Fall detection method and device, electronic equipment and storage medium

Abstract

The invention provides a fall detection method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring acceleration data associated with a target user; determining whether the target user is in a daily activity state or not according to the acceleration data and a preset first acceleration threshold value; if it is determined that the target user is not in the daily activity state, whether the target user falls down or not is determined according to the acceleration data and a second acceleration threshold value, and the second acceleration threshold value is threshold value data matched with the target user and obtained through calculation according to the acceleration data and a preset second threshold value. On the basis of first-stage tumble detection, for the suspected tumble condition, the second acceleration threshold value for second-stage tumble detection of the user is determined according to the acceleration data, whether the user tumble is judged by using the second acceleration data, the influence of different human body motion accelerations can be reduced, and the user experience is improved. Therefore, the judgment of the falling state is more accurate, and the identification accuracy of the falling state is improved.

Description

Technical Field

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

[0002] As the problem of aging society continues to become more prominent, more and more people begin to pay attention to the daily health of the elderly. According to the differences in the detection methods of fall characteristics, the research on human fall detection can be divided into wearable, visual and environmental fall detection.

[0003] Human fall detection has always been a research hotspot at home and abroad. Most of the current fall detection designs are single-source fall detection. Among them, the wearable fall detection system is worn by the human body for detection, which is the main trend of current fall detection research. Its advantages are: simple production, low cost, flexible and convenient, simple to set up and operate, wide application area, small calculation amount, and will not expose user privacy.

[0004] Currently, the fall detection algorithms based on wearable devices are mainly based on the threshold method and pattern recognition method. Among them, the pattern recognition method has higher accuracy, but the algorithm is relatively complex, the amount of calculation is large, the real-time performance is poor, and it is difficult to deploy on the device side. The threshold method is simple in calculation and easy to deploy, but the accuracy is poor. Summary of the invention

[0005] In view of this, the present application provides a fall detection method, device, electronic device and storage medium to solve the problem of poor accuracy of the existing fall detection algorithm based on the threshold method.

[0006] The technical solution adopted by this application to solve the above technical problems is:

[0007] In a first aspect, the present application provides a fall detection method, comprising:

[0008] Obtain acceleration data associated with the target user;

[0009] Determining whether the target user is in a daily activity state according to the acceleration data and a preset first acceleration threshold;

[0010] If it is determined that the target user is not in the daily activity state, whether the target user falls is determined based on the acceleration data and the second acceleration threshold, wherein the second acceleration threshold is threshold data adapted to the target user and calculated based on the acceleration data and a preset second threshold.

[0011] In some embodiments of the present application, determining whether the target user is in a daily activity state according to the acceleration data and a preset first acceleration threshold includes:

[0012] Calculate the combined acceleration value corresponding to each sampling point in a preset time period according to the acceleration data, and determine the maximum value of the combined acceleration values ​​as the target combined acceleration value;

[0013] If the target combined acceleration value is less than the first acceleration threshold, it is determined that the target user is in the daily activity state;

[0014] Otherwise, it is determined that the target user is not in the daily activity state.

[0015] In some embodiments of the present application, determining whether the target user falls according to the acceleration data and the second acceleration threshold includes:

[0016] Calculate the combined acceleration value corresponding to each sampling point in a preset time period according to the acceleration data, and determine the maximum value of the combined acceleration values ​​as the target combined acceleration value;

[0017] Calculating the second acceleration threshold according to the target combined acceleration value and the second threshold;

[0018] Whether the target user falls is determined according to the acceleration data and the second acceleration threshold.

[0019] In some embodiments of the present application, determining whether the target user falls according to the acceleration data and the second acceleration threshold includes:

[0020] Segmenting the acceleration data according to a preset time length to obtain a plurality of acceleration data segments;

[0021] For each of the acceleration data segments, calculate the combined acceleration value corresponding to each sampling point in the acceleration data segment, and determine the maximum value of the combined acceleration values ​​as the segment combined acceleration value of the acceleration data segment;

[0022] Whether the target user falls is determined according to the combined acceleration value of each segment and the second acceleration threshold.

[0023] In some embodiments of the present application, determining whether the target user falls according to the acceleration value of each segment and the second acceleration threshold includes:

[0024] For each of the segment combined acceleration values, if the segment combined acceleration value is greater than the second acceleration threshold, determining the acceleration data segment corresponding to the segment combined acceleration value as the target data segment;

[0025] The total number of the target data segments is counted, and if the total number is less than a preset segment threshold, it is determined that the target user has fallen.

[0026] In some embodiments of the present application, after determining whether the target user falls according to the acceleration data and the second acceleration threshold, the method further includes:

[0027] If it is determined that the target user falls, obtaining target acceleration data within a preset target time period after the fall;

[0028] It is determined whether the target user has fainted according to the target acceleration data and the acceleration data.

[0029] In some embodiments of the present application, determining whether the target user has fainted according to the target acceleration data and the acceleration data includes:

[0030] According to the acceleration data, a maximum value of the falling amplitude is obtained, wherein the maximum value of the falling amplitude is the maximum value of the combined acceleration of the target user before the fall;

[0031] Calculate the combined acceleration value corresponding to each sampling point in the preset target time period according to the target acceleration data, determine the maximum value of the combined acceleration values ​​as the first combined acceleration value, and determine the minimum value of the combined acceleration values ​​as the second combined acceleration value;

[0032] If the ratio of the combined acceleration difference to the maximum fall amplitude is less than a preset multiple threshold, it is determined that the target user has fainted, wherein the combined acceleration difference is the difference between the first combined acceleration value and the second combined acceleration value.

[0033] In a second aspect, the present application provides a fall detection device, comprising:

[0034] An acceleration data acquisition module, used to acquire acceleration data associated with a target user;

[0035] A daily activity state determination module, used to determine whether the target user is in a daily activity state according to the acceleration data and a preset first acceleration threshold;

[0036] A fall state determination module is used to determine whether the target user has fallen based on the acceleration data and a second acceleration threshold if it is determined that the target user is not in the daily activity state, wherein the second acceleration threshold is threshold data adapted to the target user and calculated based on the acceleration data and a preset second threshold.

[0037] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the fall and fainting detection method as described in any one of the above items are implemented.

[0038] In a fourth aspect, the present application provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for detecting falls and fainting.

[0039] In summary, due to the adoption of the above technical solution, this application has at least the following beneficial effects:

[0040] After acquiring the acceleration data of the target user, the present application firstly performs a first-stage fall detection based on the acceleration data and the first acceleration threshold to determine whether the target user is in a state of daily activities. After determining that the target user is not in a state of daily activities (suspected of falling), the second-stage fall detection is performed based on the acceleration data and the second acceleration threshold. Since the second acceleration threshold is threshold data adapted to the target user obtained based on the acceleration data, whether the target user has fallen can be more accurately determined based on the second-stage fall detection. On the basis of the first-stage fall detection, the present application adaptively determines the second acceleration threshold for the second-stage fall detection of the user based on the user's human activity characteristics, i.e., the acceleration data, for suspected falls. The second acceleration data is used to determine whether the user has fallen, which can reduce the influence of different human motion accelerations, making the judgment of the fall state more accurate and improving the recognition accuracy of the fall condition. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, but are not intended to limit the present application, wherein:

[0042] Figure 1 A flow chart of a fall detection method provided in an embodiment of the present application;

[0043] Figure 2 A schematic diagram of functional modules of a fall detection device provided in an embodiment of the present application;

[0044] Figure 3 A schematic diagram of the structure of a fall detection electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0046] In the description of this application, it should be understood that the words "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0047] In this application, the word "exemplary" is used to mean "used as an example, illustration, or description". Any embodiment described in this application as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is given to enable any technician in the field to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, known structures and processes are not elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles disclosed in this application.

[0048] Before introducing the fall detection method, device, electronic device and storage medium of the present application, relevant background information of the embodiments of the present application is first introduced.

[0049] Among the population over 65 years old, deaths caused by falls are the first cause of all accidental deaths, accounting for more than 33% of accidental deaths in this age group. If the elderly do not receive timely assistance after falling, the fall will cause serious consequences and secondary injuries. Therefore, timely assistance to the elderly who accidentally fall, and real-time detection and warning of fainting after falling will greatly improve the quality of life and dignity of the elderly, and reduce the injury and disability rate of the elderly due to falls. According to different signal acquisition methods, fall detection systems can be divided into the following types: 1) Video image-based fall detection system, which is limited by the coverage of the camera and requires that the person being detected cannot be blocked by other objects. 2) Environment-based fall detection system. It needs to be laid out for a specific environment, can only be detected in a fixed range, and the system cost is high and the calculation is large. 3) Wearable sensor-based fall detection system. It embeds micro sensors into wearable devices and presents them in the form of bracelets, belts or vests. This sensor-based detection system is small and easy to carry. It can monitor human activities in real time, is not restricted by indoor and outdoor environments, and is more suitable for application in actual environments.

[0050] Currently, the fall detection algorithms based on wearable devices are mainly based on the threshold method and pattern recognition method. The pattern recognition method has higher accuracy, but the algorithm is relatively complex, the amount of calculation is large, the real-time performance is poor, and it is difficult to deploy on the device side. The threshold method is simple in calculation and easy to deploy, but the accuracy is poor.

[0051] Based on this, a fall detection method is provided in an embodiment of the present application. The execution subject of the fall detection method can be a fall detection device, or a host device, a server device or a user equipment (UE) and other different types of devices integrated with the fall detection device. The specific method can be determined according to the actual application scenario and is not limited here. Among them, the UE can be a terminal device such as a smart phone, a tablet computer, a laptop computer, a PDA or a desktop computer.

[0052] The fall detection method can be applied to wearable devices such as smart bracelets, smart headphones, smart belts or smart vests to monitor the user's activity status.

[0053] See also Figure 1 As shown, Figure 1 The present application provides a flow chart of a fall detection method provided in an embodiment of the present application. The present application provides a fall detection method, comprising the following steps:

[0054] S1. Acquire acceleration data associated with a target user.

[0055] The execution entity for obtaining acceleration data can be set on a variety of wearable devices, such as a smart bracelet, a smart headset, a smart belt or a smart vest.

[0056] The following uses the main control chip of the wearable device as the execution subject to specifically explain how to obtain the acceleration data associated with the target user.

[0057] In the embodiment of the present application, a micro sensor may be provided on the wearable device, and the micro sensor may be used to monitor the user's behavior and activities and generate corresponding monitoring data such as acceleration data. The main control chip may be connected to the micro sensor, so that the main control unit obtains the acceleration data of the target user.

[0058] For example, the micro sensor can transmit the sampled acceleration data to the main control chip based on a preset upload frequency, so that the main control chip can obtain the acceleration data.

[0059] The main control chip may also send an upload instruction to the micro sensor based on a preset acquisition frequency, so that the micro sensor uploads the sampled acceleration data to the main control chip based on the upload instruction.

[0060] S2. Determine whether the target user is in a daily activity state according to the acceleration data and a preset first acceleration threshold.

[0061] The daily activity state may be a behavior state with a smaller range of activity, such as walking, mopping the floor, and watching TV, while the opposite of the daily activity state is the abnormal activity state, which may be a behavior state with a larger range of activity, such as running and falling.

[0062] In the embodiment of the present application, the first acceleration threshold is used to distinguish between the daily activity state and the abnormal activity state. The first acceleration threshold can be set to 16m / s 2 Etc., can be specifically determined based on multiple experiments or past experience combined with actual application scenarios, and is not limited here.

[0063] The embodiment of the present application uses the first acceleration threshold to perform the first stage fall detection, which is used to distinguish between the daily activity state with a small activity range and the abnormal activity state with a large activity range. During the first stage fall detection process, the main control unit compares the acquired acceleration data with the preset first acceleration value to determine the user's state.

[0064] In the prior art, the fall state is usually detected through a pre-set acceleration threshold, but such a detection process is easily misjudged as a fall due to the target user's continuous large-scale activities (such as running, bungee jumping, etc.). Therefore, when the embodiment of the present application determines in step S2 that the target user is not in a daily activity state, that is, in an abnormal activity state, the second stage fall detection can be continued.

[0065] S3. If it is determined that the target user is not in a daily activity state, determine whether the target user falls based on the acceleration data and the second acceleration threshold, wherein the second acceleration threshold is threshold data adapted to the target user and calculated based on the acceleration data and a preset second threshold.

[0066] In the embodiment of the present application, the second acceleration threshold is an acceleration threshold obtained by adaptively calculating the acceleration data of the target user acquired by the main control chip. The determination process of the second acceleration threshold is completely based on the activity characteristics of the target user itself, so the result of detecting the fall state of the target user is more accurate.

[0067] In the embodiment of the present application, the second acceleration threshold can be calculated based on the acceleration data and the preset second threshold. Since the second acceleration threshold is determined based on the acceleration data, the second acceleration threshold can be adapted to the activity state of the target user.

[0068] In the second stage of fall detection, the main control unit can determine whether the target user falls based on the acquired acceleration data and the second acceleration threshold. Since the second acceleration threshold that is more suitable for the target user's activity state is selected as the reference comparison object, the result of detecting whether the target user falls during the entire second stage fall detection process is undoubtedly more accurate than using the preset reference comparison object value.

[0069] After acquiring the acceleration data of the target user, the present application firstly performs a first-stage fall detection based on the acceleration data and the first acceleration threshold to determine whether the target user is in a state of daily activities. After determining that the target user is not in a state of daily activities (suspected of falling), the second-stage fall detection is performed based on the acceleration data and the second acceleration threshold. Since the second acceleration threshold is threshold data adapted to the target user obtained based on the acceleration data, whether the target user has fallen can be more accurately determined based on the second-stage fall detection. On the basis of the first-stage fall detection, the present application adaptively determines the second acceleration threshold for the second-stage fall detection of the user based on the user's human activity characteristics, i.e., the acceleration data, for suspected falls. The second acceleration data is used to determine whether the user has fallen, which can reduce the influence of different human motion accelerations, making the judgment of the fall state more accurate and improving the recognition accuracy of the fall condition.

[0070] Next, continue to Figure 1 Each step shown and a specific implementation method that may be used in practical applications are described in detail.

[0071] In some embodiments, determining whether the target user is in a daily activity state according to the acceleration data and a preset first acceleration threshold may further include:

[0072] According to the acceleration data, the combined acceleration value corresponding to each sampling point in the preset time period is calculated, and the maximum value among the combined acceleration values ​​is determined as the target combined acceleration value.

[0073] If the target combined acceleration value is less than the first acceleration threshold, it is determined that the target user is in a daily activity state.

[0074] Otherwise, it is determined that the target user is not in daily activity.

[0075] Get the target combined acceleration value SS max The process is as follows:

[0076] The main control unit obtains the acceleration values ​​of the X-axis, Y-axis, and Z-axis of multiple sampling samples within a preset time period, and calculates the combined acceleration value of each sampling point, which is specifically calculated by the following formula:

[0077] Get the X-axis acceleration signal S of multiple sampling samples within a preset time period x , Y-axis acceleration signal S y And the Z-axis acceleration signal S z , calculate the total acceleration SS:

[0078]

[0079] Secondly, select the maximum value SS of the combined acceleration SS max Determine the target combined acceleration value.

[0080] SS max =max(SS1,SS2,...,SS n ), where n is the number of sampled samples.

[0081] After obtaining the target combined acceleration value SS max After that, if the target acceleration value SS max If the acceleration is greater than the first acceleration threshold, it is determined that the target user is not in a daily activity state and may fall.

[0082] For example, the first acceleration threshold is set to 16 m / s 2 , if the target acceleration value SS max 30m / s 2 , since the target acceleration value SS max 30m / s 2 Greater than the first acceleration threshold 16m / s 2 Therefore, it is determined that the target user is in an abnormal activity state, that is, a non-daily activity state; on the contrary, if the target combined acceleration value SS max 5m / s 2 , since the target acceleration value SS max 5m / s 2 Less than the first acceleration threshold 16m / s 2 ,Therefore, it is determined that the target users are in daily activities.

[0083] In some embodiments, determining whether the target user falls according to the acceleration data and the second acceleration threshold may further include:

[0084] According to the acceleration data, the combined acceleration value corresponding to each sampling point in the preset time period is calculated, and the maximum value among the combined acceleration values ​​is determined as the target combined acceleration value.

[0085] The second acceleration threshold is calculated according to the target combined acceleration value and the second threshold.

[0086] Whether the target user falls is determined according to the acceleration data and the second acceleration threshold.

[0087] In this embodiment, the main control unit obtains the combined acceleration value corresponding to each sampling point in the preset time period and determines the target acceleration value through acceleration data, which is consistent with the process of calculating the target combined acceleration value in the above text. Please refer to the above text for details and will not be repeated here.

[0088] After obtaining the target combined acceleration value SS max Then, based on the target combined acceleration value SS max A second acceleration threshold is determined.

[0089] The process of obtaining the second acceleration threshold is as follows: the main control unit can set the target combined acceleration value SS max Subtract the second threshold value from the acceleration value to obtain the second acceleration threshold value. The second threshold value may be a preset threshold value obtained by experiment, and its value may be 5.7 m / s 2 、6.3m / s 2 wait.

[0090] In the second stage of fall detection, the second acceleration threshold is calculated based on the target combined acceleration value corresponding to the target user's own activity and the preset second threshold. The second acceleration threshold is more consistent with the target user's own movement behavior habits and the combined acceleration value when falling. In this way, the detection results obtained in the fall detection process can exclude the state of continuous activity of the target user, such as running, going up and down stairs, continuous jumping, etc., so the fall detection results obtained are more accurate.

[0091] In some embodiments, determining whether the target user falls according to the acceleration data and the second acceleration threshold may further include:

[0092] The acceleration data is processed in segments according to a preset time length to obtain a plurality of acceleration data segments.

[0093] For each acceleration data segment, the combined acceleration value corresponding to each sampling point in the acceleration data segment is calculated, and the maximum value among the combined acceleration values ​​is determined as the segment combined acceleration value of the acceleration data segment.

[0094] Whether the target user falls is determined according to the combined acceleration value of each segment and the second acceleration threshold.

[0095] The process of determining the combined acceleration value of each segment is as follows: the main control unit processes the acceleration data of a preset time length (for example, 6 seconds) in segments (for example, cutting a 6-second segment into 6 1-second sub-segments), and based on the formula for calculating the combined acceleration value above, the combined acceleration SS_slice of multiple sampling points of each sub-segment can be calculated, and the maximum value SS_slice is selected from the combined acceleration of each sub-segment max As the segment sum acceleration value for each sub-segment.

[0096] During the second stage of fall detection, the main control unit cuts the acceleration data of the preset segment into multiple sub-segments according to the acceleration data and obtains the maximum combined acceleration value of all sampling points in each sub-segment, and obtains the combined acceleration value of the segment compared with the second acceleration threshold during the second stage of acceleration threshold detection, so as to perform a second fall detection.

[0097] In some embodiments, determining whether the target user falls according to the acceleration value of each segment and the second acceleration threshold may further include:

[0098] For each segment combined acceleration value, if the segment combined acceleration value is greater than the second acceleration threshold, the acceleration data segment corresponding to the segment combined acceleration value is determined as the target data segment.

[0099] The total number of target data segments is counted, and if the total number is less than a preset segment threshold, it is determined that the target user has fallen.

[0100] In the embodiment of the present application, the fragment threshold can be determined based on multiple times, and its value can be 3, 4, etc.

[0101] In the second stage of fall detection, the main control unit compares the segment sum acceleration value SS_slice of each sub-segment. max The value of the acceleration of all sub-slices SS_slice is determined by the size of the second acceleration threshold. max The sub-segments with acceleration values ​​greater than the second acceleration threshold are taken as target data segments, and the total number of target data segments is counted. Based on the total number and the preset segment threshold, if the number of segments whose combined acceleration values ​​are greater than the second acceleration threshold (i.e., the target data segments) is less than the segment threshold, it can be determined that the target user has fallen.

[0102] Since the behavior judged as an abnormal activity state after the first stage of fall detection may be a fall, it may also be a large-scale continuous activity such as running. Therefore, in order to distinguish between large-scale continuous activities and falls, in the embodiment of the present application, the segments whose combined acceleration values ​​are greater than the second acceleration threshold are counted. If the total number of statistics is greater than or equal to the segment threshold, it can be considered that the target user has performed continuous large-scale activities such as running and skipping without falling; if the total number of statistics is less than the segment threshold, it can be considered that the target user has performed non-continuous large-scale activities, and if it is a normal large-scale activity such as exercise, it will be a continuous action, so continuous large-scale activities such as running and skipping can be excluded, thereby determining that the target user has fallen.

[0103] In some embodiments, after determining whether the target user has fallen based on the acceleration data and the second acceleration threshold, the method may further include:

[0104] If it is determined that the target user falls, the target acceleration data within a preset target time period after the fall is obtained.

[0105] Based on the target acceleration data and the acceleration data, it is determined whether the target user has fainted.

[0106] After a user falls, he or she may faint depending on the severity of the injury. If the fainting is not detected in time, life may be in danger. Therefore, in an embodiment of the present application, after determining that the user has fallen, further fainting detection may be performed on the user. If it is determined that the target user has fainted, timely fainting warning and emergency rescue measures can be initiated through the early warning module.

[0107] After determining that the target user has fallen, the main control unit can continue to obtain the target acceleration data within a preset target time period after the fall, and compare the target acceleration data with the acceleration data of the user before the fall to determine whether the target user is in a fainting state. This can continue to improve the accuracy of fainting detection and early warning while ensuring accurate fall detection.

[0108] In some embodiments, determining whether the target user has fainted based on the target acceleration data and the acceleration data may further include:

[0109] The maximum fall amplitude is obtained according to the acceleration data, wherein the maximum fall amplitude is the maximum value of the combined acceleration before the target user falls.

[0110] According to the target acceleration data, the combined acceleration value corresponding to each sampling point in the preset target time period is calculated, the maximum value of the combined acceleration values ​​is determined as the first combined acceleration value, and the minimum value of the combined acceleration values ​​is determined as the second combined acceleration value.

[0111] If the ratio of the combined acceleration difference to the maximum fall amplitude is less than a preset multiple threshold, it is determined that the target user has fainted, wherein the combined acceleration difference is the difference between the first combined acceleration value and the second combined acceleration value.

[0112] In the embodiment of the present application, the preset target time period is a preset time period for fainting detection after the main control unit detects that the user has fallen, and its value can be 100 seconds, 3 minutes, 5 minutes, etc., which can be determined according to the actual application scenario.

[0113] The preset multiple threshold value may be 1 / 10, 3 / 10, etc., or may be set to other values ​​according to the specific working scenario of the wearable device.

[0114] The main control unit obtains the maximum value of the combined acceleration SS before the target user falls based on the acceleration data above. maxThe calculation process of the first combined acceleration value and the second combined acceleration value is consistent with the above, so it will not be repeated. It can be understood that the maximum combined acceleration value SS max The reference comparison value for fainting detection is more adapted to the fainting activity characteristics of the target user than the directly preset reference comparison value, making the fainting detection more accurate.

[0115] After a user falls, if he does not faint, he will perform corresponding activities within a short period of time, such as sitting up or standing up, and his corresponding acceleration data will change. If he faints, the user's acceleration data will not change in a short period of time. Therefore, based on the acceleration data after the fall, it is possible to further detect whether the user has fainted.

[0116] The main control unit calculates the maximum value of the combined acceleration SS according to the above max As the maximum value of the fall amplitude, then calculate the combined acceleration values ​​corresponding to multiple sampling points within the preset target time period after the fall, obtain the maximum combined acceleration value in the preset time period (such as within 3 minutes after the fall) as the first combined acceleration value and the minimum combined acceleration value as the second combined acceleration value, take the difference between the two as the combined acceleration difference, and then compare the ratio of the combined acceleration difference to the maximum value of the fall amplitude with a preset multiple threshold (such as 1 / 10) to determine whether the target has fainted. Since the combined acceleration difference is the difference between the first combined acceleration value and the second combined acceleration value, the combined acceleration difference can reflect the change in the amplitude of the target user's movement after the fall. If the amplitude change is less than 1 / 10 of the maximum value of the fall amplitude, it can be determined that the target user has fainted, thereby initiating early warning and emergency rescue measures, such as notifying the emergency contact associated with the target user's wearable device or a nearby hospital.

[0117] In some embodiments, after acquiring acceleration data of a plurality of sampling samples within a preset time period, low-pass filtering may be performed on the acquired acceleration data to ensure the accuracy of the data.

[0118] After acquiring the acceleration data, the data can be low-pass filtered to make the data acquisition and subsequent data processing more accurate. Specifically, since the jitter frequency of the movement is usually 0-180 times / minute, the corresponding frequency is 3 to 4 Hz, so the low-pass frequency band range during low-pass filtering can be set to 8 Hz.

[0119] It should be noted that the identified fall results and fainting intelligent diagnosis results can be displayed on portable wearable devices such as smart bracelets and smart watches that include accelerometer modules, as a basis for personal or doctor detection and diagnosis.

[0120] See also Figure 2 As shown, Figure 2This is a block diagram of a fall detection device provided in an embodiment of the present application. The present application also provides a fall detection device 200, which is used to implement the detection method described in any of the above embodiments. The detection device includes:

[0121] The acceleration data acquisition module 201 is used to acquire acceleration data associated with the target user;

[0122] A daily activity state determination module 202, configured to determine whether the target user is in a daily activity state according to the acceleration data and a preset first acceleration threshold;

[0123] The fall state determination module 203 is used to determine whether the target user falls according to the acceleration data and the second acceleration threshold if it is determined that the target user is not in the daily activity state, wherein the second acceleration threshold is threshold data adapted to the target user and calculated based on the acceleration data and a preset second threshold.

[0124] Add beneficial effects

[0125] In order to better implement the fall detection method of the present application, the present application also provides a fall detection electronic device, which integrates any fall detection device 200 provided in the present application. The fall detection electronic device may include a processor 301 and a memory 302. The memory 302 may be used to store a computer program. When the computer program is executed by the processor 301, it can be used to implement the following functions:

[0126] Obtain acceleration data associated with the target user;

[0127] Determining whether the target user is in a daily activity state according to the acceleration data and a preset first acceleration threshold;

[0128] If it is determined that the target user is not in the daily activity state, whether the target user falls is determined based on the acceleration data and the second acceleration threshold, wherein the second acceleration threshold is threshold data adapted to the target user and calculated based on the acceleration data and a preset second threshold.

[0129] like Figure 3 As shown, it shows a structural schematic diagram of the fall detection electronic device involved in the present application, specifically:

[0130] The fall detection electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will appreciate that Figure 3The device structure shown in the figure does not constitute a limitation on the device, and the fall detection device may also include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0131] The processor 301 is the control center of the device, which uses various interfaces and lines to connect various parts of the entire device, and executes various functions of the device and processes data by running or executing software programs and / or unit modules stored in the memory 302, and calling data stored in the memory 302, so as to monitor the fall detection as a whole. Optionally, the processor 301 may include one or more processing cores; the processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communication. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0132] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and data processing by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the fall detection device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0133] The fall detection electronic device may further include a power supply 303 for supplying power to various components. Preferably, the power supply 303 may be logically connected to the processor 301 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 303 may also include any components such as one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0134] The fall detection electronic device may further include an input unit 304 and an output unit 305. The input unit 304 may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0135] Although not shown, the fall detection electronic device may also include a display unit, etc., which will not be described in detail here. Specifically in the present application, the processor 301 in the fall detection electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302, thereby realizing various functions, as follows:

[0136] Obtain acceleration data associated with the target user;

[0137] Determining whether the target user is in a daily activity state according to the acceleration data and a preset first acceleration threshold;

[0138] If it is determined that the target user is not in the daily activity state, whether the target user falls is determined based on the acceleration data and the second acceleration threshold, wherein the second acceleration threshold is threshold data adapted to the target user and calculated based on the acceleration data and a preset second threshold.

[0139] The present application also provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the fall and fainting detection method provided in any of the above embodiments is implemented.

[0140] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0141] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0142] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more application embodiments, in the above description of the embodiments of this application, multiple features are sometimes merged into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0143] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this application is hereby incorporated by reference in its entirety, except for application history documents that are inconsistent with or conflicting with the content of this application, and documents that limit the broadest scope of the claims of this application (currently or later attached to this application). It should be noted that if the descriptions, definitions, and / or use of terms in the attached materials of this application are inconsistent or conflicting with the content of this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

Claims

1. A fall detection method, characterized in that: include: Obtain acceleration data associated with the target user; Determining whether the target user is in a daily activity state according to the acceleration data and a preset first acceleration threshold; If it is determined that the target user is not in the daily activity state, whether the target user falls is determined based on the acceleration data and the second acceleration threshold, wherein the second acceleration threshold is threshold data adapted to the target user and calculated based on the acceleration data and a preset second threshold.

2. The detection method according to claim 1, characterized in that: The determining, according to the acceleration data and a preset first acceleration threshold, whether the target user is in a daily activity state includes: Calculate the combined acceleration value corresponding to each sampling point in a preset time period according to the acceleration data, and determine the maximum value of the combined acceleration values ​​as the target combined acceleration value; If the target combined acceleration value is less than the first acceleration threshold, it is determined that the target user is in the daily activity state; Otherwise, it is determined that the target user is not in the daily activity state.

3. The detection method according to claim 1, characterized in that: Determining whether the target user falls according to the acceleration data and the second acceleration threshold includes: Calculate the combined acceleration value corresponding to each sampling point in a preset time period according to the acceleration data, and determine the maximum value of the combined acceleration values ​​as the target combined acceleration value; Calculating the second acceleration threshold according to the target combined acceleration value and the second threshold; Whether the target user falls is determined according to the acceleration data and the second acceleration threshold.

4. The detection method according to claim 3, characterized in that: The determining, according to the acceleration data and the second acceleration threshold, whether the target user falls includes: Segmenting the acceleration data according to a preset time length to obtain a plurality of acceleration data segments; For each of the acceleration data segments, calculate the combined acceleration value corresponding to each sampling point in the acceleration data segment, and determine the maximum value of the combined acceleration values ​​as the segment combined acceleration value of the acceleration data segment; Whether the target user falls is determined according to the combined acceleration value of each segment and the second acceleration threshold.

5. The detection method according to claim 4, characterized in that: The determining whether the target user falls according to the acceleration value of each segment and the second acceleration threshold includes: For each of the segment combined acceleration values, if the segment combined acceleration value is greater than the second acceleration threshold, determining the acceleration data segment corresponding to the segment combined acceleration value as the target data segment; The total number of the target data segments is counted, and if the total number is less than a preset segment threshold, it is determined that the target user has fallen.

6. The detection method according to claim 5, characterized in that: Determining whether the target user falls according to the acceleration data and the second acceleration threshold, and then the method further includes: If it is determined that the target user falls, obtaining target acceleration data within a preset target time period after the fall; It is determined whether the target user has fainted according to the target acceleration data and the acceleration data.

7. The detection method according to claim 1, characterized in that: Determining whether the target user has fainted according to the target acceleration data and the acceleration data includes: According to the acceleration data, a maximum value of the falling amplitude is obtained, wherein the maximum value of the falling amplitude is the maximum value of the combined acceleration of the target user before the fall; Calculate the combined acceleration value corresponding to each sampling point in the preset target time period according to the target acceleration data, determine the maximum value of the combined acceleration values ​​as the first combined acceleration value, and determine the minimum value of the combined acceleration values ​​as the second combined acceleration value; If the ratio of the combined acceleration difference to the maximum fall amplitude is less than a preset multiple threshold, it is determined that the target user has fainted, wherein the combined acceleration difference is the difference between the first combined acceleration value and the second combined acceleration value.

8. A fall detection device, characterized in that: include: An acceleration data acquisition module, used to acquire acceleration data associated with a target user; A daily activity state determination module, used to determine whether the target user is in a daily activity state according to the acceleration data and a preset first acceleration threshold; A fall state determination module is used to determine whether the target user has fallen based on the acceleration data and a second acceleration threshold if it is determined that the target user is not in the daily activity state, wherein the second acceleration threshold is threshold data adapted to the target user and calculated based on the acceleration data and a preset second threshold.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the fall detection method according to any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the fall detection method according to any one of claims 1 to 7 are implemented.

Images