Fall detection method and device and intelligent wearable equipment
By combining an accelerometer and a mechanical wave sensor in a smart wearable device, bursts of sound in the audio signal are identified, solving the problem of inaccurate acceleration value detection in existing technologies and achieving more accurate drop detection.
Patent Information
- Application Number
- CN202411302986.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-18
- Publication Date
- 2024-11-22
AI Technical Summary
Existing drop detection methods for smart wearable devices rely on acceleration values that are easily affected by factors such as noise, wind, and vibration, leading to inaccurate detection results.
By combining accelerometers and mechanical wave sensors, the system acquires acceleration values and sound signals, identifies burst sound signals in the sound signals to determine whether the device is in a drop state, and includes steps such as preprocessing, frequency domain conversion, filtering, and time domain conversion to improve the signal-to-noise ratio.
It improves the accuracy of drop detection, avoids misjudgments caused by relying solely on acceleration values, and enhances the reliability of equipment status assessment.
Smart Images

Figure CN119007400A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of electronic technology, and more specifically, to a fall detection method, device and smart wearable device. Background Art
[0002] At present, smart wearable devices such as smart watches, bracelets, glasses, and headphones have become an indispensable part of daily life. However, the portability of smart wearable devices also brings a problem that cannot be ignored - device loss. Once the device is lost, it will not only cause economic losses to the user, but also may lead to the risk of user privacy leakage, so preventing device loss is particularly important.
[0003] Existing device anti-loss methods often use accelerometers to collect acceleration values of smart wearable devices to determine the status of smart wearable devices. However, the collection of acceleration values is easily interfered by various factors, such as noise, wind, vibration, etc., which leads to deviations in measurement results and further misjudgment of the fall status. Summary of the invention
[0004] One purpose of the embodiments of the present application is to provide a new technical solution for fall detection to solve the problem of inaccurate detection results when performing fall detection through acceleration values in the prior art.
[0005] According to a first aspect of the present application, a fall detection method is provided, comprising:
[0006] Get the acceleration value of the smart wearable device collected by the acceleration sensor;
[0007] When the acceleration value is greater than or equal to the acceleration threshold, obtaining a sound signal collected by the mechanical wave sensor;
[0008] Identifying whether there is a burst sound signal in the sound signal;
[0009] When there is a burst sound signal in the sound signal, it is determined that the smart wearable device is in a falling state.
[0010] Optionally, the identifying whether there is a burst sound signal in the sound signal includes:
[0011] Preprocessing the sound signal to obtain a processed sound signal;
[0012] According to the processed sound signal, it is determined whether a burst sound signal exists in the sound signal.
[0013] Optionally, determining whether a burst sound signal exists in the sound signal according to the processed sound signal includes:
[0014] When the maximum amplitude of the processed sound signal is greater than or equal to the amplitude threshold, it is determined that a burst sound signal exists in the sound signal.
[0015] Optionally, the preprocessing the sound signal to obtain a processed sound signal includes:
[0016] Performing denoising on the sound signal to obtain a denoised sound signal;
[0017] Dividing the denoised sound signal into a plurality of sub-sound signal segments;
[0018] Performing frequency domain conversion processing on the multiple sub-sound signal segments to obtain frequency domain sound signals;
[0019] Performing filtering processing on the frequency domain sound signal to obtain a filtered sound signal;
[0020] The filtered sound signal is subjected to time domain conversion processing to obtain a time domain sound signal as the processed sound signal.
[0021] Optionally, before identifying whether a burst sound signal exists in the sound signal, the method further includes:
[0022] Separating and processing the sound signal to obtain an effective sound signal and a noise signal;
[0023] Determining a signal-to-noise ratio of the sound signal according to the effective sound signal and the noise signal;
[0024] When the signal-to-noise ratio is greater than or equal to a signal-to-noise ratio threshold, a step of identifying whether a burst sound signal exists in the sound signal is performed.
[0025] Optionally, determining a signal-to-noise ratio of the sound signal according to the effective sound signal and the noise signal includes:
[0026] The difference between the signal strength of the effective sound signal and the signal strength of the noise signal is used as the signal-to-noise ratio of the sound signal.
[0027] Preferably, before executing the step of acquiring the sound signal collected by the mechanical wave sensor when the acceleration value is greater than or equal to the acceleration threshold, the method further includes:
[0028] When the acceleration value is greater than or equal to the acceleration threshold, obtaining an angular velocity value of the smart wearable device collected by an angular velocity sensor;
[0029] When the angular velocity value is greater than or equal to the angular velocity threshold, the step of acquiring the sound signal collected by the mechanical wave sensor is performed.
[0030] Optionally, after determining that the smart wearable device is in a falling state, the method further includes:
[0031] Output drop prompt information.
[0032] According to the second aspect of the present application, a fall detection device is also provided, including a processor and a memory, wherein the memory is used to store executable computer instructions; the processor is used to execute the detection method described in the first aspect according to the control of the executable computer instructions.
[0033] According to a third aspect of the present application, there is also provided a smart wearable device, comprising:
[0034] An acceleration sensor, a mechanical wave sensor, and a fall detection device as described in the second aspect;
[0035] Wherein, the acceleration sensor is used to collect the acceleration value of the smart wearable device and send it to the fall detection device;
[0036] The mechanical wave sensor is used to collect sound signals and send them to the fall detection device.
[0037] One of the beneficial effects of the present application is that, by acquiring the acceleration value of the smart wearable device collected by the acceleration sensor, when the acceleration value is greater than or equal to the acceleration threshold, the sound signal collected by the mechanical wave sensor is acquired, and it is identified whether there is a burst sound signal in the sound signal. When there is a burst sound signal in the sound signal, it is determined that the smart wearable device is in a falling state. In this way, the posture change of the smart wearable device can be judged by the acceleration value first, and when it is judged that the smart wearable device may have a falling event, the sound signal is acquired to judge whether there is a burst sound in the sound signal. It can be achieved by combining the acceleration value and the sound signal to comprehensively judge whether the smart wearable device has fallen, thereby improving the accuracy of fall detection. In addition, since there is a burst sound when an object falls, by adding the judgment of the burst sound signal, it is possible to avoid misjudgment when performing fall detection only by the acceleration value, greatly increasing the accuracy of fall detection.
[0038] Other features and advantages of the present application will become apparent from the following detailed description of exemplary embodiments of the present application with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with the description, serve to explain the principles of the application.
[0040] Figure 1is a schematic diagram of the hardware structure of a smart wearable device according to an embodiment of the present application;
[0041] Figure 2 is a flow chart of a fall detection method according to an embodiment of the present application;
[0042] Figure 3 is a flow chart of a fall detection method according to another embodiment of the present application;
[0043] Figure 4 is a schematic structural diagram of a fall detection device according to an embodiment of the present application;
[0044] Figure 5 It is a schematic diagram of the structure of a smart wearable device according to an embodiment of the present application. DETAILED DESCRIPTION
[0045] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present application.
[0046] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.
[0047] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.
[0048] In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.
[0049] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.
[0050] <Hardware Configuration>
[0051] like Figure 1 As shown, a block diagram of the hardware configuration of the smart wearable device 100 provided in an embodiment of the present application.
[0052] See also Figure 1 As shown, the smart wearable device 100 includes a fall detection device 1000, an acceleration sensor 2000, and a mechanical wave sensor 3000. The acceleration sensor 2000 is communicatively connected to the fall detection device 1000, and the mechanical wave sensor 3000 is communicatively connected to the fall detection device 1000.
[0053] The smart wearable device 100 can be a smart watch, a bracelet, glasses, headphones, etc., which is not limited here.
[0054] The fall detection device 1000 may include but is not limited to a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a speaker 1700, a microphone 1800, and the like. The processor 1100 may be a central processing unit CPU, a graphics processing unit GPU, a microprocessor MCU, and the like, and is used to execute a computer program, which may be written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, and the like. The memory 1200 may include, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, and the like. The interface device 1300 may include, for example, a USB interface, a serial interface, a parallel interface, and the like. The communication device 1400 may, for example, be capable of wired communication using an optical fiber or a cable, or wireless communication, and may specifically include WiFi communication, Bluetooth communication, 2G / 3G / 4G / 5G communication, and the like. The display device 1500 may be, for example, a liquid crystal display screen, a touch display screen, and the like. The input device 1600 may include, for example, a touch screen, a keyboard, a somatosensory input, and the like. The speaker 1700 is used to output audio signals. The microphone 1800 is used to collect audio signals.
[0055] As used in the embodiments of the present disclosure, the memory 1200 of the drop detection device 1000 is used to store a computer program, which is used to control the processor 1100 to operate to implement the method according to the embodiments of the present disclosure. A technician can design the computer program according to the scheme disclosed in the present disclosure. How the computer program controls the processor to operate is well known in the art, so it will not be described in detail here. The drop detection device 1000 can be installed with an intelligent operating system (such as Windows, Linux, Android, IOS, etc.) and application software.
[0056] It should be understood by those skilled in the art that although Figure 1 , multiple devices of the fall detection device 1000 are shown, but the fall detection device 1000 of the embodiment of the present disclosure may only involve some of the devices, for example, only the processor 1100 and the memory 1200, etc.
[0057] The acceleration sensor 2000 is used to collect the acceleration value of the smart wearable device 100 and send it to the fall detection device 1000.
[0058] Exemplarily, the acceleration sensor may be an accelerometer, a MEMS accelerometer, a piezoelectric accelerometer, etc.
[0059] The mechanical wave sensor 3000 is used to collect sound signals and send them to the fall detection device 1000 .
[0060] Exemplarily, the mechanical wave sensor may be a sound sensor, a vibration sensor, or the like.
[0061] In one embodiment, the smart wearable device 100 further includes an angular velocity sensor for collecting the angular velocity of the smart wearable device and sending it to the fall detection device 1000, so that the fall detection device 1000 determines the posture of the smart wearable device based on the angular velocity.
[0062] The angular velocity sensor may be, for example, a gyroscope, a laser gyroscope, a fiber optic gyroscope, or the like.
[0063] It should be understood that although Figure 1 Only one drop detection device 1000, one acceleration sensor 2000, and one mechanical wave sensor 3000 are shown, but this does not mean that their respective numbers are limited. The smart wearable device may include multiple drop detection devices 1000, multiple acceleration sensors 2000, and multiple mechanical wave sensors 3000.
[0064] In the above description, the technician can design instructions according to the solution provided by the present disclosure. How instructions control the processor to operate is well known in the art, so it will not be described in detail here.
[0065] Figure 1 The smart wearable device shown is illustrative only and is in no way intended to limit the present disclosure, its application, or use.
[0066] <Method Example>
[0067] Figure 2 is a flow chart of a fall detection method according to an embodiment of the present application, which is applied to Figure 1 The smart wearable device shown can be specifically implemented by the fall detection device 1000.
[0068] according to Figure 2 As shown, the fall detection method of this embodiment may include the following steps S210 to S240:
[0069] Step S210, obtaining the acceleration value of the smart wearable device collected by the acceleration sensor.
[0070] When the smart wearable device is in a normal wearing state, its acceleration value will fluctuate within a relatively stable range. Once the device starts to fall, the resultant acceleration of the smart wearable device in the three axes of x, y, and z will change rapidly, exceed the acceleration value range, and then gradually decrease after a certain period of time. Based on this, the acceleration value can be collected to determine the posture change of the smart wearable device.
[0071] In this embodiment, the acceleration sensor can be, for example, an accelerometer. In this case, the acceleration value of the smart wearable device collected by the accelerometer is the linear acceleration of the smart wearable device in three-dimensional space (the resultant acceleration of the object in the three axes of x, y, and z), that is, the rate of change of velocity.
[0072] The acceleration sensor may also be other types of sensors, such as a capacitive accelerometer, a piezoelectric accelerometer, etc.
[0073] Step S220: When the acceleration value is greater than or equal to the acceleration threshold, obtain the sound signal collected by the mechanical wave sensor.
[0074] In this embodiment, the acceleration threshold is related to factors such as the characteristics of the smart wearable device, the usage environment, and the required sensitivity, and multiple aspects need to be considered to set the acceleration threshold.
[0075] The acceleration threshold may be a maximum value or an effective value of acceleration values obtained from multiple drop tests on the smart wearable device.
[0076] Exemplarily, the acceleration threshold is the effective value of the acceleration value obtained from n drop experiments on the smart wearable device. That is to say, different drop conditions of the smart wearable device are simulated by experiments, and the measurement data of the accelerometer is recorded. Under the premise of valid data (excluding abnormal measurement data), the acceleration threshold is obtained by performing root mean square processing on different data. Correspondingly, the calculation formula of the acceleration threshold is as follows:
[0077]
[0078] Where n is the number of drop tests, x 1 , x 2 ,…,x n is the acceleration value corresponding to the nth drop test.
[0079] It should be noted that step S210 and step S220 are essentially to collect the acceleration value of the smart wearable device in real time through the acceleration sensor, and compare the real-time collected acceleration value with the acceleration threshold. When the acceleration value is greater than or equal to the acceleration threshold, it is considered that the smart wearable device may have a fall event. When a smart wearable device falls, it generally produces a certain burst sound, and the burst sound will produce a pulse signal with a relatively large vibration amplitude, and even signal clipping. That is, the burst sound is a sound that is very different from the ambient noise. Based on this, the sound signal can be collected by the mechanical wave sensor, so as to further determine whether the smart wearable device has a fall event based on the sound signal.
[0080] The mechanical wave sensor may be a sound sensor or a vibration sensor.
[0081] Step S230: Identify whether there is a burst sound signal in the sound signal.
[0082] In this embodiment, there are multiple ways to identify whether there is a burst sound in the sound signal, such as energy threshold detection of the sound signal, waveform analysis of the sound signal, peak detection of the sound signal, machine learning algorithm, etc. The method of identifying burst sounds in the sound signal is not limited here.
[0083] Energy threshold detection of sound signals, that is, setting an energy threshold, when the energy of the detected sound signal exceeds the energy threshold, it is considered that there is a burst sound in the sound signal. The energy threshold can be set based on the sound signal energy level of the smart wearable device under normal use conditions.
[0084] Waveform analysis of sound signals, that is, analyzing the waveform characteristics of sound signals, such as pulse width, rise time and fall time. Burst sounds have specific waveform characteristics and can be identified by these characteristics.
[0085] The machine learning algorithm identifies the burst sound in the sound signal, that is, using a machine learning algorithm, such as a support vector machine (SVM), a neural network or a deep learning model, to learn the characteristics of the burst sound signal through a training data set, and then classify and identify the real-time sound signal.
[0086] In some embodiments, the step S230 of identifying whether there is a burst sound signal in the sound signal includes: steps S2301 to S2302.
[0087] Step S2301, preprocessing the sound signal to obtain a processed sound signal.
[0088] In this embodiment, the preprocessing may be denoising, signal amplification, filtering, segmentation, etc. of the sound signal. Those skilled in the art should understand that the preprocessing may be a combination of one or more and is not limited here.
[0089] In some embodiments, the preprocessing of the sound signal in step S2301 to obtain a processed sound signal includes: steps SA1 to SA5.
[0090] Step SA1, denoising the sound signal to obtain a denoised sound signal.
[0091] Those skilled in the art should understand that denoising of sound signals is a conventional technical means in the art, and the denoising process will not be described in detail herein.
[0092] Step SA2: dividing the denoised sound signal into a plurality of sub-sound signal segments.
[0093] In this embodiment, the denoised sound signal is divided into smaller time periods or frames.
[0094] Exemplarily, the segmentation length can be set to 1024, that is, each time period or frame contains 1024 samples, which can provide good frequency resolution, and 1024 is a power of 2, which makes subsequent fast Fourier transform (FFT) calculations more efficient and facilitates further analysis of each time period or frame, thereby improving the accuracy of burst sound detection.
[0095] Step SA3: performing frequency domain conversion processing on the multiple sub-sound signal segments to obtain frequency domain sound signals.
[0096] In this embodiment, a plurality of sub-sound signals are converted from the time domain to the frequency domain to obtain frequency domain sound signals.
[0097] Exemplarily, the plurality of sub-sound signals may be converted from the time domain to the frequency domain by Fast Fourier Transform (FFT).
[0098] Step SA4: filter the frequency domain sound signal to obtain a filtered sound signal.
[0099] In this embodiment, the frequency components of the frequency domain sound signal are used for filtering, so that the signal of a specific frequency can be filtered out.
[0100] Step SA5, performing time domain conversion processing on the filtered sound signal to obtain a time domain sound signal as the processed sound signal.
[0101] In this embodiment, the filtered sound signal can be converted from the frequency domain back to the time domain through Inverse Fourier Transform (IFT).
[0102] Those skilled in the art should know that in signal processing, Fourier transform (FT) and inverse Fourier transform (IFT) are a pair of commonly used transforms, which are used to convert signals from the time domain to the frequency domain and from the frequency domain back to the time domain. Therefore, the specific methods of Fourier transform and inverse Fourier transform are not described here.
[0103] Step S2302: Determine whether there is a burst sound signal in the sound signal according to the processed sound signal.
[0104] In this embodiment, by identifying whether there is a burst sound signal in the processed sound signal, compared with identifying the unprocessed sound signal, the impact of noise on burst sound recognition can be reduced, the accuracy of burst sound detection can be improved, and the accuracy of fall detection can be improved.
[0105] In some embodiments, determining whether there is a burst sound signal in the sound signal according to the processed sound signal in step S2302 includes:
[0106] When the maximum amplitude of the processed sound signal is greater than or equal to the amplitude threshold, it is determined that a burst sound signal exists in the sound signal.
[0107] The amplitude threshold may be determined according to the maximum amplitude of a burst sound signal collected in a historical drop experiment of the smart wearable device.
[0108] For example, the maximum amplitude of the sound signal in each time period or frame may be compared to see whether it is greater than or equal to an amplitude threshold, thereby determining whether there is a sound burst signal in the sound signal, thereby improving the accuracy of sound burst detection.
[0109] For another example, the maximum amplitude of the processed sound signal may be identified first, and then the maximum amplitude may be compared with an amplitude threshold. When the maximum amplitude is greater than or equal to the amplitude threshold, it is determined that a burst sound signal exists in the sound signal.
[0110] Step S240: When there is a burst sound signal in the sound signal, determine that the smart wearable device is in a falling state.
[0111] In this embodiment, when a burst sound signal is further detected in the sound signal, it is determined that the smart wearable device is in a falling state.
[0112] In some embodiments, before identifying whether a burst sound signal exists in the sound signal, the method further includes: steps S310 to S330.
[0113] Step S310, separating the sound signal to obtain a valid sound signal and a noise signal.
[0114] In this embodiment, the separation process may be frequency domain filtering, time domain filtering, principal component analysis, machine learning method, etc., which is not limited here.
[0115] The effective sound signal may be other types of sound signals except for the noise signal.
[0116] It should be noted that the effective sound signal here may be a burst sound signal or other types of sound signals, which are not limited here.
[0117] The noise signal may be a noise signal of the surrounding environment.
[0118] Step S320: determining a signal-to-noise ratio of the sound signal according to the effective sound signal and the noise signal.
[0119] In this embodiment, the ratio of the signal strength of the effective sound signal and the noise signal can be used as the signal-to-noise ratio of the sound signal, or the difference between the signal strength of the effective sound signal and the noise signal can be used as the signal-to-noise ratio of the sound signal, which is not limited here.
[0120] In some embodiments, determining the signal-to-noise ratio of the sound signal according to the effective sound signal and the noise signal includes:
[0121] The difference between the signal strength of the effective sound signal and the signal strength of the noise signal is used as the signal-to-noise ratio of the sound signal.
[0122] For example, the signal strength of the noise signal in the sound signal collected by the sound sensor at a certain time period is a 1 , the signal strength of the effective sound signal strength is T 1 , then T 1 -a 1 is the signal-to-noise ratio of the sound signal.
[0123] Step S330 , when the signal-to-noise ratio is greater than or equal to a signal-to-noise ratio threshold, executing a step of identifying whether a burst sound signal exists in the sound signal.
[0124] For example, the signal-to-noise ratio may be the difference between the signal strength of the effective sound signal and the signal strength of the noise signal. In this case, the signal-to-noise ratio threshold may be expressed as T 1 -a 1≥10dB, that is, 10dB is the signal-to-noise ratio threshold, T 1 is the signal strength of the effective sound signal, a 1 It is the signal strength of the noise signal, that is, when the difference between the signal strength of the effective sound signal and the signal strength of the noise signal is greater than or equal to the signal-to-noise ratio threshold, it means that the sound signal has a sufficient signal-to-noise ratio for burst sound detection. Otherwise, the sound signal cannot be detected for burst sound.
[0125] Although the falling process of smart wearable devices mainly involves linear motion, occasionally the device will also have a certain rotational motion when it falls. In order to avoid misjudgment of the state of the smart wearable device and reduce the power consumption of burst sound detection, the angular velocity changes of the three axes of the device can be obtained by adding an angular velocity sensor. The angular velocity changes can assist in judging the posture changes of the device and reduce misjudgment of the device state.
[0126] Based on this, in some embodiments, before executing the step of acquiring the sound signal collected by the mechanical wave sensor in step S220 when the acceleration value is greater than or equal to the acceleration threshold, the method further includes: steps S410 to S420.
[0127] Step S410: When the acceleration value is greater than or equal to an acceleration threshold, an angular velocity value of the smart wearable device acquired by an angular velocity sensor is obtained.
[0128] In this embodiment, the angular velocity sensor may be a gyroscope, a laser gyroscope, etc., which is not limited here.
[0129] Step S420: When the angular velocity value is greater than or equal to the angular velocity threshold, obtain the sound signal collected by the mechanical wave sensor.
[0130] In this embodiment, the angular velocity threshold is related to factors such as the characteristics of the smart wearable device, the usage environment, and the required sensitivity, and multiple aspects need to be considered to set the angular velocity threshold.
[0131] The angular velocity threshold may be a maximum value or an effective value of the angular velocity values obtained from multiple drop experiments on the smart wearable device.
[0132] Exemplarily, the angular velocity threshold is the effective value of the angular velocity value obtained from n drop experiments on the smart wearable device. That is to say, different drop conditions of the smart wearable device are simulated by experiments, and the measurement data of the gyroscope is recorded. Under the premise of valid data (excluding abnormal measurement data), the angular velocity threshold is obtained by performing root mean square processing on different data. Correspondingly, the calculation formula of the angular velocity threshold is as follows:
[0133]
[0134] Where n is the number of drop tests, x 1 , x 2 ,…,x n is the angular velocity value corresponding to the nth drop test.
[0135] It should be noted that here the angular velocity value and acceleration value of the smart wearable device are first collected in real time through the angular velocity sensor and the acceleration sensor. When it is judged that the acceleration value is greater than or equal to the acceleration threshold, it is then judged whether the angular velocity value is greater than or equal to the angular velocity threshold. When the angular velocity value is greater than or equal to the angular velocity threshold, the mechanical wave sensor is started to collect the sound signal to judge the burst sound.
[0136] By adding an angular velocity sensor to assist in determining the posture change of the smart wearable device, compared with determining the posture change of the smart wearable device only by using an acceleration sensor, misjudgment of the state of the smart wearable device can be reduced.
[0137] In some embodiments, after determining in step S240 that the smart wearable device is in a falling state, the method further includes:
[0138] Output drop prompt information.
[0139] In this embodiment, the drop prompt information may be a voice prompt, a text prompt, an image prompt, etc., which is not limited here.
[0140] For example, when it is determined that the smart wearable device is in a falling state, an alarm reminder can be issued to remind the user in the first place, thereby avoiding the risk of loss and reducing the user's anxiety.
[0141] According to the embodiments of the present application, the posture change of the smart wearable device can be first determined by the acceleration value. When it is determined that the smart wearable device may have a fall event, the sound signal can be obtained to determine whether there is a burst sound in the sound signal. This can achieve a comprehensive judgment of whether the smart wearable device has fallen by combining the acceleration value and the sound signal, thereby improving the accuracy of fall detection. In addition, since there is a burst sound when an object falls, by adding the judgment of the burst sound signal, it is possible to avoid misjudgment when performing fall detection only by using the acceleration value, thereby greatly increasing the accuracy of fall detection.
[0142] Figure 3 A flow chart of a fall detection method according to another embodiment of the present application is shown. Figure 3 As shown, the fall detection method includes steps S1 to S11.
[0143] Step S1, obtaining the acceleration value of the smart wearable device collected by the acceleration sensor.
[0144] In this step, the acceleration sensor may be an accelerometer, and the acceleration value is a linear acceleration value.
[0145] Step S2, whether the acceleration value is greater than or equal to the acceleration threshold; if so, execute step S3, if not, execute step S1.
[0146] In this embodiment, the acceleration threshold may be a maximum value or an effective value of the acceleration value of the smart wearable device in a historical drop experiment.
[0147] Step S3, obtaining the angular velocity value of the smart wearable device collected by the angular velocity sensor.
[0148] In this embodiment, the angular velocity sensor may be a gyroscope or the like.
[0149] Step S4, whether the angular velocity value is greater than or equal to the angular velocity threshold; if so, execute step S5, if not, execute step S1.
[0150] In this embodiment, the angular velocity threshold may be a maximum value or an effective value of the angular velocity value of the smart wearable device in a historical drop experiment.
[0151] Step S5, obtaining the sound signal collected by the mechanical wave sensor.
[0152] In this embodiment, the mechanical wave sensor may be a vibration sensor or a sound sensor.
[0153] Step S6, separating the sound signal to obtain a valid sound signal and a noise signal.
[0154] In this embodiment, the effective sound signal may be other types of signals in the sound signal except the noise signal.
[0155] Step S7, determining the signal-to-noise ratio of the sound signal according to the effective sound signal and the noise signal.
[0156] In this embodiment, the signal-to-noise ratio may be determined according to the signal strength ratio of the effective sound signal and the noise signal, or may be determined according to the signal strength difference between the effective sound signal and the noise signal, which is not limited here.
[0157] Step S8, whether the signal-to-noise ratio is greater than or equal to the signal-to-noise ratio threshold; if so, execute step S9, if not, execute step S1.
[0158] In this embodiment, when the signal-to-noise ratio is greater than or equal to the signal-to-noise ratio threshold, it means that the sound signal meets the signal-to-noise ratio requirement of burst sound detection, and then burst sound detection for the sound signal is started, that is, step S9 and step S10 are executed.
[0159] When the corresponding signal-to-noise ratio is determined according to the signal strength difference between the effective sound signal and the noise signal, the signal-to-noise ratio threshold may be, for example, 10 dB.
[0160] Step S9: pre-process the sound signal to obtain a processed sound signal.
[0161] In this embodiment, the preprocessing may be denoising, filtering and the like.
[0162] Step S10, whether the maximum amplitude of the processed sound signal is greater than or equal to the amplitude threshold; if so, execute step S11, if not, execute step S1.
[0163] In this embodiment, the amplitude threshold can be determined based on the maximum amplitude of the burst sound signal collected in the historical drop experiment of the smart wearable device, that is, when the maximum amplitude of the processed sound signal is greater than or equal to the amplitude threshold, it is determined that there is a burst sound in the sound signal.
[0164] Step S11, outputting falling prompt information.
[0165] It should be noted that, for the explanation of the method steps in this embodiment, reference can be made to the explanation of the corresponding method steps in the above method embodiment, which will not be elaborated here.
[0166] According to the embodiments of the present application, by jointly judging the posture change of the smart wearable device by an acceleration sensor and an angular velocity sensor, the accuracy of posture judgment can be improved. Moreover, when it is judged that the posture change of the smart wearable device may be caused by the device falling, the accuracy of fall detection can be improved by performing burst sound detection on the sound signal to further judge whether a fall event has occurred in the smart wearable device.
[0167] In some embodiments, Figure 4 As shown, a fall detection device 400 is also provided, including a processor 410 and a memory 420, the memory 420 is used to store executable computer instructions; the processor 410 is used to execute the fall detection method described in any of the above method embodiments according to the control of the executable computer instructions.
[0168] In some embodiments, Figure 5 As shown, a smart wearable device 500 is also provided, including: an acceleration sensor 510, a mechanical wave sensor 520 and a fall detection device 530;
[0169] The acceleration sensor 510 is used to collect the acceleration value of the smart wearable device and send it to the fall detection device 530;
[0170] The mechanical wave sensor 520 is used to collect sound signals and send them to the fall detection device 530.
[0171] In one embodiment, the fall detection device 530 may be as follows: Figure 1 or Figure 4 The fall detection device shown.
[0172] The present application may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present application.
[0173] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.
[0174] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.
[0175] The computer program instructions for performing the operation of the present application can be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions can be executed completely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of a computer-readable program instruction to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA), the electronic circuit can execute a computer-readable program instruction, thereby realizing various aspects of the present application.
[0176] Various aspects of the present application are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.
[0177] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0178] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0179] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.
[0180] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present application is defined by the appended claims.
Claims
1. A fall detection method, applied to a smart wearable device, characterized in that: include: Get the acceleration value of the smart wearable device collected by the acceleration sensor; When the acceleration value is greater than or equal to the acceleration threshold, obtaining a sound signal collected by the mechanical wave sensor; Identifying whether there is a burst sound signal in the sound signal; When there is a burst sound signal in the sound signal, it is determined that the smart wearable device is in a falling state.
2. The method according to claim 1, characterized in that The identifying whether there is a burst sound signal in the sound signal includes: Preprocessing the sound signal to obtain a processed sound signal; According to the processed sound signal, it is determined whether a burst sound signal exists in the sound signal.
3. The method according to claim 2, characterized in that The step of determining whether there is a burst sound signal in the sound signal according to the processed sound signal comprises: When the maximum amplitude of the processed sound signal is greater than or equal to the amplitude threshold, it is determined that a burst sound signal exists in the sound signal.
4. The method according to claim 2, characterized in that: The preprocessing of the sound signal to obtain a processed sound signal includes: Performing denoising on the sound signal to obtain a denoised sound signal; Dividing the denoised sound signal into a plurality of sub-sound signal segments; Performing frequency domain conversion processing on the multiple sub-sound signal segments to obtain frequency domain sound signals; Performing filtering processing on the frequency domain sound signal to obtain a filtered sound signal; The filtered sound signal is subjected to time domain conversion processing to obtain a time domain sound signal as the processed sound signal.
5. The method according to claim 1, characterized in that Before identifying whether there is a burst sound signal in the sound signal, the method further includes: Separating and processing the sound signal to obtain an effective sound signal and a noise signal; Determining a signal-to-noise ratio of the sound signal according to the effective sound signal and the noise signal; When the signal-to-noise ratio is greater than or equal to a signal-to-noise ratio threshold, a step of identifying whether a burst sound signal exists in the sound signal is performed.
6. The method according to claim 5, characterized in that The determining the signal-to-noise ratio of the sound signal according to the effective sound signal and the noise signal comprises: The difference between the signal strength of the effective sound signal and the signal strength of the noise signal is used as the signal-to-noise ratio of the sound signal.
7. The method according to claim 1, characterized in that Before executing the step of acquiring the sound signal collected by the mechanical wave sensor when the acceleration value is greater than or equal to the acceleration threshold, the method further includes: When the acceleration value is greater than or equal to the acceleration threshold, obtaining an angular velocity value of the smart wearable device collected by an angular velocity sensor; When the angular velocity value is greater than or equal to the angular velocity threshold, the step of acquiring the sound signal collected by the mechanical wave sensor is performed.
8. The method according to claim 1, characterized in that After determining that the smart wearable device is in a falling state, the method further includes: Output drop prompt information.
9. A fall detection device, characterized in that: It comprises a processor and a memory, wherein the memory is used to store executable computer instructions; the processor is used to execute the detection method according to any one of claims 1 to 8 under the control of the executable computer instructions.
10. A smart wearable device, characterized in that: include: An acceleration sensor, a mechanical wave sensor, and a fall detection device as claimed in claim 9; Wherein, the acceleration sensor is used to collect the acceleration value of the smart wearable device and send it to the fall detection device; The mechanical wave sensor is used to collect sound signals and send them to the fall detection device.
Citation Information
Cited By
Loudspeaker control method and device, electronic equipment and storage medium
CN120416745A
High-altitude falling detection method and system based on mobile terminal multi-sensor fusion
CN120974415A
