Fall detection method, wearable device and storage medium

Abstract

The invention discloses a tumble detection method, wearable equipment and a storage medium, relates to the technical field of tumble detection, and discloses a tumble detection method applied to the wearable equipment, the wearable equipment comprises an acceleration sensor and at least one other sensor except the acceleration sensor, the tumble detection method comprises the following steps: acquiring acceleration data acquired by an acceleration sensor based on a time sequence; if the acceleration data accord with the free falling acceleration performance in the first time period and accord with the impact rebound acceleration performance in the second time period, it is judged that a falling impact event is detected; in response to the falling impact event, obtaining a falling detection result determined based on detection data collected by other sensors; and if the tumble detection result is that the tumble event exists, triggering a tumble event response process. On the basis, when falling impact is detected, detection and identification are carried out based on other sensor parameters, so that the falling detection accuracy of impact caused by falling is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fall detection, in particular to a fall detection method, a wearable device and a storage medium. BACKGROUND

[0002] Traditional fall detection devices such as wristbands, smart watches and the like rely on wrist movement data for fall judgment, which is easy to identify hand actions such as waving and ball hitting actions as falls, or misreport due to actions such as running and sudden stopping, and rapid sitting. Therefore, the current wearable fall detection device has the defect of low detection accuracy.

[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide a fall detection method, a wearable device and a storage medium, aiming at solving the technical problem of low detection accuracy of the current wearable fall detection device.

[0005] To achieve the above purpose, the present application provides a fall detection method applied to a wearable device, wherein the wearable device comprises an acceleration sensor and at least one other sensor in addition to the acceleration sensor. The fall detection method comprises: obtaining acceleration data collected by the acceleration sensor in time sequence; if the acceleration data conforms to the free-fall acceleration performance in the first period and conforms to the impact and rebound acceleration performance in the second period, it is determined that a falling impact event is detected; in response to the falling impact event, obtaining a fall detection result determined based on the detection data collected by the other sensor; if the fall detection result is that there is a fall event, triggering a fall event response process.

[0006] In an embodiment, the other sensor comprises a barometer, a gyroscope and a heart rate sensor, and the step of obtaining a fall detection result determined based on the detection data collected by the other sensor in response to the falling impact event comprises: obtaining angular velocity data collected by the gyroscope in time sequence, height data corresponding to air pressure change data collected by the barometer in time sequence, and heart rate data collected by the heart rate sensor in time sequence; determining a posture detection result according to the angular velocity data, determining a height detection result according to the height data, and determining a heart rate detection result according to the heart rate data; If the posture detection result is posture abnormality, the height detection result is height abnormality, and / or the heart rate detection result is heart rate abnormality, it is determined that the fall detection result is that a fall event exists.

[0007] In an embodiment, after the step of acquiring the angular velocity data collected in time sequence by the gyroscope, the height data corresponding to the air pressure change data collected in time sequence by the barometer, and the heart rate data collected in time sequence by the heart rate sensor, the fall detection method further comprises: acquiring a multi-modal fusion result corresponding to the angular velocity data, the height data, and the heart rate data; If the multi-modal fusion result meets a fall probability, it is determined that the fall detection result is that a fall event exists.

[0008] In an embodiment, the step of determining a posture detection result according to the angular velocity data, determining a height detection result according to the height data, and determining a heart rate detection result according to the heart rate data comprises: If the angular change rate of the angular velocity data is greater than a preset change rate, it is determined that the posture detection result is posture abnormality; If the height data is greater than or equal to a preset height, it is determined that the height detection result is height abnormality; If the heart rate data corresponds to a sudden increase amount greater than a preset sudden increase amount, or a blood oxygen decrease amount associated with the heart rate data is greater than a preset proportion, it is determined that the heart rate detection result is heart rate abnormality.

[0009] In an embodiment, after the step of acquiring the acceleration data collected in time sequence by the acceleration sensor, the fall detection method further comprises: If, in the first time period, the acceleration modulus value of the acceleration data in the gravity direction is less than a first modulus value, it is determined that the acceleration data in the first time period meets the free-fall acceleration performance; If, in the second time period, the peak value of the acceleration modulus value is greater than a second modulus value, it is determined that the acceleration data in the second time period meets the impact-rebound acceleration performance, wherein the second modulus value is greater than the first modulus value.

[0010] In an embodiment, after the step of, if, in the first time period, the acceleration modulus value of the acceleration data in the gravity direction is less than a first modulus value, it is determined that the acceleration data in the first time period meets the free-fall acceleration performance, the fall detection method further comprises: If the peak value of the acceleration modulus value is less than a third modulus value, the muscle vibration frequency of the wearable area is acquired, and the third modulus value is less than the second modulus value. determining that the acceleration data in the second time period meets the impact rebound acceleration performance.

[0011] In an embodiment, after the step of obtaining the acceleration data collected by the acceleration sensor in time sequence, the fall detection method further comprises: determining an acceleration change curve of the acceleration data in the gravity direction; if the acceleration change curve meets a preset curve, determining that the falling impact event is detected.

[0012] In an embodiment, if the fall detection result is that there is a fall event, the step of triggering a fall event response process comprises: if the fall detection result is that there is a fall event, determining an impact level according to the acceleration change curve; performing a voice inquiry action based on the impact level, and performing a fall alarm action when no response voice is received within a preset time period; if the response voice is received within the preset time period, performing a response action corresponding to the response voice.

[0013] In addition, to achieve the above-mentioned purposes, the present application also proposes a wearable device, which comprises a memory, a processor and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the fall detection method as described above.

[0014] In addition, to achieve the above-mentioned purposes, the present application also proposes a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the fall detection method as described above.

[0015] The one or more technical solutions proposed in the present application have at least the following technical effects: By obtaining the acceleration data collected by the acceleration sensor, and determining that the wearable device has a falling impact when the acceleration data meets the free fall and impact rebound performance, and then obtaining the fall detection result corresponding to the detection data collected by other sensors based on the fall detection result, the user is accurately identified whether a fall actually occurs when the wearable device has a falling impact, rather than detecting when a free fall motion is detected, thereby improving the accuracy of fall detection and identification by the wearable device, and providing a reliable basis for subsequent corresponding fall prompt measures, improving the detection accuracy while ensuring the practicality and effectiveness of the wearable device in user safety. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate an embodiment consistent with the present application and, together with the description, serve to explain the principles of the application.

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings required by the embodiments or the prior art description will be briefly introduced. Obviously, for those skilled in the field, other drawings can also be obtained based on these drawings without creative labor.

[0018] Figure 1 Functional module diagram of the wearable device of the fall detection method of the present application; Figure 2 Module interaction schematic diagram of the wearable device of the fall detection method of the present application; Figure 3 Flowchart schematic diagram provided by the first embodiment of the fall detection method of the present application; Figure 4 Flowchart schematic diagram provided by the second embodiment of the fall detection method of the present application; Figure 5 Acceleration parameter change over time schematic diagram of the fall detection method of the present application; Figure 6 Flowchart schematic diagram of the optional implementation of the fall detection method obtained by combining various embodiments of the present application; Figure 7 Device structure schematic diagram of the hardware running environment involved in the fall detection method in the embodiments of the present application.

[0019] The purpose implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0021] Traditional fall detection devices such as wristbands, smart watches, etc. rely on wrist movement data for fall judgment, which is easy to identify hand actions such as waving and hitting balls as falls, or misreport through accelerometers due to running sudden stop, quick sitting and other actions. Therefore, the current wearable fall detection device has the defect of low detection accuracy.

[0022] The present application provides a solution to obtain acceleration data collected by an acceleration sensor based on time sequence; If the acceleration data conforms to the free-fall acceleration performance in the first period and conforms to the impact-rebound acceleration performance in the second period, it is determined that a falling impact event is detected. In response to the falling impact event, a fall detection result determined based on detection data collected by the other sensors is acquired; If the fall detection result is a fall event, a fall event response process is triggered.

[0023] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a wearable device, etc. that can realize the above functions. Wearable devices include bracelets, watches, and smart wireless earphones, etc.

[0024] In order to better understand the technical solutions of the present application, the following will be described in detail in conjunction with the drawings and specific embodiments.

[0025] Please refer to Figure 1 The wearable device includes a power management module, a sensor module, a data processing module, and an alarm module. The power management module dynamically allocates power controllers to each sensor of the sensor module. The sensors of the sensor module collect corresponding data and send the collected data to the data processing module for processing. When the data processing module detects that the data meets the alarm condition, the alarm module is used for alarm processing.

[0026] Specifically, please refer to Figure 2 The dynamic power manager of the power management module accesses each device in the sensor module. The sensor module includes a three-axis accelerometer for detecting acceleration, a gyroscope for detecting angular velocity data, a barometer for detecting height changes, an optical heart rate sensor for detecting heart rate, and a signal filtering unit for signal filtering processing. The sensor module also includes a signal filtering unit. The signal filtering unit filters the collected acceleration data, angular velocity data, height data, and heart rate data, eliminating interference noise. Then the filtered data is transmitted to the data processing module. The data processing module extracts the current corresponding parameters based on the feature extraction unit, including the acceleration module value, the angular velocity change rate, and the height difference. Then the decision unit is used to determine the fall probability, and the alarm module is triggered to alarm when the probability is high. The alarm module includes local alarm and remote notification alarm functions. Optionally, a local alarm can be performed based on a buzzer, and a remote alarm can be performed to the user's mobile phone or cloud device through a Bluetooth communication unit, including sending the GPS position and help information to the mobile phone to inform the user or the user's contact person, etc.

[0027] Optionally, in addition to Figure 2In addition to the illustrated sensor types, the sensor module also includes other modules, such as a sensor (not shown in the figure) for detecting muscle tremors of a wearing user, or other sensors for detecting physiological parameters of a wearing user, or an image acquisition module such as a camera, an ambient light detection module, and the like.

[0028] Based on this, the embodiments of the present application provide a fall detection method, applied to a wearable device, the wearable device comprising an acceleration sensor and at least one other sensor in addition to the acceleration sensor. The following takes a smart wireless earphone as an example to describe the embodiments of the present application and the following embodiments. Please refer to Figure 3 , Figure 3 The flowchart of the first embodiment of the fall detection method of the present application.

[0029] In the present embodiment, the fall detection method comprises steps S10-S40: Step S10, obtaining acceleration data collected by the acceleration sensor in time sequence.

[0030] In the present embodiment, the acceleration data collected by the acceleration sensor can be used to determine whether the earphone has a falling impact event. Therefore, it is necessary to obtain the acceleration data collected by the acceleration sensor in time sequence, which includes data in multiple directions such as the horizontal direction and the gravity direction.

[0031] Step S20, if the acceleration data meets the free-fall acceleration performance in the first period and meets the impact rebound acceleration performance in the second period, it is determined that a falling impact event is detected.

[0032] In the present embodiment, the change amount of the acceleration data collected by the earphone can be used to determine whether the earphone has a falling impact, i.e., to determine whether a falling impact event is detected. Generally, when the earphone has a falling acceleration, the falling impact detection is performed. Alternatively, when the earphone is provided with a camera, the change information of the image definition of the video frames collected by the earphone can be used to determine whether a falling impact event is detected. For example, if several frames of images are blurred within a short time, it is considered that a falling impact event is detected.

[0033] It should be noted that the second period is after the first period, and after the acceleration data meets the free-fall related performance, it is detected whether the change of the subsequent acceleration meets the impact rebound performance within the second period. The second period is less than the first period.

[0034] It can be understood that a conventional wearable device usually detects a change in the acceleration of the device and then combines other sensing data for secondary identification to make a fall prediction. However, in many non-fall actions in daily life, such as quickly lifting hands, jumping, going up and down stairs, and running, the wearable device worn by the user will produce obvious acceleration changes, which coincide with the acceleration characteristics when falling. If only the acceleration change is used as the starting point for judgment, a large number of non-fall scenes will be included in the detection range, and even if other sensor parameters are combined for screening, it is difficult to completely eliminate these disturbances, resulting in an increased misjudgment rate.

[0035] Therefore, the embodiment determines whether the earphone has a falling impact event by the free-fall acceleration performance in two different time periods and whether the acceleration has a rebound acceleration change related to rebound in the process, so as to use the falling impact event as a trigger condition for subsequent detection and judgment, thereby improving the detection accuracy.

[0036] Step S30, in response to the falling impact event, obtaining a fall detection result determined based on detection data collected by the other sensors.

[0037] In the embodiment, when the falling impact event is detected, it indicates that the earphone has a falling impact. Even if it is determined that a falling impact occurs, it cannot be directly considered that the user falls, because the falling impact of the wearable device is not directly equivalent to the imbalance of the user's body and falling, for example, the user bends over and hits a table or chair, causing the earphone to fall off, or the user moves, such as jumping, and the device falls off.

[0038] Therefore, after detecting the falling impact event, the data collected by the other sensors needs to be analyzed to improve the accuracy of the fall detection.

[0039] It should be noted that the other sensors and the acceleration sensor work together, that is, when the acceleration sensor collects data, the other sensors also collect data, so the detection data collected by the other sensors contains the data detected before and after the falling impact of the wearable device in terms of time span.

[0040] As an optional implementation, other sensors include a barometer, a gyroscope, and a heart rate sensor. The detection data collected by the barometer can be used to determine the height change of the earphones, the detection data collected by the gyroscope can be used to determine the angular velocity change of the earphones, and the detection data collected by the heart rate sensor can be used to determine the heart rate change of the user wearing the earphones. Therefore, the fall detection result is further determined in combination with the changes in these data. The data sampling amplitudes of the above parameters can be different, that is, the angular velocity data, height data, and heart rate data can be detected separately based on different time periods, and these time periods can be set based on actual needs. At the same time, among the above parameters, when at least one condition is met, the fall detection result can be determined as the presence of a fall event.

[0041] Optionally, the judgment can be made based on detection data collected by ambient light sensors, image sensors, etc. The ambient light sensor can obtain the ambient light detection results of the earphones and the image recognition results. If the image light detection result shows a lighting abnormality, such as a change from dark to bright, it indicates that the earphones have fallen off the ear. If the image recognition result shows a recognition abnormality, such as a blurred image and inability to recognize the image content, it indicates that the image is blurred due to difficulty in focusing during high-speed movement.

[0042] Optionally, the detection results of the above-mentioned sensors can be combined for analysis and judgment to improve the accuracy of fall detection.

[0043] Step S40: If the fall detection result indicates that a fall event has occurred, a fall event response process is triggered.

[0044] In this embodiment, the fall event response process is generally an alarm process, which can be executed based on voice inquiry, such as asking the status of the wearing user through a voice alarm prompt, and confirming the status of the wearing user based on the voice feedback result.

[0045] Optionally, an emergency alert message and location can be sent to the wearer's contacts, or a call for help can be automatically made. The response process can execute the above processing actions sequentially or asynchronously, and the order or association of the above processing actions is not limited in this application.

[0046] As an optional implementation, when the fall event response process is triggered based on the voice inquiry, the voice inquiry action can be performed to inquire the current situation of the user, such as whether the user needs help after falling down. It can be understood that if the user only falls down slightly and can stand up by himself, no alarm processing is needed. Therefore, if the response voice is received within the preset period, the response action corresponding to the response voice is performed, for example, the user falls down consciously and sends a voice control instruction to the wearable device to make the device perform the corresponding action, such as “dial the phone of user A and explain that the current situation is falling down”, or “nothing, I fell down by accident”, at this time, the wearable device does not perform the alarm action.

[0047] Optionally, if the response voice is not received, the fall alarm action is performed, such as automatic alarm, dialing a help phone and / or notifying an emergency contact and sending corresponding location information.

[0048] The embodiment provides a fall detection method. After acceleration data is collected based on an acceleration sensor, it is determined that the acceleration data satisfies free fall and impact rebound acceleration performance after free fall, the wearable device detects the falling impact, then detection data collected by other sensors is acquired, and a fall detection result is determined based on the collected detection data, so as to determine whether the falling impact is satisfied based on the acceleration, and the detection data of other sensors is analyzed, so as to improve the accuracy of fall detection.

[0049] Based on the first embodiment of the application, in the second embodiment of the application, the same or similar contents as the above first embodiment can be referred to the above introduction, and will not be described in detail. On this basis, please refer to Figure 4 , step S30 further includes steps S31-S33: Step S31, acquiring the angular velocity data collected by the gyroscope based on the time sequence, the height data corresponding to the air pressure change data collected by the barometer based on the time sequence, and the heart rate data collected by the heart rate sensor based on the time sequence.

[0050] In the embodiment, the data collected by the gyroscope, the barometer and the heart rate sensor contains data before and after the falling impact. In the process of determining each detection result, the time period corresponding to the detection parameter is not the same, for example, the angle change within 1 second needs to be determined, or the height change data is calculated based on the average height within 10 seconds before the falling impact and the current height within 5 seconds after the falling impact.

[0051] Therefore, the angular velocity data in the first preset period can be acquired; the average height in the second preset period before the falling impact and the current height after the third preset period after the falling impact are acquired, and the difference between the average height and the current height is taken as the height data; and the heart rate data after the fourth preset period after the falling impact is acquired. The above parameter acquisition actions can be synchronously performed.

[0052] For example, when it is detected that the wearable device is subjected to the falling attack, the angular velocity data in the first preset period, i.e., 1 second, is acquired, including the change rate of the pitch angle from the upright to the lying. For the height data, the average height in the second preset period of 10 seconds before the impact and the height parameter in the third preset period of 0-5 seconds after the impact are acquired, so as to calculate the difference between the average height and the current height, thereby obtaining the height data, and further, the heart rate change rate in the fourth preset period of 5 seconds can be acquired. Optionally, the blood oxygen decrease rate in 5 seconds can also be acquired.

[0053] It should be noted that the above parameters are only used for explanation and illustration, and are not limited to the present application, and the specific values can be set according to actual needs.

[0054] In the embodiment, the corresponding parameters are collected in different preset periods, so as to improve the accuracy of each parameter collection based on actual needs, and further improve the accuracy of the fall detection and recognition.

[0055] In step S32, the posture detection result is determined according to the angular velocity data, the height detection result is determined according to the height data, and the heart rate detection result is determined according to the heart rate data.

[0056] In the embodiment, in the process of determining each detection result, if the angular change rate of the angular velocity data in a period is greater than a preset change rate, it is determined that the posture detection result is posture abnormality. For example, in the angular velocity data in one second, the pitch angle changes from the upright (-30°-30°) to the lying / lying (>60° or <-60°), and the angle change rate is greater than the preset 50° / second, and it is determined that the posture detection result is posture abnormality.

[0057] Similarly, if the height after the falling impact is greater than or equal to a preset height, it is determined that the height detection result is height abnormality, for example, the height decrease after the impact is greater than or equal to the preset 0.5 meters, and the tolerance is 0.1 meters, and at this time, it is considered that the height is abnormal.

[0058] Further, if the heart rate data corresponds to a sudden increase greater than a preset sudden increase, or the heart rate data is associated with a blood oxygen decrease greater than a preset proportion, the heart rate detection result is determined to be abnormal. After the earphone falls and hits, it is detected that the heart rate of the wearing user suddenly increases by ≥ 20bpm within 5 seconds after the impact, and it is considered that the user's heart rate is abnormal, or based on the heart rate, it is determined that the blood oxygen decreases by ≥ 5%, and it is also considered that the heart rate is abnormal. The data sampling interval of the heart rate is 1 second. It can be understood that the earphone of the embodiment has a structure design such as an in-ear earphone, an ear clip earphone, etc. that prevents falling off. Even in vigorous exercise, it can be firmly attached and not easily displaced. Therefore, the wearable device is subject to a falling impact, and it is generally considered that the earphone is hit by the wearing user. Alternatively, the heart rate detection module of the earphone can use a high-precision optical sensor, etc. Even if it is temporarily separated from the skin during the falling process, it can accumulate data through continuous detection before and the last detection information at the separation moment, and judge the heart rate change trend through the algorithm. In other words, even if the earphone falls off, the heart rate change rate of the user can be detected before and after the impact.

[0059] It should be noted that the above parameters are only used for explanation and illustration, and are not limited to the present application.

[0060] Alternatively, after step S31, the data collected by other sensors can also be processed through a multi-modal fusion manner, and the falling detection result is determined to be a falling event based on the fusion output result. Specifically, the multi-modal fusion result corresponding to the angular velocity data, the height data and the heart rate data can be obtained, and if the multi-modal fusion result satisfies the falling probability, the falling detection result is determined to be a falling event. The multi-modal fusion manner can be a weighted summation manner.

[0061] Step S33, if the posture detection result is posture abnormality, the height detection result is height abnormality, and / or the heart rate detection result is heart rate abnormality, the falling detection result is determined to be a falling event.

[0062] In the embodiment, when it is determined that the posture data, the height data and / or the heart rate data collected by the earphone are abnormal, the wearing user is determined to be in a falling state when any of the above conditions is met. That is, when the posture detection result is posture abnormality, the height detection result is height abnormality, and / or the heart rate detection result is heart rate abnormality, the wearing user is determined to be in a falling state.

[0063] The embodiment provides a fall detection method. When a wearable device is determined to exist a falling impact through a motion parameter of an accelerometer, data detected by a gyroscope, a barometer and a heart rate sensor are combined to make further fall detection judgment, and when data changes of the gyroscope, the barometer and the heart rate sensor all meet detection conditions, it is judged that a wearing user is in a falling state, so that multi-dimensional fusion judgment of motion, posture, height and physiological signals is realized. Meanwhile, through a multi-level verification mechanism, grading confirmation of fall detection is realized, so as to improve detection accuracy.

[0064] Based on the first embodiment of the application, in the third embodiment of the application, the same or similar contents as the above first embodiment can be referred to the above introduction, and subsequent details will not be repeated. On this basis, after step S10, the fall detection method further includes steps S50-S60: Step S50, if the acceleration data in the first time period is less than the first modulus value, it is determined that the acceleration data in the first time period meets the free fall acceleration performance.

[0065] In the embodiment, when the wearing user falls, the acceleration parameter of the earphone generally meets the free fall motion state. Therefore, when the acceleration parameter changes, whether the current acceleration is the acceleration of free fall is judged based on the time sequence characteristics of the acceleration, so as to determine whether the acceleration of the wearable device meets the free fall detection.

[0066] Therefore, when judging whether the falling impact occurs based on the parameters detected by the accelerometer, it is necessary to first detect whether the acceleration parameter meets the characteristics of the free fall. The free fall detection is performed by judging whether the continuous change of the acceleration of the earphone in the gravity direction meets the preset condition.

[0067] For example, in the detected acceleration parameter, the modulus values of the acceleration in the gravity direction of the continuous 3 frames are < the preset 0.3g (excluding the influence of gravity), the duration is in the preset 0.2-0.5 second interval, i.e. the first time period, at this time it is determined that the earphone is in the free fall state, i.e. the acceleration data in the first time period meets the free fall acceleration performance.

[0068] Step S60, if the peak value of the acceleration modulus in the second time period is greater than the second modulus value, it is determined that the acceleration data in the second time period meets the impact rebound acceleration performance.

[0069] In the embodiment, when the earphone is in the free fall state, it is necessary to analyze the subsequent acceleration parameter, so as to determine whether the falling impact occurs. The second modulus value is greater than the first modulus value. It can be understood that when the falling impact occurs, the instantaneous change value of the acceleration is large and the duration is short, so the preset time is usually set to a short time, such as 0.1 second.

[0070] For example, during drop detection, if the peak acceleration modulus after free fall is greater than a preset second modulus (i.e., >3g), and the duration of this peak is less than a preset second period (0.1 seconds), then the headset is considered to have experienced a drop impact. This means the acceleration data within the second period reflects impact rebound acceleration. 3g is the modulus value and does not include the direction of gravity.

[0071] It should be noted that the above parameters are only used for explanation and are not limitations on this application. At the same time, g is the unit of acceleration.

[0072] This embodiment provides a fall detection method, which constructs a screening mechanism that is more in line with the physical process of falling through free fall detection. Based on free fall detection, a large number of acceleration interferences in non-fall scenarios are filtered out, greatly reducing the scope of subsequent detection. At the same time, on this basis, the impact force characteristics at the moment of impact after free fall are judged, so that the fall detection process is more in line with the actual physical process of human fall, rather than capturing a single acceleration change in isolation. At the same time, by determining whether the wearable device has a falling impact, the situation in which the first screening condition for fall detection is directly based on acceleration change in similar situations is reduced, resulting in low detection accuracy.

[0073] Furthermore, based on the third embodiment, in the fourth embodiment of the present application, the same or similar contents as those in the third embodiment can be referred to above and will not be described in detail. On this basis, when the wearer falls and the earphones do not fall off, the impact acceleration will be weakened by the human body. Therefore, after step S50, steps S70 to S80 are also included: Step S70: If the peak value of the acceleration modulus is less than the third modulus, the muscle vibration frequency of the wearable area is obtained.

[0074] Step S80 , when the muscle vibration frequency is within a preset frequency range, determining whether the acceleration data meets the impact rebound acceleration performance within the second time period.

[0075] In this embodiment, the earphones have an anti-falling structure, so when the acceleration modulus information after free fall does not meet the conditions of step S60, it is also possible to determine whether there is a falling impact by analyzing the muscle vibration frequency of the wearer when falling.

[0076] For example, when the peak value of the impact is less than the preset third modulus value of 2g, the sensor analyzes the muscle vibration frequency in the wearable area at that time. If the muscle vibration frequency is within the preset frequency range of 5 to 15 Hz, the earphones are considered to have been dropped. The third modulus value is less than the second modulus value.

[0077] The above parameters are only used for explanation and are not a limitation of the present application, and g is the unit of acceleration.

[0078] In this embodiment, if only relying on the detection in the earphone falling-off state, false judgments may be caused by signal interference in the falling-off process, such as atypical acceleration when falling off, subsequent data interruption after falling off, and the like. Therefore, special recognition is performed for the non-falling-off state, so as to improve the recognition accuracy when the earphone exists in the falling impact, and the falling impact can also be accurately recognized in the scene where the device is not falling off, thereby improving the falling detection accuracy.

[0079] Further, based on the first or third embodiments, in the fifth embodiment of the present application, the same or similar contents as the above first or third embodiments can be referred to the above introduction, and the subsequent will not be described in detail. On this basis, after step S10, steps S90-S100 are further included: Step S90, determining the acceleration change curve of the acceleration data in the gravity direction; Step S100, if the acceleration change curve meets the preset curve, determining that the falling impact event is detected.

[0080] In this embodiment, when the wearable device is in free fall, the acceleration change can be as shown in Figure 5 , g is the acceleration, and T is the time. When the falling impact event is detected based on the acceleration data, in addition to judging based on the change information of the acceleration parameter, the acceleration change curve when actually landing can also be used for judgment. For example, the acceleration change when the falling impact occurs is usually Figure 5 .

[0081] Therefore, the curve of the acceleration parameter changing with time needs to be drawn based on the acceleration data, and then it is analyzed whether the curve is a preset curve. If yes, it is judged that the falling impact event is detected.

[0082] Further, different collision regions have different impact severity when the collision occurs, so if the falling detection result is that there is a falling event, the impact level can also be determined according to the acceleration change curve. For example, the acceleration change parameters when impacting the cement ground and the ceramic tile are different from those when impacting the carpet or directly impacting the arm of the wearer. Therefore, the impact region type of the current impact can be determined based on the acceleration change curve, and then the impact level is determined based on the impact region type. The acceleration change corresponding to different impact regions is pre-stored in the local or cloud.

[0083] Therefore, after determining the impact level based on the acceleration change curve, a voice inquiry action can be performed based on the impact level, i.e., different inquiry instructions are sent to the user wearing the device through different impact levels to improve the detection intelligence. Finally, when no response voice is received within a preset period, a fall alarm action is performed; and when a response voice is received within a preset period, a response action corresponding to the response voice is performed.

[0084] The embodiment determines whether the acceleration meets the falling impact through the acceleration change curve, thereby improving the accuracy of the falling impact.

[0085] Further, based on any of the above embodiments, in the sixth embodiment of the present application, the same or similar contents as the first embodiment can be referred to the above introduction, and will not be described in detail. On this basis, before data processing, the data also needs to be denoised. Other sensors include barometers, gyroscopes, and heart rate sensors, so before step S10, the acceleration parameters, angular velocity parameters, height parameters, and heart rate parameters of the wearable device in the running state need to be obtained, and then the noise signals of the acceleration parameters, angular velocity parameters, height parameters, and heart rate parameters are removed, thereby reducing the recognition interference of noise on fall detection.

[0086] For example, in order to facilitate understanding of the implementation process of an optional fall detection method obtained by combining the above various embodiments, please refer to Figure 6 , Figure 6 A brief flowchart of a fall detection method is provided, specifically: during data acquisition and processing, real-time acquisition of various data including data of accelerometers, gyroscopes, barometers, and heart rate sensors is performed after starting the sensors, and then the data is filtered and denoised. Next, in the feature analysis and preliminary screening stage, the acceleration modulus is analyzed, if the condition is not met, the data acquisition is continued, if the acceleration modulus meets the judgment of free fall detection and impact timing, the fall preliminary screening is triggered, i.e., the multi-dimensional verification of the data is performed, including posture verification, height verification, and physiological verification, the posture is determined to be abnormal by detecting the change of the gyroscope angle, the height drop is determined to be greater than the threshold value by calculating the barometer difference, and the heart rate is determined to be abnormal by the heart rate fluctuation parameter, finally, after the three-dimensional parameters are comprehensively verified, the subsequent alarm and feedback are triggered, if one of the parameters does not meet the condition, the continuous monitoring is returned.

[0087] Finally, in the alarm and feedback stage, a voice inquiry is triggered, if the user responds, the alarm is canceled, otherwise a ten-second countdown is performed to wait for the user's reply, if there is no reply, an alarm information is sent, and an emergency contact person is notified and sent GPS positioning information.

[0088] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the fall detection method of the present application, and more forms of simple changes based on this technical concept are within the protection scope of the present application.

[0089] The present application provides a wearable device, which comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the fall detection method in the first embodiment.

[0090] Reference will be made to the following description Figure 7 which shows a structural schematic diagram of a wearable device suitable for implementing the embodiments of the present application. Figure 7 The wearable device shown is only an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0091] As Figure 7 shown, the wearable device can include a processing device 1001 (for example, a central processor, a graphics processor, etc.) which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1002 or loaded from a storage device 1003 into a random access memory (RAM) 1004. In the random access memory 1004, various programs and data required for the operation of the wearable device are also stored. The processing device 1001, the read-only memory 1002 and the random access memory 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the wearable device to communicate with other devices wirelessly or by wire to exchange data. Although the wearable device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be alternatively implemented or provided.

[0092] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0093] The wearable device provided by the present application adopts the fall detection method in the above-mentioned embodiments, and can solve the technical problem of low detection accuracy of the current wearable fall detection device. Compared with the prior art, the wearable device provided by the present application has the same beneficial effects as the fall detection method provided by the above-mentioned embodiments, and other technical features in the wearable device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0094] It should be understood that parts of the present disclosure can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0095] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0096] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for performing the fall detection method in the above-mentioned embodiments.

[0097] The computer readable storage medium provided in the application may be, for example, a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared or semiconductor system, system or device, or any combination of the above. More specific examples of the computer readable storage medium may include, but are not limited to, an electric connection with one or more conductive wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM) or a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiment, the computer readable storage medium may be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electric wire, an optical cable, a radio frequency (RF), etc., or any suitable combination of the above.

[0098] The above computer readable storage medium may be contained in a wearable device, or may exist separately without being assembled into a wearable device.

[0099] The above computer readable storage medium carries one or more programs, which, when executed by the wearable device, cause the wearable device to: if it is detected that the wearable device is subjected to a falling impact, acquire angular velocity data, height data and heart rate data before and after the falling impact; determine a posture detection result according to the angular velocity data, determine a height detection result according to the height data, and determine a heart rate detection result according to the heart rate data; if the posture detection result is a posture anomaly, the height detection result is a height anomaly, and the heart rate detection result is a heart rate anomaly, determine that the user wearing the wearable device is in a falling state.

[0100] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, 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 the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0101] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0102] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0103] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e. computer programs) for executing the above-mentioned fall detection method, and can solve the technical problem of low detection accuracy of the current wearable fall detection device. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the fall detection method provided by the above-mentioned embodiments, and will not be described here.

[0104] The above merely describes some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation, direct / indirect application in other related technical fields, or the like, which is made based on the technical concept of the present application and the content of the specification and drawings, is included in the patent protection scope of the present application.

Claims

1. A fall detection method, characterized in that: Applied to a wearable device, the wearable device includes an acceleration sensor and at least one other sensor other than the acceleration sensor, and the fall detection method includes: Acquiring acceleration data collected by the acceleration sensor based on time sequence; If the acceleration data conforms to free fall acceleration performance in the first period and conforms to impact rebound acceleration performance in the second period, it is determined that a drop impact event is detected; In response to the fall impact event, obtaining a fall detection result determined based on the detection data collected by the other sensors; If the fall detection result indicates that a fall event occurs, a fall event response process is triggered.

2. The fall detection method according to claim 1, wherein: The other sensors include a barometer, a gyroscope, and a heart rate sensor. In response to the fall impact event, the step of obtaining a fall detection result determined based on detection data collected by the other sensors includes: Acquire the angular velocity data collected by the gyroscope based on the time sequence, the altitude data corresponding to the air pressure change data collected by the barometer based on the time sequence, and the heart rate data collected by the heart rate sensor based on the time sequence; Determine a posture detection result based on the angular velocity data; determine a height detection result based on the height data; determine a heart rate detection result based on the heart rate data; If the posture detection result is abnormal posture, the height detection result is abnormal height, and / or the heart rate detection result is abnormal heart rate, it is determined that the fall detection result is that a fall event occurs.

3. The fall detection method according to claim 2, wherein: After the step of obtaining the angular velocity data collected by the gyroscope based on the time sequence, the altitude data corresponding to the air pressure change data collected by the barometer based on the time sequence, and the heart rate data collected by the heart rate sensor based on the time sequence, the fall detection method further includes: Obtaining a multimodal fusion result corresponding to the angular velocity data, the altitude data, and the heart rate data; If the multimodal fusion result satisfies the fall probability, the fall detection result is determined to be a fall event.

4. The fall detection method according to claim 2, wherein: Determining a posture detection result based on the angular velocity data; determining a height detection result based on the height data; The step of determining the heart rate detection result according to the heart rate data comprises: If the angle change rate of the angular velocity data is greater than a preset change rate, determining that the posture detection result is abnormal; If the height data is greater than or equal to a preset height, determining that the height detection result is abnormal height; If the sudden increase corresponding to the heart rate data is greater than a preset sudden increase, or the blood oxygen decrease associated with the heart rate data is greater than a preset ratio, the heart rate detection result is determined to be an abnormal heart rate.

5. The fall detection method according to claim 1, wherein: After the step of obtaining acceleration data collected by the acceleration sensor based on a time sequence, the fall detection method further includes: If, during the first time period, the acceleration modulus of the acceleration data in the direction of gravity is less than the first modulus, it is determined that the acceleration data meets the free fall acceleration performance during the first time period; If, during the second period, the peak value of the acceleration modulus is greater than the second modulus, it is determined that the acceleration data meets the impact rebound acceleration performance during the second period, wherein the second modulus is greater than the first modulus.

6. The fall detection method according to claim 5, wherein: If, during the first time period, the acceleration modulus of the acceleration data in the direction of gravity is less than the first modulus, after determining that the acceleration data meets the free fall acceleration performance during the first time period, the fall detection method further includes: If the peak value of the acceleration modulus is less than the third modulus, obtaining the muscle vibration frequency of the wearable area, and the third modulus is less than the second modulus; When the muscle vibration frequency is within a preset frequency range, it is determined that the acceleration data meets the impact rebound acceleration performance during the second time period.

7. The fall detection method according to claim 1, wherein: After the step of obtaining acceleration data collected by the acceleration sensor based on a time sequence, the fall detection method further includes: Determining an acceleration change curve of the acceleration data in the direction of gravity; If the acceleration change curve satisfies a preset curve, it is determined that the drop impact event is detected.

8. The fall detection method according to claim 7, wherein: If the fall detection result indicates that a fall event exists, the step of triggering a fall event response process includes: If the fall detection result indicates that a fall event has occurred, determining an impact level according to the acceleration change curve; executing a voice inquiry action based on the impact level, and executing a fall alarm action if no response voice is received within a preset time period; If the response voice is received within the preset time period, a response action corresponding to the response voice is executed.

9. A wearable device, characterized in that: The wearable device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the fall detection method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the fall detection method according to any one of claims 1 to 8 are implemented.

Images