Life body detection method and device

Abstract

The embodiment of the invention provides a life body detection method and device, and the method comprises the steps: determining a first detection result according to a time domain feature and a frequency domain feature corresponding to an echo signal of a first ultrasonic signal, and the first detection result is used for indicating whether a life body exists in a vehicle or not. If the first detection result indicates that the life body exists in the vehicle, a second detection result is determined according to the phase feature corresponding to the echo signal of the second ultrasonic signal, the second detection result is used for indicating whether the life body exists in the vehicle, and the second ultrasonic signal is different from the first ultrasonic signal. Therefore, according to the life body detection method, preliminary detection can be carried out based on the first ultrasonic signal, life body detection with higher precision is further carried out based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal when the preliminary detection result is that the life body exists in the vehicle, and the accuracy of life body examination can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of life body detection, and in particular to a life body detection method and device. Background Art

[0002] With the development of economy and technology, vehicles are used more and more frequently. Studies have shown that at a temperature of 35 degrees Celsius (℃), if a vehicle is exposed to sunlight for 20 minutes, the temperature inside the vehicle will exceed the critical level that the human body can withstand (i.e. 41℃). If a child or pet is left alone in the car at this time, they will face the risk of severe heatstroke or even death because they cannot open the doors and windows, call for help, etc. Therefore, vehicles are required to have "child presence detection" technology to detect whether there are children in the vehicle, thereby reducing the risk of accidents caused by children being left in the car. Summary of the invention

[0003] The embodiments of the present application provide a method and device for detecting a living being, which can improve the accuracy of detecting a living being.

[0004] In a first aspect, the present application provides a method for detecting a life form, which can be applied to a first device, a chip in the first device, or a logic module or software that can realize all or part of the functions of the first device. The first device is used as an example for description below. The signal transmission method includes: the first device determines a first detection result based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, and the first detection result is used to indicate whether there is a life form in the vehicle. If the first detection result indicates that there is a life form in the vehicle, the first device determines a second detection result based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal, and the second detection result is used to indicate whether there is a life form in the vehicle, and the second ultrasonic signal is different from the first ultrasonic signal.

[0005] It can be seen that this method performs preliminary detection based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal. When the preliminary detection results indicate the presence of a living organism in the vehicle, it further performs more accurate life organism detection based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal, thereby improving the accuracy of life organism detection.

[0006] In an optional embodiment, before the first device determines the first detection result based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, the method also includes: the first device sends the first ultrasonic signal; the first device receives the echo signal of the first ultrasonic signal.

[0007] Optionally, the first device receives an echo signal of a first ultrasonic signal, including: the first device receives a first signal, the first signal including the echo signal of the first ultrasonic signal; the first device filters the first signal using a sliding window to obtain a second signal having a signal strength greater than a first value, the second signal including the echo signal of the first ultrasonic signal; the first device processes the second signal using a matched filtering algorithm to determine a time when the echo signal of the first ultrasonic signal is received; the first device determines the echo signal of the first ultrasonic signal based on the time when the echo signal of the first ultrasonic signal is received.

[0008] Optionally, the time domain feature corresponding to the echo signal of the first ultrasonic signal is the matched filter sequence result obtained by the first device using the matched filter algorithm to process the second signal. The matched filter sequence result reflects the time when the echo signal of the first ultrasonic signal reaches the first device through multiple paths in the vehicle, and to a certain extent reflects the structure of the vehicle. Compared with the case where there is a living body in the car, the echo signal in the case where there is no living body in the car lacks the path of reflection through the living body, so there are differences between the matched filter sequence results obtained for the two cases of there being a living body in the car and there being no living body in the car. Therefore, using the matched filter sequence result as the time domain feature corresponding to the echo signal of the first ultrasonic signal is beneficial to detecting whether there is a living body in the vehicle.

[0009] The frequency domain feature corresponding to the echo signal of the first ultrasonic signal is the spectrum sequence obtained by the first device performing fast Fourier transform on the echo signal of the first ultrasonic signal. It is understandable that if there is movement in the car, the echo signal will produce a frequency shift according to the Doppler effect; then, there is a difference between the spectrum sequences obtained for the two cases where there is movement in the car and there is no movement in the car. Therefore, based on the spectrum sequence, it is possible to determine whether there is movement in the car, which is conducive to detecting whether there is a living organism in the vehicle.

[0010] In an optional embodiment, the first device determines the first detection result according to the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, including: the first device determines the first detection result according to the first model and the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal. The first model can be a machine learning model, through which the implicit features in the echo signal of the first ultrasonic signal can be captured, and the difference in the time domain characteristics corresponding to the echo signal of the first ultrasonic signal can be identified when there is a living body in the car and when there is no living body in the car, and the difference in the frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal can be identified when there is movement in the car and when there is no movement in the car, which is conducive to improving the accuracy of detecting whether there is a living body in the vehicle.

[0011] In an optional embodiment, the first ultrasonic signal is a frequency modulated continuous wave signal.

[0012] In an optional embodiment, before the first device determines the second detection result according to the phase characteristics corresponding to the echo signal of the second ultrasonic signal, the method also includes: the first device sends the second ultrasonic signal; and the second device receives the echo signal of the second ultrasonic signal.

[0013] In an optional embodiment, the first ultrasonic signal is sent by the first device through a speaker, and the echo signal of the first ultrasonic signal is received by the first device through a microphone. And / or, the second ultrasonic signal is sent by the first device through a speaker, and the echo signal of the second ultrasonic signal is received by the first device through a microphone. It can be seen that the first device can generate ultrasonic signals and collect echo signals of ultrasonic signals through ordinary audio equipment, without relying on special ultrasonic devices, millimeter wave radars and other additional devices, which is conducive to making the life detection method applicable to all scenarios with ordinary audio equipment, and can also reduce the cost of life detection.

[0014] In an optional implementation, the second ultrasonic signal is a single-frequency continuous sine wave signal.

[0015] In an optional embodiment, the second ultrasonic signal is a signal obtained by superimposing multiple continuous sinusoidal signals of different frequencies. The first device determines the second detection result according to the phase feature corresponding to the echo signal of the second ultrasonic signal, including: the first device determines the second detection result according to the phase feature corresponding to the echo signal of each continuous sinusoidal signal in the multiple continuous sinusoidal signals. It can be seen that the first device can determine the second detection result based on multiple phase features to further improve the accuracy of the second detection result.

[0016] In an optional embodiment, the first device receives the echo signal of the second ultrasonic signal, including: the first device receives the third signal, and the third signal includes the echo signal of the second ultrasonic signal. The method also includes: the first device performs filtering processing on the third signal to obtain a fourth signal; the fourth signal is an echo signal corresponding to the single-frequency continuous sine wave signal in the second ultrasonic signal. The first device performs two-way orthogonal modulation on the fourth signal to obtain two fifth signals. The first device performs low-pass filtering, sampling processing, window processing, averaging processing and smoothing processing on each of the two fifth signals in turn to obtain two sixth signals. The first device divides the two sixth signals bit by bit and uses the inverse tangent function to process the division result to obtain the phase characteristics corresponding to the fourth signal.

[0017] In an optional implementation, the first device determines the first detection result according to the phase feature corresponding to the echo signal of the second ultrasonic signal, including: the first device determines the second detection result according to the phase feature corresponding to the echo signal of the second ultrasonic signal and the second model. The first model may be a machine learning model, through which the implicit features in the echo signal of the second ultrasonic signal can be captured, which is conducive to improving the accuracy of detecting whether there is a life form in the vehicle.

[0018] In an optional embodiment, the method further includes: if the first detection result indicates that there is no life in the vehicle and the confidence of the first detection result is less than a second value, the first device performs an operation of determining the second detection result according to the phase feature corresponding to the echo signal of the second ultrasonic signal. It can be seen that if the first detection result indicates that there is no life in the vehicle and the confidence of the first detection result is low, the first device can further perform more accurate life detection based on the phase feature corresponding to the echo signal of the second ultrasonic signal, which can improve the accuracy of life detection.

[0019] In an optional embodiment, after the first device determines the second detection result according to the phase feature corresponding to the echo signal of the second ultrasonic signal, the method further includes: the first device outputs second information, and the second information is used to prompt the user of the second detection result. Through this embodiment, the first device can inform the user of the second detection result. It is beneficial to enable the user to be reminded to return to the vehicle in time when the second detection result indicates that there is a living being in the vehicle, thereby reducing the risk of children or pets being left alone in the vehicle and facing severe heatstroke or even death.

[0020] Optionally, if the first detection result is different from the second detection result, the confidence of the second information is less than the third value. If the first detection result is the same as the second detection result, the confidence of the second information is greater than the third value.

[0021] Optionally, the method also includes: if the user's feedback behavior for the second information does not match the second detection result, the first device updates the first model based on the echo signal of the first ultrasonic signal, and updates the second model based on the echo signal of the second ultrasonic signal. If the user's feedback behavior for the second information matches the second detection result and the confidence of the second information is less than a third value, the first device updates the first model based on the echo signal of the first ultrasonic signal. Among them, the first model is used by the first device to determine the first detection result, and the second model is used by the second device to determine the second detection result. This implementation method timely updates the model based on user feedback, which is conducive to reducing the impact of equipment aging on the accuracy of life detection, so that the life detection method provided in the embodiment of the present application can be used for a long time and maintain a high accuracy, thereby ensuring user experience for a long time.

[0022] In an optional embodiment, the method further includes: if the first detection result is different from the second detection result, the first device updates the first model based on the echo signal of the first ultrasonic signal, and the first model is used by the first device to determine the first detection result. Since the confidence of the second detection result is higher than that of the first detection result, updating the first model by comparing the first detection result and the second detection result is conducive to reducing the impact of equipment aging on the accuracy of life detection, so that the life detection method provided in the embodiment of the present application can be used for a long time and maintain a high accuracy, thereby ensuring the user experience for a long time.

[0023] In an optional embodiment, the method further includes: if the first detection result indicates that there is no life form in the vehicle and the confidence of the first detection result is greater than a second value, the first device outputs first information, and the first information is used to prompt the user that there is no life form in the vehicle. Since there is no life form and no large foreign objects in the vehicle, the first device can more accurately detect the absence of life form in the vehicle based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, and obtain the first detection result indicating that there is no life form in the vehicle. Therefore, when the first detection result indicates that there is no life form in the vehicle and the confidence of the first detection result is high, the first device may no longer perform further detection based on the second ultrasonic signal, but directly inform the user of the detection result that there is no life form in the vehicle, thereby achieving rapid detection when there is no life form in the vehicle.

[0024] Optionally, the method further includes: if the user's feedback behavior for the first information does not match the first detection result, the first device updates the first model based on the echo signal of the first ultrasonic signal, and the first model is used by the first device to determine the first detection result. This implementation method timely updates the first model based on user feedback, which is conducive to reducing the impact of device aging on the accuracy of life detection, so that the life detection method provided in the embodiment of the present application can be used for a long time and maintain a high accuracy, thereby ensuring the user experience for a long time.

[0025] In a second aspect, an embodiment of the present application provides a device, the device comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to make the device execute: determine a first detection result based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, the first detection result is used to indicate whether there is a life form in the vehicle. If the first detection result indicates that there is a life form in the vehicle, determine a second detection result based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal, the second detection result is used to indicate whether there is a life form in the vehicle, and the second ultrasonic signal is different from the first ultrasonic signal.

[0026] In an optional embodiment, one or more processors are also used to call the computer instructions to cause the device to execute: sending a first ultrasonic signal and receiving an echo signal of the first ultrasonic signal before determining a first detection result based on time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal.

[0027] Optionally, the device receives an echo signal of a first ultrasonic signal, including: receiving a first signal, the first signal including the echo signal of the first ultrasonic signal; filtering the first signal using a sliding window to obtain a second signal having a signal strength greater than a first value, the second signal including the echo signal of the first ultrasonic signal; processing the second signal using a matched filtering algorithm to determine a time when the echo signal of the first ultrasonic signal is received; and determining the echo signal of the first ultrasonic signal based on the time when the echo signal of the first ultrasonic signal is received.

[0028] In an optional embodiment, the device determines the first detection result based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, including: determining the first detection result based on the first model and the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal.

[0029] In an optional embodiment, the first ultrasonic signal is a frequency modulated continuous wave signal.

[0030] In an optional embodiment, one or more processors are also used to call the computer instructions to cause the device to execute: before determining the second detection result based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal, sending a second ultrasonic signal and receiving the echo signal of the second ultrasonic signal.

[0031] In an optional embodiment, the first ultrasonic signal is sent by the device through a speaker, and the echo signal of the first ultrasonic signal is received by the device through a microphone. And / or, the second ultrasonic signal is sent by the device through a speaker, and the echo signal of the second ultrasonic signal is received by the device through a microphone.

[0032] In an optional implementation, the second ultrasonic signal is a single-frequency continuous sine wave signal.

[0033] In an optional embodiment, the second ultrasonic signal is a signal obtained by superimposing a plurality of continuous sinusoidal signals of different frequencies. The device determines the second detection result according to the phase feature corresponding to the echo signal of the second ultrasonic signal, including: determining the second detection result according to the phase feature corresponding to the echo signal of each continuous sinusoidal signal in the plurality of continuous sinusoidal signals.

[0034] In an optional embodiment, the device receives an echo signal of a second ultrasonic signal, including: receiving a third signal, the third signal including the echo signal of the second ultrasonic signal. One or more processors are also used to call the computer instruction so that the device executes: filtering the third signal to obtain a fourth signal; the fourth signal is an echo signal corresponding to a single-frequency continuous sinusoidal wave signal in the second ultrasonic signal. Dual-channel orthogonal modulation is performed on the fourth signal to obtain two fifth signals. Each of the two fifth signals is subjected to low-pass filtering, sampling processing, window processing, averaging processing and smoothing processing in turn to obtain two sixth signals. The two sixth signals are divided bit by bit and the division result is processed using an inverse tangent function to obtain a phase feature corresponding to the fourth signal.

[0035] In an optional embodiment, the device determines the first detection result according to the phase characteristics corresponding to the echo signal of the second ultrasonic signal, including: determining the second detection result according to the phase characteristics corresponding to the echo signal of the second ultrasonic signal and the second model.

[0036] In an optional embodiment, one or more processors are also used to call the computer instructions to cause the device to execute: if the first detection result indicates that there is no living organism in the vehicle and the confidence level of the first detection result is less than a second value, execute an operation of determining a second detection result based on a phase feature corresponding to an echo signal of a second ultrasonic signal.

[0037] In an optional embodiment, one or more processors are also used to call the computer instructions to cause the device to execute: after determining the second detection result based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal, output second information, and the second information is used to prompt the user of the second detection result.

[0038] Optionally, if the first detection result is different from the second detection result, the confidence of the second information is less than the third value. If the first detection result is the same as the second detection result, the confidence of the second information is greater than the third value.

[0039] Optionally, one or more processors are also used to call the computer instructions to cause the device to execute: if the user's feedback behavior for the second information does not match the second detection result, update the first model based on the echo signal of the first ultrasonic signal, and update the second model based on the echo signal of the second ultrasonic signal. If the user's feedback behavior for the second information matches the second detection result and the confidence of the second information is less than a third value, update the first model based on the echo signal of the first ultrasonic signal. The first model is used to determine the first detection result, and the second model is used to determine the second detection result.

[0040] In an optional embodiment, one or more processors are also used to call the computer instructions to cause the device to execute: if the first detection result is different from the second detection result, update the first model based on the echo signal of the first ultrasonic signal, and the first model is used to determine the first detection result.

[0041] In an optional embodiment, one or more processors are also used to call the computer instruction to cause the device to execute: if the first detection result indicates that there is no living organism in the vehicle and the confidence level of the first detection result is greater than a second value, output first information, and the first information is used to prompt the user that there is no living organism in the vehicle.

[0042] Optionally, one or more processors are also used to call the computer instructions to cause the device to execute: if the user's feedback behavior in response to the first information does not match the first detection result, update the first model based on the echo signal of the first ultrasonic signal, and the first model is used to determine the first detection result.

[0043] In the third aspect, an embodiment of the present application provides a chip system, which can be applied to the device described in the second aspect, and the chip system includes one or more processors, which are used to call computer instructions so that the device executes the method described in the first aspect and any possible implementation method of the first aspect.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed, the method described in the first aspect and any possible implementation manner in the first aspect is implemented.

[0045] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising: a computer program code, which, when executed in parallel, implements the method described in the first aspect and any possible implementation manner in the first aspect.

[0046] It is understandable that the device provided in the second aspect, the chip system provided in the third aspect, the computer-readable storage medium provided in the fourth aspect, and the computer program product provided in the fifth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1a It is a schematic diagram of a system architecture provided by an embodiment of the present application;

[0048] Figure 1b is a schematic diagram of a vehicle scenario provided in an embodiment of the present application;

[0049] Figure 2 It is a flow chart of a method for detecting a living being provided in an embodiment of the present application;

[0050] Figure 3 is a schematic diagram of a matching filtering algorithm provided in an embodiment of the present application;

[0051] Figure 4 is a schematic diagram of a phase sequence provided in an embodiment of the present application;

[0052] Figure 5 is a schematic diagram of a spectrum sequence provided in an embodiment of the present application;

[0053] Figure 6 is a schematic diagram of a device provided in an embodiment of the present application;

[0054] Figure 7 is a schematic diagram of another method for detecting life forms provided in an embodiment of the present application;

[0055] Figure 8 is a schematic diagram of another method for detecting life forms provided in an embodiment of the present application;

[0056] Fig. 9 is a schematic diagram of a functional unit and a physical unit provided in an embodiment of the present application;

[0057] Fig.10 It is a schematic diagram of another device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The technical solutions in the embodiments of the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0059] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0060] First, in order to better understand the life detection method disclosed in the embodiment of the present application, the applicable scenarios and system architecture of the embodiment of the present application are described.

[0061] The embodiments of the present application can be applied to scenes in closed spaces, such as scenes in vehicles with closed windows. The embodiments of the present application can also be applied to scenes in semi-enclosed spaces, such as scenes in vehicles with open windows. The embodiments of the present application can also be applied to scenes in open spaces, such as scenes in open spaces such as indoors and outdoors, and parking lots. For ease of explanation, the following text uses the scene of a vehicle as an example for explanation, and the application of the embodiments of the present application to other scenes is similar and will not be repeated.

[0062] The embodiment of the present application provides a system architecture, which includes a first device, and the first device can be used to execute the life detection method provided by the embodiment of the present application. Figure 1a As shown, the system architecture may further include an electronic device, and the first device may send the life detection result to the electronic device to inform the user. Figure 1b As shown, the embodiment of the present application can be applied to a vehicle scenario. In this scenario, the first device can be a vehicle, and the first device can also be a cockpit device in the vehicle. The first device can detect whether there is a living being in the vehicle; in addition, the first device can also send the detection result of whether there is a living being in the vehicle to the electronic device of the user (for example, the driver or a third party). In this way, the first device can promptly remind the user to return to the vehicle when the presence of a living being is detected in the vehicle, which is conducive to reducing the risk of accidents caused by living beings such as children or pets being left in the vehicle.

[0063] The electronic device may also be referred to as a terminal device, user equipment (UE), terminal, access terminal, remote terminal, mobile device, user terminal, user agent or user device. The electronic device in the embodiment of the present application may be a handheld device, a vehicle-mounted device, a wearable device, a computing device, etc. with a wireless communication function. For example, the electronic device may be a smart phone, a smart watch, a tablet computer (Pad), a personal digital assistant (PDA) computer, a tablet computer, a handheld device (handset), a laptop computer, a personal computer (PC), etc.

[0064] The life form detection method provided in the embodiments of the present application is described below in conjunction with the accompanying drawings.

[0065] See also Figure 2 , Figure 2 This is a flow chart of a method for detecting a life form provided in an embodiment of the present application. The diagram takes the first device as an example to illustrate the corresponding method, but the present application does not limit the illustrated execution subject. For example, the first device in the figure may also be a chip or chip system or processor that supports the first device to implement the corresponding method, or a logic module or software that can implement all or part of the functions of the first device. The method for detecting a life form includes the following steps:

[0066] S101. A first device sends a first ultrasonic signal.

[0067] In an optional embodiment, the first ultrasonic signal may be a frequency modulated continuous wave signal with strong autocorrelation, for example, the first ultrasonic signal may be a single pulse signal such as a chirp sequence or a ZC (Zadoff-Chu) sequence. A frequency modulated continuous wave signal with strong autocorrelation has the following characteristics: the autocorrelation result of the frequency modulated continuous wave signal has a prominent peak value and the side lobe attenuation is obvious. Therefore, using a frequency modulated continuous wave signal with strong autocorrelation as the first ultrasonic signal is beneficial for the first device to subsequently accurately determine the time when the echo signal obtained by the reflection of the first ultrasonic signal reaches the first device through calculation, which is beneficial for the first device to extract the echo signal of the first ultrasonic signal. Using a frequency modulated continuous wave signal with strong autocorrelation as the first ultrasonic signal is also beneficial for reducing multipath interference in the process of life detection and improving the signal-to-noise ratio.

[0068] In addition, since the longer the duration of the frequency modulated continuous wave signal, the higher the resolution of the displacement distance; the shorter duration of the frequency modulated continuous wave signal is conducive to reducing the delay and the amount of calculation; then, in the scenario where the frequency modulated continuous wave signal is used as the first ultrasonic signal, the duration of the first ultrasonic signal can be set based on the detection accuracy, delay and calculation requirements. For example, the duration of the first ultrasonic signal can be set within the range of 50 milliseconds (ms) to 100 ms, and the first ultrasonic signal within this range is conducive to balancing the detection accuracy with the delay and the amount of calculation. Among them, the duration of the first ultrasonic signal is greater than or equal to 50 ms, which is conducive to ensuring that the first device has a higher detection accuracy when performing life body detection based on the first ultrasonic signal, and the duration of the first ultrasonic signal is less than or equal to 100 ms, which is conducive to making the duration of the first ultrasonic signal shorter, so as to enable the first device to perform rapid detection based on the first ultrasonic signal, and then quickly obtain the first detection result, and also help to reduce the delay and the amount of calculation. In addition, in the embodiment of the present application, the duration of the first ultrasonic signal can also be set to be higher than 100 ms, without restriction.

[0069] In an optional embodiment, the first ultrasonic signal may be an audio signal played by the first device through a speaker. In this case, the frequency band of the first ultrasonic signal needs to match the playback capability of the speaker. For example, for a speaker that can play an audio signal with a maximum frequency of 24 kilohertz (kHz), the frequency band of the first ultrasonic signal may be set to 17kHz to 23kHz, wherein the frequency of the first ultrasonic signal being greater than or equal to 17kHz is conducive to ensuring that most people cannot hear the first ultrasonic signal, and the frequency of the first ultrasonic signal being less than or equal to 23kHz is conducive to reducing the noise generated by the speaker playing high-frequency signals.

[0070] In an optional embodiment, Figure 2 The life form detection method shown can be executed by the first device when / after determining that the user (e.g., the driver) leaves the vehicle. With this implementation, the first device does not need to execute the life form detection method all the time, which can save the power consumption of the first device. For example, when the driver is in the vehicle, the first device does not need to detect whether there is a life form in the vehicle, which saves the power consumption of the first device.

[0071] Optionally, the first device can determine that the user has left the vehicle by acquiring one or more of the following events: parking events, door opening and closing events, car locking events, and Bluetooth connection loss events of electronic devices connected to the vehicle. The aforementioned events can be acquired or detected by the first device through sensors of the vehicle's doors, windows, seats, and / or Bluetooth devices, visual devices (e.g., cameras), etc. For example, the door opening and closing events can be detected by the first device through sensors corresponding to the vehicle's doors and windows, the car locking events can be detected by the first device through the vehicle's door locks, and the Bluetooth connection loss events can be acquired by the first device from a Bluetooth device in the vehicle. In addition, in addition to the aforementioned events, the first device can also determine that the user has left the vehicle by acquiring or detecting other events that can characterize the user leaving the vehicle, without limitation.

[0072] S102: The first device receives an echo signal of a first ultrasonic signal.

[0073] In an optional embodiment, the first device receives an echo signal of a first ultrasonic signal, which may include: the first device receives a first signal, the first signal includes the echo signal of the first ultrasonic signal; the first device filters the first signal using a sliding window to obtain a second signal with a signal strength greater than a first value, the second signal including the echo signal of the first ultrasonic signal; the first device processes the second signal using a matched filtering algorithm to determine the time when the echo signal of the first ultrasonic signal is received; the first device determines the echo signal of the first ultrasonic signal based on the time.

[0074] It is understandable that in the process of the first device using a sliding window to filter the first signal, if the signal strength obtained by the first device based on the sliding window filtering at a certain moment is greater than the first value, it can be considered that the echo signal of the first ultrasonic signal is detected in the sliding window at that moment, that is, the signal in the sliding window at that moment includes the echo signal of the first ultrasonic signal. Therefore, the signal strength of the second signal is greater than the first value, and it can be considered that the first device has detected the echo signal of the first ultrasonic signal in the sliding window for obtaining the second signal, that is, the second signal includes the echo signal of the first ultrasonic signal. Optionally, the length of the sliding window (which can be referred to as: sliding window) used by the first device can be pre-set, and the set sliding window length is greater than the duration of the first ultrasonic signal.

[0075] Optionally, the operation of the first device filtering the first signal using a sliding window may be implemented by the first device using a bandpass filter that matches the frequency band of the first ultrasonic signal. For example, if the frequency band of the first ultrasonic signal is 17kHz to 23kHz, then the first device may perform the operation of filtering the first signal using a sliding window through a bandpass filter with a passband of 17kHz to 23kHz.

[0076] It is understandable that the first device uses a matched filtering algorithm to process the second signal, that is, the first device can use a matched filtering algorithm within the sliding window in which the echo signal of the first ultrasonic signal is detected, so as to detect the exact time when the echo signal of the first ultrasonic signal reaches the first device, thereby facilitating the first device to extract the echo signal of the first ultrasonic signal. Figure 3 The first device uses a matched filtering algorithm to process the second signal, which may include: the first device performs time deconvolution processing on the first ultrasonic signal, and convolves the conjugate signal corresponding to the first ultrasonic signal after the time deconvolution processing with the second signal.

[0077] Optionally, the first signal may be an audio signal recorded by the first device through a microphone. This embodiment may be applied to a scenario in which the first ultrasonic signal is an audio signal played by the first device through a speaker, and the recording function of the speaker may be turned on before the speaker plays the first ultrasonic signal. It can be seen that the first device may generate the first ultrasonic signal and collect the echo signal of the first ultrasonic signal through an ordinary audio device, without relying on additional devices such as dedicated ultrasonic devices and millimeter-wave radars, which is conducive to making the life detection method provided in the embodiment of the present application applicable to all scenarios with ordinary audio devices, and can also reduce the cost of life detection.

[0078] S103. The first device determines a first detection result according to time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, where the first detection result is used to indicate whether there is a living being in the vehicle.

[0079] Optionally, the time domain feature corresponding to the echo signal of the first ultrasonic signal can be a matched filtering sequence result obtained by the first device using a matched filtering algorithm to process the second signal, which can reflect the similarity between the echo signal of the first ultrasonic signal and the first ultrasonic signal. It can be understood that the echo signal is obtained by superimposing the echoes of multiple paths obtained by the signal being reflected at different positions in the car. Since the length of each path is different (for example, some paths are signals transmitted from the transmitting end to the receiving end in a straight line, and some paths are signals that are reflected by windows, seats, or people in the car and then transmitted to the receiving end), the time for the echoes of different paths to arrive at the receiving end is also different. Therefore, the matched filtering sequence result obtained by matching the echo signal of the first ultrasonic signal using a matched filtering algorithm to match filter the echo signal of the first ultrasonic signal reflects the time when the echo signal of the first ultrasonic signal reaches the first device through multiple paths, and to a certain extent reflects the structure of the car. Compared with the case where there is a living body in the car, when there is no living body in the car, the echo signal lacks the path of reflection by the living body, so there is a difference between the matched filtering sequence results obtained for the two cases of having a living body in the car and having no living body in the car. Therefore, the matched filtering sequence result can be used as the time domain feature corresponding to the echo signal of the first ultrasonic signal to detect whether there is a life form in the vehicle. For the specific description of the second signal and the matched filtering algorithm, please refer to the above related description, which will not be repeated here.

[0080] In addition, the frequency domain feature corresponding to the echo signal of the first ultrasonic signal can be a spectrum sequence obtained by the first device performing a fast Fourier transform on the echo signal of the first ultrasonic signal. It is understandable that if there is no movement in the car, the spectrum of the echo signal is relatively fixed (if an audio device is used to play and collect ultrasonic signals, the spectrum of the echo signal is only affected by the inherent hardware characteristics of the audio device), but if there is movement in the car, according to the Doppler effect, the echo signal will produce a frequency shift; then, there is a difference between the spectrum sequences obtained for the two cases of movement in the car and no movement in the car. Therefore, based on the spectrum sequence, it is possible to determine whether there is movement in the car, which is beneficial for detecting whether there is a living organism in the vehicle.

[0081] In an optional embodiment, the first device determines the first detection result according to the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, which may include: the first device determines the first detection result according to the first model and the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal. Exemplarily, the first device can perform binary classification based on the first model to determine whether there is a life form in the vehicle, and the binary classification includes two categories: there is a life form in the vehicle and there is no life form in the vehicle. Among them, the first model can be a machine learning model trained based on the time domain characteristics and frequency domain characteristics corresponding to the ultrasonic signal (such as a frequency modulated continuous wave signal with strong autocorrelation). For example, the first model can be a K-nearest neighbor (KNN), a support vector machine (SVM), a neural network or other models.

[0082] It is understandable that, in the case where the matched filtering sequence result obtained by the first device using the matched filtering algorithm to process the second signal is used as the time domain feature corresponding to the echo signal of the first ultrasonic signal, since the echo signal of the first ultrasonic signal is obtained by superimposing the signals after the first ultrasonic signal is reflected through more than one path, the matched filtering sequence result is not intuitive, and the difference between the matched filtering sequence results obtained for the two situations of there being a living body in the car and there being no living body in the car is difficult to distinguish through observation or regularized algorithms. In addition, in the case where the spectrum sequence obtained by the first device performing fast Fourier transform on the echo signal of the first ultrasonic signal is used as the frequency domain feature corresponding to the echo signal of the first ultrasonic signal, the difference between the spectrum sequences obtained for the two situations of there being movement in the car and there being no movement in the car is not intuitive and is affected by hardware. Then, this implementation can capture the implicit features in the echo signal of the first ultrasonic signal through a machine learning model, which is conducive to the detection of living bodies.

[0083] S104: The first device determines whether the first detection result indicates that a life form exists in the vehicle. If the first detection result indicates that a life form exists in the vehicle, steps S105 to S107 are executed.

[0084] In an optional embodiment, if the first detection result indicates that there is no life in the vehicle and the confidence of the first detection result is less than the second value, the first device may also perform steps S105 to S107. The second value may be predefined. Exemplarily, when the confidence of the first detection result is less than the second value, it can be considered that the confidence of the first detection result is low, then the first device can detect whether there is a life in the vehicle again based on the second ultrasonic signal, thereby improving the accuracy of life detection. When the confidence of the first detection result is greater than the second value, it can be considered that the confidence of the first detection result is high, and the first device may not detect whether there is a life in the vehicle again based on the second ultrasonic signal. Optionally, for the case where the first detection result is determined by the first device according to the first model and the time domain features and frequency domain features corresponding to the echo signal of the first ultrasonic signal, the confidence of the first detection result can be expressed as the "score" of the first detection result output by the first model. Since the first model can be a machine learning model, it will also output the "score" of the first detection result while outputting the first detection result, then the "score" of the first detection result can be used to characterize the confidence of the first detection result.

[0085] Understandably, the first device can detect whether there is a moving (approximately 2 cm or more) life form based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, but the detection accuracy is easily affected by large foreign objects (such as large cartons, packages, etc.), that is, in the case where there is no life form in the vehicle but there is a large foreign object, the first device may obtain the first detection result based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, which may also indicate the presence of a life form in the vehicle. Therefore, when the first detection result indicates the presence of a life form in the vehicle, or when the first detection result indicates the absence of a life form in the vehicle and the confidence of the first detection result is less than the second value, the first device can detect again whether there is a life form in the vehicle through steps S105 to S107, thereby improving the accuracy of life form detection.

[0086] In addition, for a scenario where there is no life form and no large foreign objects in the vehicle, the first device can more accurately detect the absence of life forms in the vehicle based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, and obtain a first detection result that is consistent with the actual scenario and indicates that there is no life form in the vehicle. Therefore, when the first detection result indicates that there is no life form in the vehicle and the confidence level of the first detection result is greater than the second value, the first device may not perform steps S105 to S107, thereby achieving rapid detection when there is no life form in the vehicle.

[0087] In an optional implementation, if the first device determines that the first detection result indicates that there is no life in the vehicle and the confidence of the first detection result is greater than the second value, the first device can output a first message, and the first message is used to prompt the user that there is no life in the vehicle, thereby informing the user (for example, the driver or a third party) that there is no life in the vehicle; or, the first device may not output the first message, so that when the user does not receive the first message, it can be assumed that the first device detects that there is no life in the vehicle. The first device outputs the first information, which can be: the first device sends the first information to the electronic device. The electronic device can prompt the user by vibration, voice, interface display, etc. to let the user know that there is no life in the vehicle. The embodiment of the present application does not limit the specific way in which the electronic device prompts the user.

[0088] S105: The first device sends a second ultrasonic signal, wherein the second ultrasonic signal is different from the first ultrasonic signal.

[0089] In an optional embodiment, the second ultrasonic signal may be a single-frequency continuous sine wave signal, for example, the second ultrasonic signal may be a continuous sine wave signal with a frequency of 19 kHz. Alternatively, the second ultrasonic signal may be a signal obtained by superimposing a plurality of continuous sine wave signals with different frequencies. For example, the second ultrasonic signal may be a signal obtained by superimposing 9 continuous sine wave signals with frequencies of 17.5 kHz, 18 kHz, 18.5 kHz, 19 kHz, 19.5 kHz, 20 kHz, 20.5 kHz, 21 kHz, and 21.5 kHz, respectively.

[0090] In an optional embodiment, the second ultrasonic signal and the first ultrasonic signal may be sent by the first device through the same device. For example, the second ultrasonic signal and the first ultrasonic signal may be audio signals played by the first device through the same speaker. Sending the second ultrasonic signal through the speaker is similar to sending the first ultrasonic signal through the speaker. Please refer to the above-mentioned explanation of sending the first ultrasonic signal through the speaker, which will not be repeated here. For another example, the second ultrasonic signal and the first ultrasonic signal may be sent by the first device through the same ultrasonic transmitting device.

[0091] In another optional embodiment, the second ultrasonic signal and the first ultrasonic signal may be sent by the first device through different devices. For example, the second ultrasonic signal and the first ultrasonic signal may be audio signals played by the first device through different speakers. For another example, the second ultrasonic signal may be an audio signal played by the first device through a speaker, and the first ultrasonic signal may be sent by the first device through other ultrasonic emitting devices. For another example, the first ultrasonic signal may be an audio signal played by the first device through a speaker, and the second ultrasonic signal may be sent by the first device through other ultrasonic emitting devices. For another example, the second ultrasonic signal and the first ultrasonic signal may be sent by the first device through different ultrasonic emitting devices. In addition, sending the second ultrasonic signal through a speaker is similar to sending the first ultrasonic signal through a speaker. Please refer to the aforementioned explanation of sending the first ultrasonic signal through a speaker, and no further details will be given.

[0092] S106. The first device receives an echo signal of the second ultrasonic signal.

[0093] Wherein, the first device receives the echo signal of the second ultrasonic signal, including: the first device receives the third signal, and the third signal includes the echo signal of the second ultrasonic signal. Since the first device will also receive interference signals caused by factors such as noise and propagation medium when receiving the echo signal of the second ultrasonic signal, the signal actually received by the first device is the third signal, and the third information includes the interference signal in addition to the echo signal of the second ultrasonic signal. Optionally, in the case where the second ultrasonic signal is a continuous sine wave signal, the first device can continuously send the second ultrasonic signal, and the signal received by the first device within a preset duration is the third signal, that is, the duration of the third signal received by the first device is the preset duration. The preset duration can be predefined. Exemplarily, the preset duration can be set to be longer, for example, the preset duration can include at least 4 breathing cycles (about 10 seconds) of the life body, which is conducive to improving the accuracy of subsequent detection of life bodies by detecting breathing based on phase characteristics and reducing false alarms.

[0094] In addition, after receiving the third signal, the first device also determines the phase characteristics corresponding to the echo signal of the second ultrasonic signal. In the case where the second ultrasonic signal is a single-frequency continuous sine wave signal, the first device determines the phase characteristics corresponding to the echo signal of the single-frequency continuous sine wave signal, and the echo signal of the single-frequency continuous sine wave signal can be obtained by filtering the third signal by the first device. In the case where the second ultrasonic signal is a signal obtained by superimposing multiple continuous sine wave signals of different frequencies, the first device determines the phase characteristics corresponding to the echo signal of each continuous sine wave signal in the multiple continuous sine wave signals, and the echo signal of any one of the multiple continuous sine wave signals can be obtained by filtering the third signal by the first device.

[0095] In an optional embodiment, the first device may process the fourth signal using a phase amplification algorithm to obtain a phase feature corresponding to the fourth signal. The fourth signal is an echo signal corresponding to a single-frequency continuous sine wave signal in the second ultrasonic signal. Specifically, when the second ultrasonic signal is a single-frequency continuous sine wave signal, the fourth signal is an echo signal of the single-frequency continuous sine wave signal. When the second ultrasonic signal is a signal obtained by superimposing multiple continuous sine wave signals of different frequencies, the fourth signal is an echo signal of any one of the multiple continuous sine wave signals.

[0096] Exemplarily, the first device uses a phase amplification algorithm to process the fourth signal, which may include: the first device performs dual-path orthogonal modulation on the fourth signal to obtain two fifth signals; the first device performs low-pass filtering, sampling processing, window processing, averaging processing and smoothing processing on each of the two fifth signals in turn to obtain two sixth signals; the first device divides the two sixth signals by bit and uses an inverse tangent function to process the division result to obtain a phase sequence, which is the phase characteristic corresponding to the fourth signal. Optionally, the first device can also perform a discrete Fourier transform on the obtained phase sequence to obtain a corresponding spectrum sequence, which can also reflect the phase characteristic corresponding to the fourth signal. It can be seen that the first device can use a software algorithm to implement signal processing to obtain the phase characteristic corresponding to the echo signal of the second ultrasonic signal, without relying on hardware processing signals such as mixing circuits, which is conducive to making the life detection method provided in the embodiment of the present application applicable to more scenarios.

[0097] It is understandable that the operation of the first device performing two-way orthogonal modulation on the fourth signal is conducive to moving the fourth signal to the zero frequency band, so that the frequency bands of the two fifth signals obtained by the two-way orthogonal modulation are generally low-frequency. The operation of the first device performing low-pass filtering on the fifth signal (this operation can be performed multiple times) can filter out the high-frequency signals (such as noise) remaining in the fifth signal and retain the low-frequency signals. The operation of the first device performing sampling processing on the fifth signal can reduce the signal length of the fifth signal, which is conducive to reducing the computational complexity of subsequent signal processing. In addition, the operations of the first device performing window processing, averaging processing and smoothing processing on the fifth signal are conducive to the situation where the second ultrasonic signal is played by a speaker and the third signal is collected by a microphone, reducing the baseline drift caused by the poor frequency response of ordinary audio equipment, which causes it to generate noise for high-frequency signals.

[0098] S107. The first device determines a second detection result according to a phase feature corresponding to an echo signal of the second ultrasonic signal, where the second detection result is used to indicate whether there is a living being in the vehicle.

[0099] It is understandable that, since the phase corresponding to the echo signal of the ultrasonic signal will change with the propagation time of the ultrasonic signal in the air, and the propagation time is related to the distance between the first device and the reflecting surface (for example, in the case where the ultrasonic signal is sent through a speaker and the echo signal of the ultrasonic signal is received through a microphone, the propagation time is related to the distance between the speaker and the reflecting surface, and the distance between the microphone and the reflecting surface), the movement of the object will cause the reflecting surface to move, and therefore, the movement of the object will cause the phase corresponding to the echo signal of the ultrasonic signal to change. Then, the first device can identify whether there is a small movement (for example, a small movement less than 3.5 mm) based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal. For example, it can identify small movements such as periodic movements of the chest and abdomen caused by the breathing of living organisms. Since the periodicity of the phase change is the same as the periodicity of breathing, the periodicity is used as the basis for judgment, which can reduce false alarms caused by the movement of non-living objects such as toys, fans, and floating cloths, and improve the accuracy of life detection.

[0100] In addition, optionally, since the phase characteristics corresponding to the echo signal of the second ultrasonic signal can identify tiny movements such as periodic movements of the chest and abdomen caused by the breathing of the living body, the breathing frequency of the living body can also be estimated based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal, which is used to detect sleep quality, detect sleep apnea syndrome, etc.

[0101] In an optional implementation, in the case where the second ultrasonic signal is a single-frequency continuous sine wave signal, the second detection result is determined by the first device according to the phase characteristic corresponding to the echo signal of the single-frequency continuous sine wave signal. 0 A continuous sine wave signal with a frequency of f 0 The third signal is filtered by the passband to obtain a frequency of f 0 The echo signal of the continuous sine wave signal is processed by the phase amplification algorithm with a frequency of f 0 A phase sequence is obtained from the echo signal of the continuous sinusoidal wave signal, and a second detection result is determined based on the phase sequence.

[0102] In the case where the second ultrasonic signal is a signal obtained by superimposing multiple continuous sinusoidal signals of different frequencies, the second detection result can be determined by the first device according to the phase characteristics corresponding to the echo signal of each continuous sinusoidal signal in the multiple continuous sinusoidal signals. It can be seen that the first device can determine the second detection result based on multiple phase characteristics to further improve the accuracy of the second detection result. For example, the second ultrasonic signal is a signal obtained by superimposing n (n is an integer greater than 1) continuous sinusoidal signals of different frequencies, and the n continuous sinusoidal signals are signal #1 to signal #n, and the frequencies of signal #1 to signal #n are f respectively. 1 、f 2 ,…,f n The first device can respectively use a frequency of f 1 、f 2 ,…,f n The received third signal is filtered by a bandpass filter to obtain an echo signal of each signal from signal #1 to signal #n. For each signal from signal #1 to signal #n, the first device can use a phase amplification algorithm to process, so that the first device can obtain n phase sequences and determine the second detection result based on the n phase sequences.

[0103] In one optional manner, if all or most of the n phase sequences reflect the presence of a living being in the vehicle, the second detection result indicates that there is a living being in the vehicle; if all or most of the n phase sequences reflect the absence of a living being in the vehicle, the second detection result indicates that there is no living being in the vehicle.

[0104] In another optional method, the n phase sequences can be directly added bit by bit, and the second detection result is determined based on a phase sequence obtained by adding the n phase sequences bit by bit. It is understandable that since there will be some noise at different frequencies in the environment, there will be some differences in the n phase sequences due to the noise, and even the periodicity of a single phase sequence may be masked by the noise; but for the scenario where there are living things in the vehicle, the n phase sequences fluctuate at the same breathing frequency, so adding the n phase sequences bit by bit can reduce the impact of noise in different frequency bands, amplify the periodicity of breathing, and help to more accurately detect whether there are living things in the vehicle.

[0105] In an optional embodiment, the first device may receive a third signal in each of a plurality of time periods, wherein the third signal received by the first device in each time period includes an echo signal of the second ultrasonic signal in the time period. For each of the plurality of time periods, the first device may determine a third detection result based on the phase feature corresponding to the echo signal of the second ultrasonic signal in the third signal received in the time period, and the third detection result is used to indicate whether there is a life form in the vehicle. In this way, the first device can obtain a plurality of third detection results corresponding to a plurality of time periods one by one, and then determine the second detection result based on the plurality of third detection results, which is conducive to improving the confidence of the second detection result. It is understandable that since the second ultrasonic signal is a continuous sine wave signal, the first device can continuously send the second ultrasonic signal, and the first device can continuously receive the echo signal of the second ultrasonic signal. Then, the first device can perform a third detection result based on the third signal received in the time period of the preset time period at each interval of the preset time length, and then determine the second detection result based on the plurality of third detection results obtained.

[0106] For example, the first device is at t 1 to 2 During this period of time, a third signal #1 is received, and the third signal #1 includes the second ultrasonic signal at t 1 to 2 The first device can determine the third detection result #1 based on the phase feature corresponding to the echo signal of the second ultrasonic signal in the third signal #1. 2 to 3 During this period of time, a third signal #2 is received, and the third signal #2 includes the second ultrasonic signal at t 2 to 3 The first device can determine the third detection result #2 based on the phase feature corresponding to the echo signal of the second ultrasonic signal in the third signal #2; the first device at t 3 to 4During this period of time, a third signal #3 is received, and the third signal #3 includes the second ultrasonic signal at t 3 to 4 For the echo signal of this time period, the first device can determine the detection result #3 based on the phase feature corresponding to the echo signal of the second ultrasonic signal in the third signal #3. If all or most of the third detection results #1 to the third detection result #3 indicate that there is a life form in the vehicle, the first device can determine that the second detection result indicates that there is a life form in the vehicle; otherwise, the first device can determine that the second detection result indicates that there is no life form in the vehicle.

[0107] In an optional embodiment, the first device can determine whether there is a life form in the vehicle by judging whether the phase feature corresponding to the echo signal of the second ultrasonic signal reflects the phase change. For example, if the phase sequence obtained by processing the fourth signal using the phase amplification algorithm has a period of change between 10 and 30 times per minute, it can be considered that the phase sequence reflects the existence of a life form in the vehicle. For another example, in the spectrum sequence obtained by performing a discrete Fourier transform on the phase sequence obtained by processing the fourth signal using the phase amplification algorithm, if the amplitude of the frequency band corresponding to the change period (for example, when the period is approximately between 10 and 30 times per minute, the corresponding frequency band is 0.16Hz to 0.5Hz) is higher than a preset threshold, it can be considered that there is an obvious periodicity of phase change, then, it can be considered that the spectrum sequence reflects the existence of a life form in the vehicle. In addition, the specific description of the phase amplification algorithm can be found in the above-mentioned related description, which will not be repeated here.

[0108] For example, taking the second ultrasonic signal as a single-frequency continuous sine wave signal, combined with Figure 4 and Figure 5 , Figure 4 The phase sequence obtained by the first device using the phase amplification algorithm in a scenario where a living being in a vehicle breathes at a frequency of 0.27 Hz is exemplarily shown. Figure 5 Shows the Figure 4 The spectral sequence obtained by discrete Fourier transform of the phase sequence shown. It can be seen that Figure 4 There are variations in the phase sequence shown, Figure 5 The frequency spectrum sequence shown reflects that the frequency component of the echo signal of the second ultrasonic signal includes a frequency of 0.27 Hz. It can be considered that both the phase sequence and the frequency spectrum sequence reflect the existence of a living being in the vehicle.

[0109] In an optional embodiment, the first device determines the second detection result according to the phase characteristics corresponding to the echo signal of the second ultrasonic signal, which may include: the first device determines the second detection result according to the phase characteristics corresponding to the echo signal of the second ultrasonic signal and the second model. The second model may be a machine learning model trained based on the phase sequence corresponding to the ultrasonic signal. For example, the second model may be a KNN, SVM, neural network or other model. Optionally, the first device may perform binary classification based on the second model to determine whether there is a life form in the vehicle, and the binary classification includes two categories: the existence of a life form in the vehicle and the absence of a life form in the vehicle.

[0110] For example, in the case where the second ultrasonic signal is a single-frequency continuous sine wave signal, the phase characteristics corresponding to the echo signal of the single-frequency continuous sine wave signal can be input into the second model, and the second model outputs information to indicate whether there is a living being in the vehicle. The information output by the second model indicates the second detection result.

[0111] For another example, in the case where the second ultrasonic signal is a signal obtained by superimposing multiple continuous sinusoidal signals of different frequencies, the phase characteristics corresponding to the echo signal of each continuous sinusoidal signal in the multiple continuous sinusoidal signals can be respectively input into the second model, and the second model outputs multiple information corresponding to the multiple continuous sinusoidal signals (each information is used to indicate whether there is a life form in the vehicle), and then the second detection result is obtained based on the multiple information output by the second model. Exemplarily, if all or most of the multiple information indicate that there is a life form in the vehicle, the second detection result indicates that there is a life form in the vehicle; if all or most of the multiple information indicate that there is no life form in the vehicle, the second detection result indicates that there is no life form in the vehicle.

[0112] In an optional embodiment, after the first device determines the second detection result, the method further includes: the first device outputs the second information, and the second information is used to prompt the user of the second detection result. Exemplarily, the first device may send the second information to the electronic device to inform the user of the second detection result. The electronic device may prompt the user by vibration, voice, interface display, etc. so that the user knows the second detection result. The embodiment of the present application does not limit the specific way in which the electronic device prompts the user. Optionally, if the first detection result is different from the second detection result, the confidence of the second information output by the first device is less than the third value; if the first detection result is the same as the second detection result, the confidence of the second information output by the first device is greater than the third value. It can be seen that compared with the case where the first detection result is different from the second detection result, the confidence of the second information is higher when the first detection result is the same as the second detection result. Among them, the third value can be predefined. Optionally, in the case where the first model is used to determine the first detection result and the second model is used to determine the second detection result, the first model and the second model will output the confidence of the detection results at the same time as the detection results. Then, the confidence of the second information can be determined based on the first detection result, the confidence of the first detection result, the second detection result, and the confidence of the second detection result.

[0113] In an optional embodiment, when the first device determines the first detection result based on the first model and the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, the first device can timely update the first model according to user feedback or the second detection result. When the first device determines the second detection result based on the second model and the phase characteristics corresponding to the echo signal of the second ultrasonic signal, the first device can timely update the second model according to user feedback. This embodiment is conducive to reducing the impact of equipment aging on the accuracy of life detection, so that the life detection method provided in the embodiment of the present application can be used for a long time and maintain a high accuracy, thereby ensuring the user experience for a long time. The optional way for the first device to update the first model and the second model is explained below, as described in the following optional embodiments 1.1 and 1.2.

[0114] In implementation 1.1, the first detection result indicates that there is no life in the vehicle and the confidence of the first detection result is greater than the second value. In this case, the first device may not perform steps S105-S107, that is, it may not detect again whether there is a life in the vehicle based on the second ultrasonic signal, and the first device may output the first information, which is used to prompt the user that there is no life in the vehicle.

[0115] If the user's feedback behavior in response to the first information does not match the first detection result, the first device may update the first model based on the echo signal of the first ultrasonic signal. Since the first detection result indicates that there is no life form in the vehicle, if the user's feedback behavior in response to the first information is that the user returns to the vehicle in a short time or the user remotely turns on the vehicle's air conditioning or exhaust system, etc., which can reflect that the user believes that there is a life form in the vehicle, it can be considered that the user's feedback behavior in response to the first information does not match the first detection result.

[0116] Optionally, the first device updates the first model based on the echo signal of the first ultrasonic signal, which may include: the first device adds the echo signal of the first ultrasonic signal as incremental data to the incremental learning data set corresponding to the first model, and retrains the first model based on the incremental learning data set to adjust the parameters of the first model. Optionally, when the amount of data in the incremental learning data set corresponding to the first model exceeds a threshold, the incremental data added earlier may be deleted, thereby helping to reduce the impact caused by the excessive storage space occupied by the incremental learning data set. The incremental learning data set corresponding to the second model in the following text is similar to this and will not be repeated in the following text.

[0117] In implementation 1.2, the first detection result indicates that there is a life form in the vehicle, or the first detection result indicates that there is a life form in the vehicle and the confidence of the first detection result is less than the second value. In this case, the first device will execute steps S105-S107, that is, the first device will further detect whether there is a life form in the vehicle based on the second ultrasonic signal, and the first device may output a second message to prompt the user of the second detection result.

[0118] If the user's feedback behavior for the second information does not match the second detection result, the first device may update the second model based on the echo signal of the second ultrasonic signal, and update the first model based on the echo signal of the first ultrasonic signal. If the user's feedback behavior for the second information matches the second detection result and the confidence of the second information is less than a third value, the first device may update the first model based on the echo signal of the first ultrasonic signal.

[0119] Among them, in the case where the second detection result indicates that there is a life form in the vehicle, if the user's feedback behavior for the second information is that the user ignores the second information and / or the user does not return to the vehicle, etc., which can reflect that the user believes that there is no life form in the vehicle, it can be considered that the user's feedback behavior for the second information does not match the second detection result. Generally speaking, if there is a life form in the vehicle (for example, a child or pet left behind by the user in the vehicle), the user will return to the vehicle in a timely manner after receiving the prompt information indicating the presence of a life form in the vehicle. Then, if the user ignores the prompt information indicating the presence of a life form in the vehicle and / or the user does not return to the vehicle, it can be considered that the first device has detected an error.

[0120] Regarding the situation where the second detection result indicates that there is no living thing in the vehicle, if the user's feedback behavior to the second information is that the user returns to the vehicle in a short time or the user remotely turns on the vehicle's air conditioning or exhaust system, etc., which can reflect that the user believes that there is a living thing in the vehicle, it can be considered that the user's feedback behavior to the second information does not match the second detection result.

[0121] Optionally, the first device updates the second model based on the echo signal of the second ultrasonic signal, which may include: the first device adds the echo signal of the second ultrasonic signal to the incremental learning data set corresponding to the second model, and retrains the second model based on the incremental learning data set to adjust the parameters of the second model. In addition, for the specific description of the first device updating the first model based on the echo signal of the first ultrasonic signal, please refer to the relevant description in Implementation 1.1, which will not be repeated here.

[0122] Optionally, if the first detection result is different from the second detection result, the first device can update the first model based on the echo signal of the first ultrasonic signal. Since the accuracy of life detection based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal is higher than that based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, when the first detection result is different from the second detection result, it is considered that the confidence of the second detection result is higher than the confidence of the first detection result. Then, the first device can update the first model based on the echo signal of the first ultrasonic signal. For the specific explanation of the first device updating the first model based on the echo signal of the first ultrasonic signal, please refer to the relevant explanation in Implementation 1.1, which will not be repeated here.

[0123] In addition, in the above steps S101 to S107, any one or more of steps S101, S102, S105, and S106 may be optional steps.

[0124] In summary, in the method for detecting life forms, the first device can determine a first detection result based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, and the first detection result is used to indicate whether there is a life form in the vehicle. When the first detection result indicates that there is a life form in the vehicle, the first device further determines a second detection result based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal, and the second detection result is used to indicate whether there is a life form in the vehicle.

[0125] It can be seen that the life form detection method can perform preliminary detection based on the first ultrasonic signal. When the preliminary detection result indicates the presence of a life form in the vehicle, further more accurate life form detection can be performed based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal, thereby improving the accuracy of life form detection.

[0126] In addition, when a speaker is used to send the first ultrasonic signal and / or the second ultrasonic signal, and a microphone is used to receive the echo signal of the first ultrasonic signal and / or the echo signal of the second ultrasonic signal, the life detection method provided in the embodiment of the present application can achieve high-accuracy life detection by using audio equipment on ordinary cars or other electronic devices without relying on commonly used ultrasonic devices, millimeter-wave radars and other additional devices (including high-frequency signal transceiver devices, mixing circuits).

[0127] It is understandable that, in order to implement the functions in the above method, the first device includes a hardware structure and / or software module corresponding to each function. Those skilled in the art should easily realize that, in combination with the units and method steps of each example described in the embodiments disclosed in this application, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0128] like Figure 6 As shown, the embodiment of the present application provides an apparatus 600, which can be a first device or a component of the first device (for example, an integrated circuit, a chip, a chip system, etc.), for implementing the method in the method embodiment of the present application. The apparatus 600 may include a signal transmitting module 601, a signal receiving module 602, and a computing processing module 603.

[0129] The signal transmitting module 601 is used to transmit a first ultrasonic signal. The signal receiving module 602 is used to receive an echo signal of the first ultrasonic signal. The computing and processing module 603 is used to determine a first detection result according to time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, and the first detection result is used to indicate whether there is a life form in the vehicle. The computing and processing module 603 is also used to determine whether the first detection result indicates that there is a life form in the vehicle.

[0130] If the first detection result indicates that there is a living organism in the vehicle, the signal transmitting module 601 is also used to send a second ultrasonic signal, the signal receiving module 602 is also used to receive the echo signal of the second ultrasonic signal, and the calculation and processing module 603 is also used to determine the second detection result based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal. The second detection result is used to indicate whether there is a living organism in the vehicle, and the second ultrasonic signal is different from the first ultrasonic signal.

[0131] In an optional embodiment, if the first detection result indicates that there is no living organism in the vehicle and the confidence level of the first detection result is less than a second value, the signal transmitting module 601 is also used to send a second ultrasonic signal, the signal receiving module 602 is also used to receive an echo signal of the second ultrasonic signal, and the computing and processing module 603 is also used to determine a second detection result based on a phase feature corresponding to the echo signal of the second ultrasonic signal, and the second detection result is used to indicate whether there is a living organism in the vehicle.

[0132] In an optional embodiment, the device 600 may further include a vehicle status detection module 604, which may be used to detect whether the user has left the vehicle. Exemplarily, the vehicle status detection module 604 may determine that the user has left the vehicle by acquiring one or more of the following events: a parking event, a door opening and closing event, a vehicle locking event, and an event in which the Bluetooth connection of an electronic device connected to the vehicle is lost. In addition, in addition to the above events, the vehicle status detection module 604 may also determine that the user has left the vehicle by acquiring or detecting other events that may indicate that the user has left the vehicle, without limitation.

[0133] In an optional embodiment, the signal receiving module 602 receives the echo signal of the first ultrasonic signal, and is specifically used for: the signal receiving module 602 receives the first signal, and the first signal includes the echo signal of the first ultrasonic signal. In addition, the signal receiving module 602 is also used to output the first signal to the calculation and processing module 603. The calculation and processing module 603 is also used to filter the first signal using a sliding window to obtain a second signal with a signal strength greater than the first value, and the second signal includes the echo signal of the first ultrasonic signal. The calculation and processing module 603 is also used to process the second signal using a matched filtering algorithm, determine the time when the echo signal of the first ultrasonic signal is received, and determine the echo signal of the first ultrasonic signal based on the time.

[0134] In addition, the calculation and processing module 603 can also be used to determine the matched filtering sequence results obtained by using the matched filtering algorithm as the time domain characteristics corresponding to the echo signal of the first ultrasonic signal, and determine the spectrum sequence obtained by performing fast Fourier transform on the extracted echo signal of the first ultrasonic signal as the frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal.

[0135] In an optional embodiment, the signal receiving module 602 determines the first detection result based on the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, and is specifically used to: determine the first detection result based on the first model and the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal.

[0136] In an optional embodiment, the signal receiving module 602 receives the echo signal of the second ultrasonic signal, and is specifically used for: the signal receiving module 602 receives a third signal, and the third signal includes the echo signal of the second ultrasonic signal. The signal receiving module 602 can also be used to output the third signal to the calculation and processing module 603. The calculation and processing module 603 can also be used to filter the third signal to obtain a fourth signal; wherein, when the second ultrasonic signal is a single-frequency continuous sine wave signal, the fourth signal is the echo signal of the single-frequency continuous sine wave signal, and when the second ultrasonic signal is a signal obtained by superimposing multiple continuous sine wave signals of different frequencies, the fourth signal is the echo signal of any one of the multiple continuous sine wave signals. The calculation and processing module 603 can also be used to process the fourth signal using a phase amplification algorithm to obtain a phase feature corresponding to the fourth signal.

[0137] Exemplarily, the calculation and processing module 603 uses a phase amplification algorithm to process the fourth signal, which can be specifically used to execute: dual-channel orthogonal modulation of the fourth signal to obtain two fifth signals; low-pass filtering, sampling processing, window processing, averaging processing and smoothing processing are performed on each of the two fifth signals in turn to obtain two sixth signals; the two sixth signals are processed by phase division and inverse tangent function to obtain a phase sequence, which is the phase feature corresponding to the fourth signal. Optionally, the calculation and processing module 603 can also perform discrete Fourier transform on the obtained phase sequence to obtain a corresponding spectrum sequence, which can also reflect the phase feature corresponding to the fourth signal.

[0138] In an optional embodiment, the signal receiving module 602 determines the second detection result based on the phase characteristics corresponding to the echo signal of the second ultrasonic signal, and is specifically used to: determine the second detection result based on the second model and the phase characteristics corresponding to the echo signal of the second ultrasonic signal.

[0139] In an optional embodiment, the device 600 may further include a communication module 605. When the first detection result indicates that there is no life form in the vehicle and the confidence of the first detection result is greater than a second value, the calculation and processing module 603 may also be used to output the first detection result to the communication module 605, and the communication module 605 may be used to output a first message, and the first message is used to prompt the user that there is no life form in the vehicle. When the first detection result indicates that there is a life form in the vehicle, or when the first detection result indicates that there is no life form in the vehicle and the confidence of the first detection result is less than a second value, the calculation and processing module 603 may also be used to output a second detection result to the communication module 605, and the communication module 605 may be used to output a second message, and the second message is used to prompt the user of the second detection result.

[0140] In an optional embodiment, when the computing and processing module 603 determines the first detection result according to the first model and the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, the computing and processing module 603 can also be used to timely update the first model according to user feedback or the second detection result. When the computing and processing module 603 determines the second detection result according to the second model and the phase characteristics corresponding to the echo signal of the second ultrasonic signal, the computing and processing module 603 can also be used to timely update the second model according to user feedback. As described in the following optional embodiments 2.1 and 2.2.

[0141] In implementation 2.1, for a situation where the first detection result indicates that there is no life form in the vehicle and the confidence level of the first detection result is greater than the second value, and the communication module 605 further outputs the first information for prompting the user that there is no life form in the vehicle, if the user's feedback behavior regarding the first information does not match the first detection result, the calculation processing module 603 may update the first model based on the echo signal of the first ultrasonic signal.

[0142] In implementation 2.2, when the first detection result indicates the presence of a living being in the vehicle, or when the first detection result indicates the presence of a living being in the vehicle and the confidence level of the first detection result is less than a second value, the computing and processing module 603 determines a second detection result based on a phase feature corresponding to an echo signal of the second ultrasonic signal, and the second detection result is used to indicate whether there is a living being in the vehicle.

[0143] If the first detection result is different from the second detection result, the calculation processing module 603 can update the first model based on the echo signal of the first ultrasonic signal. In addition, in the scenario where the communication module 605 also outputs the second information for prompting the user of the second detection result, if the user's feedback behavior for the second information does not match the second detection result, the calculation processing module 603 can update the second model based on the echo signal of the second ultrasonic signal, and update the first model based on the echo signal of the first ultrasonic signal; if the user's feedback behavior for the second information matches the second detection result and the confidence of the second information is less than the third value, the calculation processing module 603 can update the first model based on the echo signal of the first ultrasonic signal.

[0144] In addition, the specific description of the above-mentioned implementation modes can also refer to the relevant description in the aforementioned life body detection method, which will not be repeated here. Figure 6 The device 600 shown can also be used to implement other functions of the first device in the life detection method, and also has corresponding beneficial effects, which will not be described in detail here.

[0145] The following takes the device 600 including a signal transmitting module 601, a signal receiving module 602, a calculation processing module 603, a vehicle state detection module 604 and a communication module 605 as an example. Figure 7 The method of detecting life forms is described by way of example. Figure 7 The life body detection method shown includes the following steps:

[0146] S201, the vehicle state detection module 604 determines that the user leaves the vehicle.

[0147] S202 , the vehicle state detection module 604 outputs information for instructing the signal receiving module 602 to start signal reception to the signal receiving module 602 .

[0148] S203, the signal receiving module 602 starts signal reception.

[0149] S204, the signal transmitting module 601 transmits a first ultrasonic signal. Correspondingly, the signal receiving module 602 receives the first signal, which includes an echo signal of the first ultrasonic signal.

[0150] S205 , the signal receiving module 602 outputs the first signal to the calculation processing module 603 .

[0151] S206: The calculation and processing module 603 determines the echo signal of the first ultrasonic signal from the first signal.

[0152] S207: The calculation processing module 603 determines the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal.

[0153] S208, the calculation and processing module 603 determines a first detection result according to the first model and the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, and the first detection result is used to indicate whether there is a living body in the vehicle.

[0154] S209, the calculation processing module 603 determines whether the first detection result indicates that there is a life form in the vehicle. If the first detection result indicates that there is no life form in the vehicle and the confidence of the first detection result is greater than the second value, steps S210 and S211 are executed. If the first detection result indicates that there is a life form in the vehicle, or the first detection result indicates that there is no life form in the vehicle and the confidence of the first detection result is less than the second value, steps S212 to S218 are executed.

[0155] S210 , the calculation processing module 603 outputs the first detection result to the communication module 605 .

[0156] S211, the communication module 605 sends a first message to the electronic device, where the first message is used to prompt the user that there is no living being in the vehicle.

[0157] S212 , the calculation processing module 603 outputs information for instructing the signal transmitting module 601 to transmit the second ultrasonic signal to the signal transmitting module 601 .

[0158] S213, the signal transmitting module 601 transmits a second ultrasonic signal. Correspondingly, the signal receiving module 602 receives a third signal, which includes an echo signal of the second ultrasonic signal.

[0159] S214 , the signal receiving module 602 outputs the third signal to the calculation processing module 603 .

[0160] S215: The calculation processing module 603 determines a phase feature corresponding to the echo signal of the second ultrasonic signal based on the third signal.

[0161] S216, the calculation and processing module 603 determines a second detection result according to the second model and the phase feature corresponding to the echo signal of the second ultrasonic signal, and the second detection result is used to indicate whether there is a living being in the vehicle.

[0162] S217, the calculation processing module 603 outputs the second detection result to the communication module 605.

[0163] S218, the communication module 605 sends second information to the electronic device, where the second information is used to prompt the user of the second detection result.

[0164] In an optional embodiment, Figure 7 The calculation processing module 603 in the embodiment can also update the first model and / or the second model. Figure 8 As shown in the dashed box, for the case where the first detection result indicates that there is no life in the vehicle and the confidence level of the first detection result is greater than the second value, Figure 7 After step S211 in the life body detection method shown, steps S219 and S220 may also be included:

[0165] S219, the calculation processing module 603 determines whether the user's feedback behavior for the first information matches the first detection result. If the user's feedback behavior for the first information does not match the first detection result, step S220 is executed.

[0166] S220: The calculation processing module 603 updates the first model based on the echo signal of the first ultrasonic signal.

[0167] In addition, in the case where the first detection result indicates that there is a life form in the vehicle, or the first detection result indicates that there is no life form in the vehicle and the confidence level of the first detection result is less than the second value, Figure 7 After step S218 in the life body detection method shown, steps S221 to S224 may also be included:

[0168] S221, the calculation processing module 603 determines whether the user's feedback behavior for the second information matches the second detection result. If the user's feedback behavior for the second information does not match the second detection result, step S222 is executed.

[0169] S222: The calculation processing module 603 updates the first model based on the echo signal of the first ultrasonic signal, and updates the second model based on the echo signal of the second ultrasonic signal.

[0170] S223, the calculation processing module 603 determines whether the first detection result is the same as the second detection result. If the first detection result is different from the second detection result, step S224 is executed.

[0171] S224: The calculation processing module 603 updates the first model based on the echo signal of the first ultrasonic signal.

[0172] In addition, in an optional embodiment, as Fig. 9 As shown, for Figure 6 In the device 600 shown, the signal transmitting module 601 in the device 600 may include one or more speakers or ultrasonic transmitting devices to implement the sending of the first ultrasonic signal and / or the second ultrasonic signal.

[0173] The signal receiving module 602 may include one or more microphones or ultrasonic receiving devices to receive the echo signal of the first ultrasonic signal and / or the echo signal of the second ultrasonic signal.

[0174] The computing and processing module 603 may include a processor and a memory. The processor may be used to design the first ultrasonic signal and / or the second ultrasonic signal, and process the echo signal of the first ultrasonic signal to determine the first detection result, and process the echo signal of the second ultrasonic signal to determine the second detection result. The memory may be used to store the incremental learning data set corresponding to the first model so that the processor can update the first model, and store the incremental learning data set corresponding to the second model so that the processor can update the second model.

[0175] The vehicle state detection module 604 may be used to monitor the vehicle's doors, windows, seats and other sensors as well as Bluetooth, vision (e.g., camera) and other devices to determine whether the user has left the vehicle. Optionally, the vehicle state detection module 604 may include the vehicle's doors, windows, seats and other sensors as well as Bluetooth, vision and other devices.

[0176] The communication module 605 may include an antenna, and the antenna outputs first information for prompting the user that there is no life form in the vehicle or outputs second information for prompting the user of a second detection result.

[0177] in addition, Fig. 9 Each physical unit can also realize other functions of the corresponding functional unit. For specific descriptions, please refer to the above-mentioned related descriptions and will not be repeated here.

[0178] Also, see Fig.10 The present application also provides an apparatus 1000, which may be a first device, or a chip, a chip system, or a processor that supports the first device to implement the above method. The apparatus may be used to implement the method described in the above method embodiment, and the details may refer to the description in the above method embodiment.

[0179] The apparatus 1000 may include one or more processors 1001. The processor 1001 may be used to implement part or all of the functions of the first device through a logic circuit or running a computer program. The processor 1001 may be a general-purpose processor or a dedicated processor, etc. For example, it may be a baseband processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component or a central processing unit (CPU), etc.

[0180] Optionally, the device 1000 may include one or more memories 1002, on which instructions 1004 or computer program codes may be stored, and the instructions or computer program codes may be executed on the processor 1001, so that the device 1000 performs the method described in the above method embodiment. Optionally, data may also be stored in the memory 1002. The processor 1001 and the memory 1002 may be provided separately or integrated together.

[0181] The memory 1002 may include, but is not limited to, a non-volatile memory such as a hard disk drive (HDD) or a solid-state drive (SSD), a random access memory (RAM), an erasable programmable ROM (EPROM), a ROM or a portable read-only memory (CD-ROM), etc.

[0182] Optionally, the apparatus 1000 may further include a transceiver 1005 and an antenna 1006. The transceiver 1005 may be referred to as a transceiver unit, a transceiver, or a transceiver circuit, etc., for implementing a transceiver function. The transceiver 1005 may include a receiver and a transmitter, the receiver may be referred to as a receiver or a receiving circuit, etc., for implementing a receiving function; the transmitter may be referred to as a transmitter or a transmitting circuit, etc., for implementing a transmitting function.

[0183] In one possible design, the transceiver 1005 is used to send a first ultrasonic signal; the transceiver 1005 is also used to receive an echo signal of the first ultrasonic signal. The processor 1001 is used to determine a first detection result according to time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, and the first detection result is used to indicate whether there is a living body in the vehicle.

[0184] If the first detection result indicates the presence of a living being in the vehicle, the transceiver 1005 is also used to send a second ultrasonic signal; the transceiver 1005 is also used to receive an echo signal of the second ultrasonic signal, and the processor 1001 is also used to determine a second detection result based on a phase feature corresponding to the echo signal of the second ultrasonic signal, and the second detection result is used to indicate whether there is a living being in the vehicle, and the second ultrasonic signal is different from the first ultrasonic signal.

[0185] In another possible design, the processor 1001 may store instructions 1003, and the instructions 1003 are executed on the processor 1001, so that the device 1000 can execute the method described in the above method embodiment. The instructions 1003 may be fixed in the processor 1001, in which case the processor 1001 may be implemented by hardware.

[0186] The embodiment of the present application also provides a chip or chip system, which may include a processor and an interface. Among them, the number of processors may be one or more, and the number of interfaces may be multiple. The processor may be a logic circuit, and the interface may be an input-output interface, an input interface, or an output interface. The chip or chip system may also include a memory, which may be used to store programs or instructions. The processor may be used to execute the program or instructions stored in the memory so that the chip or chip system performs the method described in the above embodiment.

[0187] The embodiments of the present application and the above-mentioned method embodiments are based on the same concept, and the technical effects they bring are also the same. For the specific principles, please refer to the description in the above-mentioned method embodiments, which will not be repeated here.

[0188] Those skilled in the art may also understand that the various illustrative logical blocks and steps listed in the embodiments of the present application may be implemented by hardware, software, or a combination of the two. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the functions described for each specific application, but such implementation should not be understood as exceeding the scope of protection of the embodiments of the present application.

[0189] The present application also provides a computer-readable storage medium for storing instructions or computer programs, which, when executed by a device, implement the functions of any of the above method embodiments.

[0190] The present application also provides a computer program product for storing instructions or computer program codes, which, when executed by a device, implement the functions of any of the above method embodiments.

[0191] The present application also provides a computer program, which, when executed on a computer, implements the functions of any of the above method embodiments.

[0192] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting a living being, characterized in that: The method comprises: The first device determines a first detection result according to time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal, wherein the first detection result is used to indicate whether there is a living being in the vehicle; If the first detection result indicates the presence of a living being in the vehicle, the first device determines a second detection result based on a phase characteristic corresponding to an echo signal of a second ultrasonic signal, and the second detection result is used to indicate whether there is a living being in the vehicle, and the second ultrasonic signal is different from the first ultrasonic signal.

2. The method according to claim 1, characterized in that The method further comprises: The first device receives a first signal, wherein the first signal includes an echo signal of the first ultrasonic signal; The first device filters the first signal using a sliding window to obtain a second signal having a signal strength greater than a first value, wherein the second signal includes an echo signal of the first ultrasonic signal; The first device processes the second signal using a matched filtering algorithm to determine the time when the echo signal of the first ultrasonic signal is received; The first device determines the echo signal of the first ultrasonic signal according to the time when the echo signal of the first ultrasonic signal is received.

3. The method according to claim 2, characterized in that The time domain feature corresponding to the echo signal of the first ultrasonic signal is: a matched filtering sequence result obtained by the first device processing the second signal using a matched filtering algorithm; The frequency domain feature corresponding to the echo signal of the first ultrasonic signal is: a frequency spectrum sequence obtained by the first device performing fast Fourier transform on the echo signal of the first ultrasonic signal.

4. The method according to any one of claims 1 to 3, characterized in that: The first device determines a first detection result according to a time domain feature and a frequency domain feature corresponding to an echo signal of the first ultrasonic signal, including: The first device determines the first detection result according to the first model and the time domain characteristics and frequency domain characteristics corresponding to the echo signal of the first ultrasonic signal.

5. The method according to any one of claims 1 to 4, characterized in that: The first ultrasonic signal is a frequency modulated continuous wave signal.

6. The method according to any one of claims 1 to 5, characterized in that: The first ultrasonic signal is sent by the first device through a speaker, and the echo signal of the first ultrasonic signal is received by the first device through a microphone; and / or, The second ultrasonic signal is sent by the first device through a speaker, and an echo signal of the second ultrasonic signal is received by the first device through a microphone.

7. The method according to any one of claims 1 to 6, characterized in that: The second ultrasonic signal is a single-frequency continuous sine wave signal.

8. The method according to any one of claims 1 to 6, characterized in that: The second ultrasonic signal is a signal obtained by superimposing a plurality of continuous sinusoidal wave signals of different frequencies; The first device determines the second detection result according to the phase characteristics corresponding to the echo signal of the second ultrasonic signal, including: the first device determines the second detection result according to the phase characteristics corresponding to the echo signal of each continuous sine wave signal in the multiple continuous sine wave signals.

9. The method according to claim 7 or 8, characterized in that: The method further comprises: The first device receives a third signal, wherein the third signal includes an echo signal of the second ultrasonic signal; The first device performs filtering processing on the third signal to obtain a fourth signal; the fourth signal is an echo signal corresponding to the single-frequency continuous sine wave signal in the second ultrasonic signal; The first device performs two-way orthogonal modulation on the fourth signal to obtain two fifth signals; The first device sequentially performs low-pass filtering, sampling processing, window processing, averaging processing and smoothing processing on each of the two fifth signals to obtain two sixth signals; The first device divides the two sixth signals bit by bit and processes the division result using an inverse tangent function to obtain a phase feature corresponding to the fourth signal.

10. The method according to any one of claims 1 to 9, characterized in that: The first device determines a first detection result according to a phase feature corresponding to an echo signal of the second ultrasonic signal, including: The first device determines the second detection result according to the phase characteristics corresponding to the echo signal of the second ultrasonic signal and the second model.

11. The method according to any one of claims 1 to 10, characterized in that: After the first device determines the second detection result according to the phase feature corresponding to the echo signal of the second ultrasonic signal, the method further includes: The first device outputs second information, where the second information is used to prompt a user of the second detection result.

12. The method according to claim 11, characterized in that The method further comprises: If the user's feedback behavior in response to the second information does not match the second detection result, the first device updates the first model based on the echo signal of the first ultrasonic signal, and updates the second model based on the echo signal of the second ultrasonic signal; If the user's feedback behavior for the second information matches the second detection result and the confidence level of the second information is less than a third value, the first device updates the first model based on the echo signal of the first ultrasonic signal; The first model is used by the first device to determine the first detection result, and the second model is used by the first device to determine the second detection result.

13. The method according to any one of claims 1 to 12, characterized in that: The method further comprises: If the first detection result is different from the second detection result, the first device updates a first model based on the echo signal of the first ultrasonic signal, the first model being used by the first device to determine the first detection result.

14. A device, characterized in that: including one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, where the computer program codes include computer instructions, and the one or more processors call the computer instructions to cause the apparatus to perform the method according to any one of claims 1 to 13.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 13 is implemented.

Images