein the state information includes: gear position, handbrake position, power signal, door lock position, air conditioning position, and window position.

[0031] Optionally, the device further includes a notification module, configured to send an alarm message to the remote terminal of the vehicle and start the vehicle's air conditioning system if, after the identification module controls the star-flash communication module to identify the liveness type of the target live body in SLE mode, the live body type is a child and there is no adult present.

[0032] According to another aspect of the embodiments of this application, a storage medium is also provided, the storage medium including a stored program that executes the above steps when the program is run.

[0033] According to another aspect of the embodiments of this application, an electronic device is also provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; wherein: the memory is used to store computer programs; and the processor is used to execute the steps in the above method by running the programs stored in the memory.

[0034] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the above-described method.

[0035] The beneficial effects of this invention are:

[0036] 1. A multi-dimensional channel feature fusion-based biological presence detection method was constructed. Specifically, multi-dimensional channel environment information, including Received Signal Strength Indication (RSSI), Channel State Information (CSI), Doppler spectrum, and multipath delay spectrum, was acquired through a star-flash wireless communication system. Physiological, physical, and movement characteristics of organisms were systematically extracted to achieve a comprehensive determination and type identification of biological presence, thus avoiding false alarms and misleading detection.

[0037] 2. Taking advantage of the dual-mode coexistence of SLE low-power mode and SLB basic mode in Starflash technology, an innovative hierarchical detection mechanism was designed. The dual-mode collaborative working mechanism significantly reduces the overall power consumption of the system while ensuring detection accuracy. Attached Figure Description

[0038] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0039] Figure 1 This is a hardware structure block diagram of a car according to an embodiment of the present invention;

[0040] Figure 2 This is a flowchart of a method for detecting the presence of living beings inside a vehicle according to an embodiment of the present invention;

[0041] Figure 3 This is a layout diagram of the star-flash communication module provided in an embodiment of the present invention;

[0042] Figure 4 This is a flowchart of the system initialization and dual-mode baseline scanning method in an embodiment of the present invention;

[0043] Figure 5 This is a flowchart of the life detection assisted in SLE mode according to an embodiment of the present invention;

[0044] Figure 6 This is a flowchart of static life form depth detection in SLB mode according to an embodiment of the present invention;

[0045] Figure 7 This is a schematic diagram illustrating the principle of classifying target living organisms according to an embodiment of the present invention;

[0046] Figure 8 This is a flowchart of an embodiment of the present invention for detecting the presence of biological entities in a vehicle based on a dual-mode star-flash system.

[0047] Figure 9 This is a flowchart of the in-vehicle biological presence detection and alarm based on star flash according to an embodiment of the present invention;

[0048] Figure 10This is a structural block diagram of a vehicle-mounted live body detection device according to an embodiment of the present invention. Detailed Implementation

[0049] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of them. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present application can be combined with each other.

[0050] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0051] Example 1

[0052] The method embodiment provided in Embodiment 1 of this application can be executed in an automobile, server, processor, security controller, autonomous driving / assisted driving / intelligent driving controller, or similar processing device. Taking its operation in an automobile as an example, Figure 1 This is a hardware structure block diagram of a car according to an embodiment of the present invention. For example... Figure 1 As shown, a car may include one or more ( Figure 1 Only one is shown in the image. A processor 11 (processor 11 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 12 for storing data are also shown. Optionally, the vehicle may further include a transmission device 13 for communication functions and an input / output device 14. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned automobile. For example, the automobile may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0053] The memory 12 can be used to store automotive programs, such as application software programs and modules, like the automotive program corresponding to a method for detecting the presence of living beings inside a car according to an embodiment of the present invention. The processor 11 executes various functional applications and data processing by running the automotive program stored in the memory 12, thereby implementing the aforementioned method. The memory 12 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 12 may further include memory remotely located relative to the processor 11, and these remote memories can be connected to the car via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0054] The transmission device 13 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a vehicle's communication provider. In one example, the transmission device 13 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 13 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0055] This embodiment provides a method for detecting the presence of living beings inside a vehicle. Figure 2 This is a flowchart of a method for detecting the presence of living beings inside a vehicle according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0056] Step S201: Call the vehicle's Star Flash Communication Module to collect the first static initial information inside the vehicle in the basic SLB mode and the second static initial information inside the vehicle in the low power SLE mode.

[0057] The star-flash communication module in this embodiment is the star-flash device. Figure 3 This is a schematic diagram of the layout of the StarScan communication module provided in this embodiment of the invention. It is arranged in front of the windshield and behind the rear seats, with two sets of StarScan devices deployed at the front and rear respectively for transmitting and receiving wireless signals, forming a 2×2 array. The wireless signals are transmitted via multipath to cover the entire interior of the vehicle, ensuring no dead zones. Optionally, the StarScan devices can also be integrated with other sensors and vehicle infotainment systems within the vehicle to perform certain communication tasks.

[0058] In this embodiment, the first static initial information and the second static initial information are the communication signals between the nodes of the Star Flash Communication Module when the vehicle is in a static environment.

[0059] Step S202: Determine whether there is a target living body inside the vehicle based on the first static initial information and the second static initial information;

[0060] The target living being in this embodiment can be any living being, such as a pet, a child, or an adult.

[0061] Step S203: If a target living body is present in the vehicle, control the Star Flash Communication Module to locate the living body's position in SLE mode;

[0062] Step S204: Enhance the signal power of the star-flash communication module, control the star-flash communication module to start beamforming and focusing signal towards the living body location in SLB mode, and extract target feature information of the received signal; extract biometrics from the target feature information; and use the biometrics to identify the living body type of the target living body.

[0063] In this embodiment, the beamforming focusing signal is the focusing signal after the Star-Temperature Communication module initiates beamforming towards the live position in SLB mode. By adjusting the radiation parameters of the antenna array of the Star-Temperature Communication module, the signal energy is concentrated towards the live position to form a focusing signal.

[0064] Through the above steps, the vehicle's StarFlash Communication module is invoked to collect first static initial information inside the vehicle in basic SLB mode and second static initial information inside the vehicle in low-power SLE mode. Based on the first and second static initial information, it is determined whether a target living being exists inside the vehicle. If a target living being exists inside the vehicle, the StarFlash Communication module is controlled to locate the living being's position in SLE mode. The StarFlash Communication module is also controlled to identify the living being's type in SLB mode. This achieves the detection of the location and type of living beings inside the vehicle, improves the detection accuracy of living beings inside the vehicle, and avoids false alarms when adults are inside the vehicle.

[0065] In one embodiment of this example, determining whether a target living being exists inside the vehicle based on the second static initial information includes: extracting the initial received signal strength index (RSSI) sequence from the second static initial information; performing a moving average filter on the initial RSSI sequence to obtain an intermediate RSSI sequence; calculating the mean and standard deviation of the intermediate RSSI sequence; constructing a baseline RSSI threshold for the static environment using the mean and standard deviation; continuing to collect real-time RSSI values ​​inside the vehicle in the SLE mode; and determining whether a target living being exists inside the vehicle based on the baseline RSSI threshold and the real-time RSSI values.

[0066] In one example, determining whether a target living being exists inside the vehicle based on the baseline RSSI threshold and the real-time RSSI value includes: determining whether the baseline RSSI threshold and the real-time RSSI value satisfy the following relationship: ; This is the real-time RSSI value. The mean, The standard deviation, the benchmark RSSI threshold includes , If the criteria are met, it is confirmed that a living target is present inside the vehicle.

[0067] In one embodiment of this example, determining whether a target living being exists inside the vehicle based on the first static initial information includes: extracting the Channel State Information (CSI) signal from the first static initial information and calculating the subcarrier energy of the CSI signal; calculating the multipath energy entropy of all subcarrier energies; and determining whether a target living being exists inside the vehicle based on the multipath energy entropy.

[0068] The presence of a target living being inside the vehicle is confirmed when both the first static initial information and the second static initial information confirm that a target living being inside the vehicle exists. Alternatively, the presence of a target living being inside the vehicle is confirmed when either the first static initial information or the second static initial information confirms that a target living being inside the vehicle exists.

[0069] In one example, determining whether a target living being exists inside the vehicle based on the multipath energy entropy includes: determining the material type of the vehicle's interior material, wherein the material type is used to characterize the degree of energy reflection of the material surface; finding a correction coefficient that matches the material type; updating the energy entropy threshold based on the correction coefficient; determining whether the multipath energy entropy is greater than the energy entropy threshold; and if the multipath energy entropy is greater than the energy entropy threshold, determining that a target living being exists inside the vehicle.

[0070] Figure 4 This is a flowchart of the system initialization and dual-mode baseline scanning method in an embodiment of the present invention, including:

[0071] The Starflash detection system starts up and initializes the SLB and SLE modules. It detects the power supply status of the Starflash RF front-end, antenna impedance matching, baseband processor clock synchronization, etc., loads the Starflash protocol stack and configures the physical layer parameters of SLB and SLE modes, including modulation scheme, subcarrier spacing, MIMO beamforming, channel bandwidth, etc., and calibrates the radiation pattern and performs phase synchronization.

[0072] The StarScan SLE mode is used to collect RSSI background noise data for the entire vehicle as the second static initial information. StarScan transceivers are deployed at four points inside the vehicle, forming a rectangular topology to ensure seamless scanning of the entire vehicle. Optionally, the sampling frequency band is set to the 2.4GHz ISM band, the sampling bandwidth is 1MHz, and the sampling rate is 10 times per second. The original RSSI sequence is filtered using a moving average to suppress sudden interference pulses, and the mean RSSI is calculated using the following formula. and variance :

[0073] ,

[0074] in For the first The received power at each sampling point.

[0075] Based on the calculated RSSI mean and variance, a baseline RSSI threshold for the static environment is established. The criteria for judging anomalies in the real-time RSSI value inside the vehicle are set as follows: It can cover 99.7% of the normal distribution confidence interval, significantly reducing the probability of false alarms;

[0076] The Starflash SLB mode performs a fine scan of the omnidirectional CSI signal to obtain the first static initial information. Optionally, the receiver uses the 6GHz unlicensed band with an instantaneous bandwidth of 160MHz and a frequency resolution of 1.25MHz to perform channel estimation using the least squares method.

[0077] Calculate the initial CSI multipath energy entropy to preliminarily determine the presence of a target living being. Perform initial CSI multipath energy entropy calculation and living being prediction, and use CSI signals to preliminarily locate the living being. Multipath energy entropy (E) is an indicator that characterizes the randomness of the energy distribution of multipath signals in a wireless channel, measuring the degree of dispersion or uncertainty of the energy distribution of multipath components. Even slight movements of a living being (such as breathing or heartbeat) will lead to... Significantly increased, calculated using the following formula:

[0078]

[0079] in The normalized subcarrier energy is calculated using the following formula:

[0080]

[0081] in This is the subcarrier channel response.

[0082] When multipath energy entropy At that time, the presence of a silent life form is determined. Optionally, dynamic confidence correction can be performed, automatically adjusting the threshold based on a vehicle interior material database (leather / fabric / plastic), with the following adjustment rules:

[0083]

[0084] For example, full leather seats (low-reflective material) .

[0085] This method performs a preliminary scan of the channel information of the static starlight wireless communication environment inside the vehicle, providing baseline data for subsequent detection and making a preliminary prediction of the biological presence inside the vehicle.

[0086] In this embodiment, controlling the StarFlash communication module to locate the live position of a target living being in SLE mode includes: controlling the vehicle to collect the received power and CSI signal of the sampling points inside the vehicle in SLE mode; calculating the RSSI variance of the received power and extracting the ultra-low frequency component from the CSI signal, wherein the frequency range of the ultra-low frequency component corresponds to the body movement frequency of the living organism; calculating the signal periodicity index of the ultra-low frequency component; using the RSSI variance and the signal periodicity index to determine whether there is a target living being inside the vehicle; if there is a target living being inside the vehicle, locating the live position of the target living being.

[0087] Optionally, determining whether there is a moving object inside the vehicle using the RSSI variance and the signal periodicity index includes: determining whether the RSSI variance is an abnormal abrupt change value based on a benchmark RSSI threshold, and determining whether the signal periodicity index is greater than a preset threshold; if the RSSI variance is an abnormal abrupt change value, it is determined that there is a moving living object inside the vehicle; if the signal periodicity index is greater than the preset threshold, it is determined that there is a silent living object inside the vehicle.

[0088] Optionally, locating the live position of the target live body includes: if the target live body is a moving live body, controlling one node of the star-flash communication module as a transmitter and the other three nodes as receivers, acquiring a first set of communication signals between the transmitter and the receivers, and performing triangulation on the target live body based on the RSSI signal of the first set of communication signals to obtain a first live position of the target live body, wherein the star-flash communication module includes at least four nodes; if the target live body is a silent live body, controlling one node of the star-flash communication module as a transmitter and the other three nodes as receivers, acquiring a second set of communication signals between the transmitter and the receivers, and performing triangulation on the target live body based on the CSI signal of the second set of communication signals to obtain a second live position of the target live body.

[0089] Figure 5This is a flowchart of the life detection assisted by the SLE mode in an embodiment of the present invention, which can realize the detection of the location of a living body, including the following steps:

[0090] The StarFlash SLE mode provides continuous monitoring, constantly detecting sudden changes in the RSSI signal inside the vehicle. With its extremely low power consumption, the StarFlash SLE mode is suitable for continuous monitoring. When a sudden change in the RSSI signal inside the vehicle is detected (by continuously calculating the variance of the RSSI inside the vehicle and comparing it with the variance information of the static RSSI inside the vehicle collected by the baseline scan), it is preliminarily determined that there is a moving object inside the vehicle.

[0091] The Star Flash SLE mode activates SLE enhanced sampling every 30 seconds to collect 10 seconds of CSI phase information.

[0092] The 0.1-0.5Hz ultra-low frequency component is extracted using a compressed sensing algorithm, and the signal periodicity index is calculated.

[0093] Compressed sensing algorithms (which recover signals under undersampling conditions, reducing data volume and computational complexity, and are suitable for low-power SLE mode) are used to reconstruct the original signal from the sparse CSI signal and extract the ultra-low frequency components of 0.1-0.5Hz (corresponding to slight movements, breathing, or heartbeats in living organisms). The signal periodicity exponent is then calculated according to the following formula. .

[0094]

[0095] in The peak value of the autocorrelation coefficient representing the reconstructed signal, in Peak search volume within the range , and represent The mean and variance of noise outside the range.

[0096] Based on RSSI signal mutations and CSI phase data, anomalies inside the vehicle are determined using triangulation. For moving living entities (such as active people or pets), RSSI signals are used as the location signal; for silent living entities (such as sleeping or unconscious people or pets), CSI phase data is used as the location signal. A triangulation algorithm (where one star flash node acts as the transmitter and the other three as receivers) is employed to locate the anomaly point, providing the target living entity's position information.

[0097] By recovering the CSI phase signal under undersampling conditions through compressed sensing, the amount of data and computational complexity are reduced. It supports the persistent detection of life presence in the Starflash SLE low-power mode, thereby avoiding the power loss caused by frequent use of SLB mode. It provides the trigger conditions (coarse detection results) and the location information of potential life forms for the determination of silent life form depth detection in SLB mode.

[0098] Optionally, the target feature information includes CSI phase difference sequence, multipath delay spectrum, and Doppler spectrum information. Extracting biometric features from the target feature information includes: extracting first energy information of the CSI phase difference sequence in a first frequency band and second energy information in a second frequency band; calculating the periodicity exponent and harmonic components of the CSI phase difference sequence; calculating the standard deviation and multipath reflection energy entropy of the multipath delay spectrum; and calculating the peak power and spectral entropy of the Doppler spectrum information. The first energy information is determined as a first respiratory feature, the second energy information is determined as a first heartbeat feature, the periodicity exponent is determined as a second respiratory feature, the harmonic components are determined as a second heartbeat feature, the standard deviation and the multipath reflection energy entropy are determined as body shape features, and the peak power and the spectral entropy are determined as movement features. The biometric features include physiological features, body shape features, and movement features, and the physiological features include heartbeat features and respiratory features.

[0099] Optionally, identifying the liveness type of the target live body using the biometrics includes: for each target live body, inputting the corresponding biometrics into a decision tree logic, and using the decision tree logic to identify the liveness type of the target live body, wherein the liveness type includes: adult, child, and pet; if the decision tree logic fails to identify the live body, inputting the biometrics into a pre-trained neural network model, and using the neural network model to output the liveness type of the target live body.

[0100] Figure 6 This is a flowchart of a static life form depth detection process in SLB mode according to an embodiment of the present invention, which can realize the identification of living organism types, including:

[0101] Beamforming is initiated in anomaly areas to focus the signal path and enhance signal power. Beamforming is also initiated in anomaly areas located using RSSI or CSI phase information to focus the signal and enhance signal power.

[0102] The star stroboscopic device transmits linear frequency modulated continuous waves and acquires CSI phase difference sequences, multipath delay spectra, and micro-Doppler spectrum information;

[0103] Multidimensional feature extraction of living organisms includes biological features such as physiological features, body shape features, and movement features. Physiological features are hidden in CSI phase information. Energy in the 0.1-0.5Hz and 1-2Hz frequency bands is extracted to correspond to respiratory and heartbeat information, respectively. The periodicity exponent of the CSI phase signal is calculated to represent respiratory information, and the harmonic components of the CSI phase information are calculated to represent the heartbeat signal. Body shape information can be obtained from the multipath delay spectrum. The multipath delay standard deviation and multipath reflection energy entropy are calculated to jointly represent body shape information; the larger the body shape, the larger the multipath delay standard deviation and the smaller the multipath reflection energy entropy, and vice versa. Motion state information is represented by calculating the peak power and spectral entropy of the Doppler shift.

[0104] Multidimensional Feature-Based Organism Classification (Adults, Children, Pets). Based on extracted organism feature information, organisms are classified (adults, children, pets). Initial classification is performed using decision tree logic; if accurate classification fails, a pre-trained neural network model is used for secondary classification. Figure 7 This is a schematic diagram illustrating the principle of classifying live targets in an embodiment of the present invention. The judgment logic of the decision tree and the input of the neural network model can be formulated according to the differences in periodicity index, harmonic components, standard deviation, reflected energy entropy, peak power, and spectral entropy among adults, children, and pets.

[0105] If there are multiple anomalies, the above process is repeated until all anomalies have been detected.

[0106] This embodiment utilizes star-light beamforming to pinpoint the detection of multiple life forms. It detects life forms inside the vehicle by fusing channel features such as CSI, Doppler spectrum, and multipath delay, and distinguishes life forms inside the vehicle as adults, children, and pets to avoid false alarms or false alarm events caused by the presence of adults inside the vehicle.

[0107] Figure 8 This is a flowchart of an embodiment of the present invention for in-vehicle biological presence detection based on star-flash dual-mode collaboration, including:

[0108] The system initializes and performs a dual-mode baseline scan to acquire static initial information and determine whether the CSI multipath energy entropy is greater than the threshold E. After the StarShine Liveness Detection System starts, it first initializes the system by acquiring static initial information inside the vehicle through SLB and SLE modes, respectively, and calculating the CSI multipath energy entropy and RSSI under static conditions. If the CSI multipath energy entropy is greater than the threshold E (e.g., 2.5), it indicates that there may be a silent life form inside the vehicle, and the system directly enters the StarShine SLB silent life form deep detection mode; otherwise, it enters the StarShine SLE life sign auxiliary detection mode (detecting the location of the life form).

[0109] The StarShock SLE (Simultaneous Levitational Detection) system determines whether the auxiliary detection has met the trigger conditions. It utilizes StarShock's low-power SLE mode to continuously monitor the RSSI and CSI phase signal characteristics within the vehicle. When the auxiliary detection meets the trigger conditions, it enters the StarShock SLB (Silent Vital Detection) mode; otherwise, it continues with SLE auxiliary vital sign detection. Trigger conditions include: 1) a sudden increase in RSSI variance (triggered by live movement); 2) a CSI phase signal periodicity index > 0.7 (triggered by micro-movements, heartbeat, or respiration, etc.). Meeting either condition is sufficient.

[0110] The StarShine SLB mode silent life form depth detection involves switching the StarShine SLB to ultra-fine mode and emitting radio waves. It collects and uses multi-dimensional information such as CSI phase difference sequence, multipath delay spectrum and micro-Doppler spectrum information to determine whether there are silent life forms inside the vehicle, and classifies silent life forms as adults, pets and children.

[0111] This embodiment cleverly utilizes the characteristics of star-flash dual-mode communication to design a two-step determination mechanism of SLE mode resident detection and SLB mode depth detection. It also combines multi-dimensional information such as RSSI, CSI, multipath delay spectrum, and Doppler spectrum to jointly determine the presence characteristics of multiple organisms in the vehicle and classify them. While ensuring detection accuracy, it minimizes system power consumption, making this method more universal in electric new energy vehicles.

[0112] In one scenario of this embodiment, before invoking the vehicle's StarSignal Communication module to collect the first static initial information inside the vehicle in SLB mode and the second static initial information inside the vehicle in low-power SLE mode, the method further includes: detecting the vehicle's state information; determining whether the vehicle is in a preset state based on the state information; if the vehicle is in a preset state, determining to invoke the vehicle's StarSignal Communication module to collect the first static initial information inside the vehicle in SLB mode and the second static initial information inside the vehicle in low-power SLE mode.

[0113] Optionally, determining whether the vehicle is in a preset state based on the state information includes: determining whether the vehicle is in a parked state based on the gear position and handbrake position; if the vehicle is in a parked state, determining whether the vehicle is in a turned-off state based on the power signal; if the vehicle is in a turned-off state, determining whether the vehicle is in a closed state based on the door lock position; if the vehicle is in a closed state, determining whether the vehicle is in a sealed state based on the air conditioning and window positions; if the vehicle is in a sealed state, determining that the vehicle is in a preset state, wherein the state information includes: gear position, handbrake position, power signal, door lock position, air conditioning position, and window position.

[0114] First, the vehicle's parking status is checked. The vehicle is parked when it is in Park (P) and the electronic parking brake is engaged. The gear position signal status can be read from the transmission control module (TCM) via the CAN bus. A gear position code value in the range of 0×A1-0×A3 (ISO 11898 standard) corresponds to Park (P). The motor current characteristics of the electronic parking brake (EPB) are checked. When the current characteristics are all within the normal lock-up current range and there is no current fluctuation for 3 seconds, the electronic parking brake is engaged. The powertrain is also confirmed to be completely off. The vehicle is considered off when the drive motor phase current drops to 50mA. A 30-second countdown begins after the off-road signal is detected. If any door is detected to be open during this period, the timer is immediately reset. This operation prevents accidental triggering due to temporary engine shutdown. The doors are confirmed to be continuously closed. The Body Control Module (BCM) acquires the status of each door lock, performing a check every second. If no door is left open within two minutes, it is considered fully closed. The timer resets when any door is detected to be open, eliminating interference from brief door openings and closings. The system primarily relies on the status of the air conditioning and windows (including the sunroof) to determine if the interior is a sealed space. A barometric pressure sensor can also be used to detect the rate of change in interior air pressure; a rate of change less than 0.1 Pa / s indicates the interior is sealed.

[0115] By using information such as the handbrake, motor system, door locks, and air conditioning ventilation, the system can accurately determine whether the vehicle is in a non-operating state, thus avoiding power loss caused by activating the StarFlash Bio-existence detection system when temporarily parking.

[0116] In one implementation scenario of this embodiment, after controlling the Star Flash Communication module to identify the liveness type of the target live body in SLE mode, the method further includes: if the liveness type is a child and there is no adult, sending an alarm message to the remote terminal of the vehicle and starting the air conditioning system of the vehicle.

[0117] It can control the in-car flashing device or vehicle system to send alarm information to the owner's remote smart devices (such as mobile phones), and at the same time send the air conditioning start command to the vehicle control system to start heating / cooling and ventilation. If the air conditioning system fails to start, it can open the windows or doors.

[0118] Figure 9 This is a flowchart of the in-vehicle biological presence detection and alarm process based on starlight according to an embodiment of the present invention, including the following steps:

[0119] Determine that the vehicle has completely entered a non-operating state. This is done by checking factors such as the handbrake, motor system, door locks, and air conditioning ventilation.

[0120] Activate the in-vehicle Star Flash dual-mode biological detection system to detect the presence of multiple organisms in the vehicle and distinguish between adults, children, and pets. Children and pets are considered as vulnerable organisms without the ability to save themselves by default.

[0121] Determine if a vulnerable creature is alone inside the vehicle. If the vulnerable creature and an adult are both present, the adult can perform self-rescue actions, and the process ends. If the vulnerable creature is alone inside the vehicle, it is unable to perform self-rescue actions, and the process proceeds to the next step.

[0122] The in-car flashing device sends an alarm message to the owner's smart device and simultaneously sends a command to the vehicle control system to turn on the air conditioning and ventilation. The process ends here.

[0123] By classifying multiple organisms inside the vehicle and categorizing those without self-rescue capabilities as vulnerable organisms, the system only activates an alarm when a vulnerable organism is present alone, reducing false alarms. Furthermore, reusing the starlight device used for organism presence detection to send alarm information and commands further reduces system power consumption.

[0124] This embodiment provides a method for detecting the presence of living organisms inside a vehicle based on a dual-mode StarFlash communication system. This method utilizes multi-dimensional channel characteristics (including CSI information, Doppler shift, and multipath delay spectrum) within the StarFlash wireless communication channel environment to jointly detect the presence of multiple organisms and differentiate their types. It cleverly leverages the characteristics of dual-mode StarFlash communication to design a two-step decision mechanism: persistent detection in SLE mode and depth detection in SLB mode. This ensures detection accuracy while minimizing system power consumption, making the method more universally applicable in electric-powered new energy vehicles. The cost of StarFlash equipment is lower than that of millimeter-wave radar, making it cost-effective for detecting children inside vehicles and reducing overall vehicle costs.

[0125] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0126] Example 2

[0127] This embodiment also provides a device for detecting the presence of living beings inside a vehicle. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0128] Figure 10 This is a structural block diagram of a vehicle-mounted live body detection device according to an embodiment of the present invention, such as... Figure 10 As shown, the device includes:

[0129] The acquisition module 101 is used to call the vehicle's Star Flash Communication module to acquire the first static initial information inside the vehicle in the basic SLB mode and the second static initial information inside the vehicle in the low power SLE mode.

[0130] The first judgment module 102 is used to determine whether there is a target living body inside the vehicle based on the first static initial information and the second static initial information.

[0131] The positioning module 103 is used to control the star flash communication module to locate the live position of the target living body in SLE mode if there is a target living body in the vehicle.

[0132] The identification module 104 includes: a processing unit for enhancing the signal power of the star-flash communication module, controlling the star-flash communication module to start beamforming and focusing signals toward the living body location in SLB mode, and extracting target feature information from the received signals; an extraction unit for extracting biometrics from the target feature information; and an identification unit for identifying the living body type of the target living body using the biometrics.

[0133] Optionally, the first judgment module includes: a first extraction unit, used to extract the initial received signal strength indicator (RSSI) sequence from the second static initial information; a filtering unit, used to perform a moving average filter on the initial RSSI sequence to obtain an intermediate RSSI sequence; a calculation unit, used to calculate the mean and standard deviation of the intermediate RSSI sequence; a construction unit, used to construct a baseline RSSI threshold for the static environment using the mean and the standard deviation; a collection unit, used to continue collecting real-time RSSI values ​​inside the vehicle in the SLE mode; and a first judgment unit, used to determine whether a target living being exists inside the vehicle based on the baseline RSSI threshold and the real-time RSSI values.

[0134] Optionally, the first determination unit includes: a determination subunit, used to determine whether the reference RSSI threshold and the real-time RSSI value meet the following relationship: ; This is the real-time RSSI value. The mean, The standard deviation, the benchmark RSSI threshold includes , If the criteria are met, it is confirmed that a living target is present inside the vehicle.

[0135] Optionally, the first judgment module includes: a first extraction unit, used to extract the Channel State Information (CSI) signal from the first static initial information and calculate the subcarrier energy of the CSI signal; a calculation unit, used to calculate the multipath energy entropy of all subcarrier energies; and a second judgment unit, used to determine whether there is a target living body inside the vehicle based on the multipath energy entropy.

[0136] Optionally, the second determination unit includes: a determination subunit, used to determine the material type of the interior material of the vehicle, wherein the material type is used to characterize the degree of energy reflection of the material surface; a search subunit, used to search for a correction coefficient matching the material type; an update subunit, used to update the energy entropy threshold based on the correction coefficient; a determination subunit, used to determine whether the multipath energy entropy is greater than the energy entropy threshold; and a determination subunit, used to determine that a target living body exists inside the vehicle if the multipath energy entropy is greater than the energy entropy threshold.

[0137] Optionally, the positioning module includes: a control unit for controlling the vehicle to collect the received power and CSI signal of the sampling points inside the vehicle in SLE mode; a first calculation unit for calculating the RSSI variance of the received power and extracting the ultra-low frequency component from the CSI signal, wherein the frequency range of the ultra-low frequency component corresponds to the body movement frequency of a living organism; a second calculation unit for calculating the signal periodicity index of the ultra-low frequency component; a first judgment unit for using the RSSI variance and the signal periodicity index to determine whether there is a target living body inside the vehicle; and a positioning unit for locating the living position of the target living body if it exists inside the vehicle.

[0138] Optionally, the first determination unit is further configured to: determine whether the RSSI variance is an abnormal abrupt change value based on a benchmark RSSI threshold, and determine whether the signal periodicity index is greater than a preset threshold; if the RSSI variance is an abnormal abrupt change value, determine that there is a moving living body in the vehicle; if the signal periodicity index is greater than the preset threshold, determine that there is a silent living body in the vehicle.

[0139] Optionally, the positioning unit is further configured to: if the target living body is a moving living body, control one node of the star-flash communication module as a transmitter and the other three nodes as receivers, acquire a first set of communication signals between the transmitter and the receiver, and perform triangulation positioning on the target living body based on the RSSI signal of the first set of communication signals to obtain a first living body position of the target living body, wherein the star-flash communication module includes at least four nodes; if the target living body is a stationary living body, control one node of the star-flash communication module as a transmitter and the other three nodes as receivers, acquire a second set of communication signals between the transmitter and the receiver, and perform triangulation positioning on the target living body based on the CSI signal of the second set of communication signals to obtain a second living body position of the target living body.

[0140] Optionally, the target feature information includes CSI phase difference sequence, multipath delay spectrum, and Doppler spectrum information. The extraction unit is further configured to: extract first energy information of the CSI phase difference sequence in a first frequency band and second energy information in a second frequency band; calculate the periodicity exponent and harmonic components of the CSI phase difference sequence; calculate the standard deviation and multipath reflection energy entropy of the multipath delay spectrum; and calculate the peak power and spectral entropy of the Doppler spectrum information; determine the first energy information as a first respiratory feature, the second energy information as a first heartbeat feature, the periodicity exponent as a second respiratory feature, the harmonic components as a second heartbeat feature, the standard deviation and the multipath reflection energy entropy as body shape features, and the peak power and the spectral entropy as motion features, wherein the biological features include physiological features, body shape features, and motion features, and the physiological features include heartbeat features and respiratory features.

[0141] Optionally, the identification unit is further configured to: for each target living organism, input the corresponding biometric features into a decision tree logic, and use the decision tree logic to identify the living organism type of the target living organism, wherein the living organism type includes: adult, child, pet; if the decision tree logic identification fails, input the biometric features into a pre-trained neural network model, and use the neural network model to output the living organism type of the target living organism.

[0142] Optionally, the device further includes: a detection module, configured to detect vehicle status information before the acquisition module calls the vehicle's StarSignal Communication module to acquire first static initial information inside the vehicle in SLB mode and second static initial information inside the vehicle in low-power SLE mode; a second judgment module, configured to determine whether the vehicle is in a preset state based on the status information; and a determination module, configured to determine, if the vehicle is in a preset state, to call the vehicle's StarSignal Communication module to acquire first static initial information inside the vehicle in SLB mode and second static initial information inside the vehicle in low-power SLE mode.

[0143] Optionally, the second determination module is further configured to: determine whether the vehicle is in a parked state based on the gear position and handbrake position; if the vehicle is in a parked state, determine whether the vehicle is in a turned-off state based on the power signal; if the vehicle is in a turned-off state, determine whether the vehicle is in a closed state based on the door lock position; if the vehicle is in a closed state, determine whether the vehicle is in a sealed state based on the air conditioning position and window position; if the vehicle is in a sealed state, determine that the vehicle is in a preset state, wherein the state information includes: gear position, handbrake position, power signal, door lock position, air conditioning position, and window position.

[0144] Optionally, the device further includes a notification module, configured to send an alarm message to the remote terminal of the vehicle and start the vehicle's air conditioning system if, after the identification module controls the star-flash communication module to identify the liveness type of the target live body in SLE mode, the live body type is a child and there is no adult present.

[0145] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0146] Example 3

[0147] Embodiments of the present invention also provide a storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0148] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0149] S1, the vehicle's Star Flash Communication Module is invoked to collect the first static initial information inside the vehicle in the basic SLB mode and the second static initial information inside the vehicle in the low power SLE mode.

[0150] S2, determine whether there is a target living being inside the vehicle based on the first static initial information and the second static initial information;

[0151] S3, if a target living body is present in the vehicle, control the Star Flash Communication Module to locate the living body's position in SLE mode;

[0152] S4, enhance the signal power of the starlight communication module, control the starlight communication module to start beamforming and focusing signal towards the living body location in SLB mode, and extract target feature information of the received signal; extract biometrics from the target feature information; use the biometrics to identify the living body type of the target living body.

[0153] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0154] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0155] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0156] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0157] S1, the vehicle's Star Flash Communication Module is invoked to collect the first static initial information inside the vehicle in the basic SLB mode and the second static initial information inside the vehicle in the low power SLE mode.

[0158] S2, determine whether there is a target living being inside the vehicle based on the first static initial information and the second static initial information;

[0159] S3, if a target living body is present in the vehicle, control the Star Flash Communication Module to locate the living body's position in SLE mode;

[0160] S4, enhance the signal power of the starlight communication module, control the starlight communication module to start beamforming and focusing signal towards the living body location in SLB mode, and extract target feature information of the received signal; extract biometrics from the target feature information; use the biometrics to identify the living body type of the target living body.

[0161] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0162] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0163] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0164] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0165] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for detecting the presence of living beings inside a vehicle, characterized in that, include: The vehicle's StarFlash Communication module is invoked to collect the first static initial information inside the vehicle in basic SLB mode and the second static initial information inside the vehicle in low-power SLE mode. Determine whether there is a living target inside the vehicle based on the first static initial information and the second static initial information; If a target living being is present inside the vehicle, the Star Flash Communication Module is controlled to locate the living being's position in SLE mode; The signal power of the star-flash communication module is enhanced, and the star-flash communication module is controlled to start beamforming and focusing signals toward the living body location in SLB mode, and target feature information of the received signal is extracted; biometric features are extracted from the target feature information; and the living body type of the target living body is identified using the biometric features. The process of controlling the star-flash communication module to locate the live body position of the target living being in SLE mode includes: controlling the vehicle to collect the received power and CSI signal of the sampling points inside the vehicle in SLE mode; calculating the RSSI variance of the received power and extracting the ultra-low frequency component from the CSI signal, wherein the frequency range of the ultra-low frequency component corresponds to the body movement frequency of the living organism; calculating the signal periodicity index of the ultra-low frequency component; using the RSSI variance and the signal periodicity index to determine whether there is a target living being inside the vehicle; if there is a target living being inside the vehicle, locating the live body position of the target living being; wherein using the RSSI variance and the signal periodicity index to determine whether there is a target living being inside the vehicle includes: determining whether the RSSI variance is an abnormally abrupt value based on a benchmark RSSI threshold, and determining whether the signal periodicity index is greater than a preset threshold; if the RSSI variance is an abnormally abrupt value, determining whether there is a target living being inside the vehicle. If a moving living being is present, and the periodicity exponent of the signal is greater than a preset threshold, a stationary living being is determined to exist within the vehicle. The location of the target living being includes: if the target living being is moving, controlling one node of the StarSignal communication module as a transmitter and the other three nodes as receivers, acquiring a first set of communication signals between the transmitter and the receivers, and performing triangulation on the target living being based on the RSSI signal of the first set of communication signals to obtain the first living position of the target living being, wherein the StarSignal communication module includes at least four nodes; if the target living being is stationary, controlling one node of the StarSignal communication module as a transmitter and the other three nodes as receivers, acquiring a second set of communication signals between the transmitter and the receivers, and performing triangulation on the target living being based on the CSI signal of the second set of communication signals to obtain the second living position of the target living being.

2. The method according to claim 1, characterized in that, Determining whether a target living being exists inside the vehicle based on the second static initial information includes: Extract the initial received signal strength indicator (RSSI) sequence from the second static initial information; The initial RSSI sequence is subjected to a moving average filter to obtain an intermediate RSSI sequence; Calculate the mean and standard deviation of the intermediate RSSI sequence; A baseline RSSI threshold for the static environment is constructed using the mean and the standard deviation. The real-time RSSI value inside the vehicle continues to be collected in the SLE mode; The presence of a target living being inside the vehicle is determined based on the baseline RSSI threshold and the real-time RSSI value.

3. The method according to claim 2, characterized in that, Determining whether a target living being exists inside the vehicle based on the baseline RSSI threshold and the real-time RSSI value includes: Determine whether the following relationship exists between the baseline RSSI threshold and the real-time RSSI value: ; This is the real-time RSSI value. The mean, The standard deviation, the benchmark RSSI threshold includes , ; If the conditions are met, it is confirmed that a living target is present inside the vehicle.

4. The method according to claim 1, characterized in that, Determining whether a target living being exists inside the vehicle based on the first static initial information includes: Extract the Channel State Information (CSI) signal from the first static initial information, and calculate the subcarrier energy of the CSI signal; Calculate the multipath energy entropy of all subcarrier energies; The presence of a target living being inside the vehicle is determined based on the multipath energy entropy.

5. The method according to claim 4, characterized in that, Determining whether a living target exists inside the vehicle based on the multipath energy entropy includes: The material type of the interior material of the vehicle is determined, wherein the material type is used to characterize the degree of energy reflection of the material surface; Find the correction factor that matches the material type; Update the energy entropy threshold based on the correction coefficient; Determine whether the multipath energy entropy is greater than the energy entropy threshold; If the multipath energy entropy is greater than the energy entropy threshold, it is determined that there is a target living being inside the vehicle.

6. The method according to claim 1, characterized in that, The target feature information includes CSI phase difference sequence, multipath delay spectrum, and Doppler spectrum information. Extracting biomarkers from the target feature information includes: Extract the first energy information of the CSI phase difference sequence in the first frequency band and the second energy information in the second frequency band, calculate the periodic exponent and harmonic components of the CSI phase difference sequence, calculate the standard deviation and multipath reflection energy entropy of the multipath delay spectrum, and calculate the peak power and spectral entropy of the Doppler spectrum information; The first energy information is determined as the first respiratory feature, the second energy information is determined as the first heartbeat feature, the periodicity index is determined as the second respiratory feature, the harmonic component is determined as the second heartbeat feature, the standard deviation and the multipath reflection energy entropy are determined as body shape features, and the peak power and the spectral entropy are determined as motion features. The biological features include physiological features, body shape features, and motion features, and the physiological features include heartbeat features and respiratory features.

7. The method according to claim 1, characterized in that, The biometric identification of the target living organism's living type includes: For each target living organism, the corresponding biometric features are input into a decision tree logic, and the decision tree logic is used to identify the living organism type of the target living organism, wherein the living organism type includes: adult, child, and pet; If the decision tree logic recognition fails, the biometric features are input into a pre-trained neural network model, and the neural network model outputs the liveness type of the target live organism.

8. The method according to claim 1, characterized in that, Before invoking the vehicle's StarFlash communication module to collect the first static initial information inside the vehicle in SLB mode and the second static initial information inside the vehicle in low-power SLE mode, the method further includes: Detect vehicle status information; Determine whether the vehicle is in a preset state based on the status information; If the vehicle is in a preset state, the vehicle's StarFlash communication module is invoked to collect the first static initial information inside the vehicle in SLB mode and the second static initial information inside the vehicle in low-power SLE mode.

9. The method according to claim 8, characterized in that, Determining whether the vehicle is in a preset state based on the status information includes: Determine whether the vehicle is in a parked state based on the gear position and handbrake status; If the vehicle is in a parked state, determine whether the vehicle is in a turned-off state based on the power signal; If the vehicle is turned off, determine whether the vehicle is in a closed state based on the door lock status; If the vehicle is in a closed state, determine whether the vehicle is in a sealed state based on the air conditioning status and the window status. If the vehicle is in a sealed state, the vehicle is determined to be in a preset state, and the state information includes: gear position, handbrake position, power signal, door lock position, air conditioning position, and window position.

10. The method according to claim 1, characterized in that, After controlling the starlight communication module to identify the liveness type of the target liveness subject in SLE mode, the method further includes: If the living subject is a child and no adult is present, an alarm message is sent to the remote terminal of the vehicle, and the vehicle's air conditioning system is activated.

11. A device for detecting the presence of living beings inside a vehicle, characterized in that, include: The acquisition module is used to call the vehicle's Star Flash Communication module to acquire the first static initial information inside the vehicle in the basic SLB mode and the second static initial information inside the vehicle in the low power SLE mode. The first judgment module is used to determine whether there is a target living body inside the vehicle based on the first static initial information and the second static initial information. The positioning module is used to control the Star Flash Communication Module to locate the live position of the target living body in SLE mode if a target living body is present in the vehicle. The identification module includes: a processing unit for enhancing the signal power of the star-flash communication module, controlling the star-flash communication module to initiate beamforming focusing signals toward the live body location in SLB mode, and extracting target feature information from the received signals; an extraction unit for extracting biometrics from the target feature information; and an identification unit for identifying the live body type of the target live body using the biometrics. The positioning module includes: a control unit for controlling the vehicle to collect the received power and CSI signal at sampling points inside the vehicle in SLE mode; a first calculation unit for calculating the RSSI variance of the received power and extracting the ultra-low frequency component from the CSI signal, wherein the frequency range of the ultra-low frequency component corresponds to the body movement frequency of a living organism; a second calculation unit for calculating the signal periodicity index of the ultra-low frequency component; a first judgment unit for determining whether a target living body exists inside the vehicle using the RSSI variance and the signal periodicity index; and a positioning unit for locating the living body location if a target living body exists inside the vehicle. The first judgment unit is further configured to: determine whether the RSSI variance is an abnormal abrupt change value based on a benchmark RSSI threshold, and determine whether the signal periodicity index is greater than a preset threshold; if the RSSI variance is an abnormal abrupt change value, determine the vehicle... If a moving living being is present in the vehicle, and the periodicity exponent of the signal is greater than a preset threshold, a stationary living being is determined to be present in the vehicle. The positioning unit is further configured to: if the target living being is moving, control one node of the star-flash communication module as a transmitter and the other three nodes as receivers, acquire a first set of communication signals between the transmitter and the receivers, and perform triangulation on the target living being based on the RSSI signal of the first set of communication signals to obtain a first living being position, wherein the star-flash communication module includes at least four nodes; if the target living being is stationary, control one node of the star-flash communication module as a transmitter and the other three nodes as receivers, acquire a second set of communication signals between the transmitter and the receivers, and perform triangulation on the target living being based on the CSI signal of the second set of communication signals to obtain a second living being position.

12. A storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is configured to execute the method described in any one of claims 1 to 10 when it is run.

13. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method as described in any one of claims 1 to 10.

Images