Fall detection switching method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a fall detection method and device, electronic equipment and a storage medium, and the method is characterized in that the method is applied to first wearable equipment, and the first wearable equipment is in communication connection with second wearable equipment; the first wearable device and the second wearable device are both worn by a target user; the method comprises the following steps: acquiring first acceleration data acquired by an acceleration sensor; acquiring second acceleration data corresponding to a second wearable device; and if it is determined that a first tumble event occurs according to the first acceleration data and a second tumble event occurs according to the second acceleration data, determining that the target user tumble. By implementing the embodiment of the invention, the accuracy of fall detection can be improved, and the situation of false alarm of fall is reduced.

Description

Technical Field

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

[0002] At present, falls are common in daily life, and the older the elderly are, the more likely they are to fall. Falls among the elderly can easily cause a "domino effect", resulting in injuries to the elderly after the fall, which can cause a series of complications or even death. If rescue is provided immediately after a fall, the consequences of complications can be effectively reduced. Therefore, timely detection of falls and reporting to the police for medical treatment can reduce deaths caused by delays in the best treatment time and the occurrence of a series of complications caused by falls. At present, the accuracy of detecting whether a user has fallen is not high, and it is easy to falsely report a fall. Summary of the invention

[0003] The embodiments of the present application disclose a fall detection method, device, electronic device and storage medium, which can improve the accuracy of fall detection and reduce the occurrence of false fall alarms.

[0004] The embodiment of the present application discloses a fall detection method, which is applied to a first wearable device, wherein the first wearable device is communicatively connected with a second wearable device; the first wearable device and the second wearable device are both worn by a target user; the method comprises:

[0005] Acquire first acceleration data collected by the acceleration sensor;

[0006] Acquire second acceleration data corresponding to the second wearable device;

[0007] If a first fall event is determined to have occurred according to the first acceleration data, and a second fall event is determined to have occurred according to the second acceleration data, then it is determined that the target user has fallen.

[0008] As an optional implementation manner, the acquiring the second acceleration data of the second wearable device includes:

[0009] In the case where a first fall event is determined to have occurred according to the first acceleration data, sending a collection instruction to the second wearable device, the collection instruction including a first time period; the collection instruction is used to instruct the second wearable device to send the second acceleration data corresponding to the first time period to the first wearable device; the first time period includes a time point corresponding to the occurrence of the first fall event;

[0010] Receive second acceleration data corresponding to the first time period sent by the second wearable device.

[0011] As an optional implementation manner, the acquiring second acceleration data corresponding to the second wearable device includes:

[0012] Receiving second acceleration data sent in real time by the second wearable device;

[0013] The obtaining of first acceleration data collected by the acceleration sensor includes:

[0014] When it is determined that a second fall event has occurred according to the second acceleration data, first acceleration data of a second time period collected by the acceleration sensor is acquired, where the second time period includes a time point corresponding to an occurrence of the second fall event.

[0015] As an optional implementation, the first acceleration data includes first accelerations corresponding to multiple acceleration directions respectively; the second acceleration data includes second accelerations corresponding to the multiple acceleration directions respectively; after acquiring the first acceleration data collected by the acceleration sensor, the method further includes:

[0016] Calculating first fall data corresponding to each of the acceleration directions according to the first acceleration data within the target duration; the first fall data includes a first acceleration average value or a first acceleration maximum value corresponding to the acceleration direction;

[0017] If it is detected that the first fall data corresponding to the first direction is greater than the first acceleration threshold corresponding to the first direction, it is determined that the first fall event occurs; the first direction is any of the acceleration directions;

[0018] After acquiring the second acceleration data corresponding to the second wearable device, the method further includes:

[0019] Calculating second fall data corresponding to each of the acceleration directions according to the second acceleration data within the target duration; the second fall data includes a second acceleration average value or a second acceleration maximum value corresponding to the acceleration direction;

[0020] If it is detected that the second fall data corresponding to the second direction is greater than the second acceleration threshold corresponding to the second direction, it is determined that the second fall event occurs; the second direction is any of the acceleration directions.

[0021] As an optional implementation manner, before acquiring the first acceleration data collected by the acceleration sensor, the method further includes:

[0022] Obtain a first sample acceleration set and a second sample acceleration set, wherein the first sample acceleration set includes a plurality of first sample accelerations and a fall occurrence label corresponding to each first sample acceleration, and the second sample acceleration set includes a plurality of second sample accelerations and a fall occurrence label corresponding to each second sample acceleration, wherein the first sample acceleration is collected by a wearable device worn on a user's hand, and the second sample acceleration is collected by a wearable device worn on a user's head;

[0023] Determine a first acceleration threshold corresponding to each of the acceleration directions according to the first sample acceleration set;

[0024] A second acceleration threshold corresponding to each of the acceleration directions is determined according to the second sample acceleration set.

[0025] As an optional implementation manner, the first wearable device further includes a speaker; after determining that the target user falls, the method further includes:

[0026] A fall warning sound with a decibel value greater than a preset value is output through a speaker, and / or a distress signal is sent to a preset terminal.

[0027] As an optional implementation, the first wearable device is worn on the hand of the target user, and the second wearable device is worn on the head of the target user.

[0028] The embodiment of the present application discloses a fall detection device, which is applied to a first wearable device, wherein the first wearable device is communicatively connected with a second wearable device; both the first wearable device and the second wearable device are worn by a target user, and the device includes:

[0029] A first acquisition module, used to acquire first acceleration data collected by the acceleration sensor;

[0030] A second acquisition module, used to acquire second acceleration data corresponding to the second wearable device;

[0031] A determination module is used to determine that the target user has fallen if a first fall event is determined to have occurred according to the first acceleration data and a second fall event is determined to have occurred according to the second acceleration data.

[0032] An embodiment of the present application discloses an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements any one of the fall detection methods disclosed in the embodiments of the present application.

[0033] The embodiments of the present application disclose a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute any one of the fall detection methods disclosed in the embodiments of the present application.

[0034] Compared with the related art, the embodiments of the present application have the following beneficial effects:

[0035] The embodiments of the present application provide a fall detection method, device, electronic device and storage medium, which obtain first acceleration data collected by an acceleration sensor; obtain second acceleration data corresponding to the second wearable device; if a first fall event is determined to have occurred based on the first acceleration data, and a second fall event is determined to have occurred based on the second acceleration data, then determine that the target user has fallen. By implementing the embodiments of the present application, the first acceleration data collected by the first wearable device and the second acceleration data collected by the second wearable device are respectively obtained, and then the first fall event is determined to have occurred based on the first acceleration data, and the second fall event is determined to have occurred based on the second acceleration data. The acceleration data of multiple wearable devices are combined to jointly determine whether a fall has occurred, which can reduce the situation of misjudging the occurrence of a fall event and reduce the probability of falsely reporting the occurrence of a fall event, thereby improving the accuracy of fall detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 This is an application scenario diagram of a fall detection method disclosed in an embodiment of the present application;

[0038] Figure 2 It is a flowchart of a fall detection method disclosed in an embodiment of the present application;

[0039] Figure 3 A schematic diagram of a flow chart of another fall detection method disclosed in an embodiment of the present application;

[0040] Figure 4 A schematic diagram of a flow chart of another fall detection method disclosed in an embodiment of the present application;

[0041] Figure 5 is a schematic diagram of a flow chart of determining whether a first fall event occurs according to first acceleration data disclosed in an embodiment of the present application;

[0042] Figure 6is a flow chart of determining whether a second fall event occurs according to second acceleration data disclosed in an embodiment of the present application;

[0043] Figure 7 is a schematic diagram of a process for determining a first acceleration threshold and a second acceleration threshold disclosed in an embodiment of the present application;

[0044] Figure 8 is a structural schematic diagram of a fall detection device disclosed in an embodiment of the present application;

[0045] Fig. 9 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0046] 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 ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present application and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0048] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first acceleration threshold may be referred to as a second acceleration threshold, and similarly, a second acceleration threshold may be referred to as a first acceleration threshold. Both the first acceleration threshold and the second acceleration threshold are acceleration thresholds, but they are not the same acceleration threshold.

[0049] In the existing technology, there are already some methods and systems for fall detection. For example, the acceleration data is collected by the wearable device worn by the target user, and the collected acceleration data is used to determine whether a fall has occurred. If the collected acceleration data is greater than a preset threshold, it is determined that the target user has fallen; or, the posture information of the target user is collected by the wearable device, and the posture information is used to determine whether a fall has occurred, wherein the posture information may be information related to the height and angle of the wearable device worn by the target user. However, these methods often lack accuracy in fall detection.

[0050] Since the acceleration data collected by the wearable device is used for fall detection, the wearable device can be worn on the hand or head of the target user. When the target user needs to bend or squat due to daily activities, the acceleration data generated by these actions may exceed the preset threshold. At the same time, the posture information generated by these actions may be similar to the posture information generated when a fall occurs. Therefore, the wearable device may determine that the target user has fallen, resulting in a false alarm of a fall.

[0051] The above problems limit the accuracy of fall detection, so the method for fall detection needs to be further improved.

[0052] The embodiments of the present application disclose a fall detection method, device, electronic device and storage medium, which can improve the accuracy of fall detection.

[0053] See also Figure 1 , Figure 1 1 is an application scenario diagram of a fall detection method disclosed in an embodiment of the present application. . The application scenario may include a first wearable device 101 and a second wearable device 102. In some embodiments, the first wearable device 101 may be a wearable device worn on the hand of the target user, such as a smart watch, a smart bracelet or a smart ring, etc., which is not specifically limited. The second wearable device 102 is a wearable device worn on the head of the target user, such as headphones, hearing aids, hearing aids, smart glasses, etc., which is not specifically limited.

[0054] In some embodiments, the first wearable device 101 can establish a communication connection with the second wearable device 102 in the form of a Bluetooth connection, or can establish a communication connection with the second wearable device 102 in the form of a wired connection. By establishing a communication connection between the first wearable device 101 and the second wearable device 102, the first wearable device 101 and the second wearable device 102 can realize information exchange. An acceleration sensor can be set on the first wearable device 101, and the first acceleration data can be collected through the acceleration sensor in the first wearable device 101. At the same time, an acceleration sensor can also be set on the second wearable device 102, and the acceleration sensor in the second wearable device 102 can be used to collect second acceleration data. When the second wearable device 102 is in the device-on state, the second wearable device 102 can send the collected second acceleration data to the first wearable device.

[0055] The first wearable device 101 obtains first acceleration data collected by the acceleration sensor, and obtains second acceleration data corresponding to the second wearable device 102. If the first wearable device 101 determines that a first fall event occurs according to the first acceleration data, and determines that a second fall event occurs according to the second acceleration data, it is determined that the target user falls.

[0056] Figure 2 is a flow chart of a fall detection method disclosed in an embodiment of the present application. Figure 2 As shown, in one embodiment, the fall detection method can be applied to the first wearable device mentioned above, and the method may include the following steps:

[0057] Step S202: Acquire first acceleration data collected by the acceleration sensor.

[0058] When the target user wears the first wearable device, the first wearable device may collect first acceleration data through the acceleration sensor. In some embodiments, the first wearable device is worn on the hand of the target user, and the first acceleration data may include acceleration data of the hand. In the normal daily activities of the user, the acceleration data generated by the hand in multiple directions is usually within a preset range. When the target user falls, the target user's hand will generate acceleration data in a certain direction that exceeds the preset range. Therefore, the first acceleration data collected by the acceleration sensor in the first wearable device can be used as one of the bases for judging whether the target user falls.

[0059] In some embodiments, when the first wearable device recognizes that it is currently in a wearing state, that is, when the first wearable device is worn on the hand of the target user, the first wearable device can send a start signal to the acceleration collector in the first wearable device, so that the acceleration sensor starts and collects the first acceleration, thereby obtaining the first acceleration collected by the acceleration sensor.

[0060] Optionally, the first wearable device can collect the temperature through the built-in temperature sensor, and determine whether the first wearable device is in a wearing state according to the temperature collected by the temperature sensor. When the first wearable device is in a wearing state, since the first wearable device contacts the skin surface of the target user, the temperature sensor in the first wearable device will collect the body surface temperature of the target user. The first wearable device can collect the body surface temperature of the target user according to the temperature sensor, and determine whether the first wearable device is in a wearing state according to the body surface temperature. When the body surface temperature collected by the temperature sensor is greater than a preset temperature threshold, it is determined that the first wearable device is currently in a wearing state.

[0061] Optionally, the first wearable device may also collect the heart rate data of the target user through a photoelectric sensor, and determine whether the first wearable device is in a wearing state based on the heart rate data. If the heart rate data collected by the photoelectric sensor is within a preset heart rate range, it can be determined that the first wearable device is in a wearing state. When the first wearable device is in a wearing state, a start signal may be sent to the acceleration sensor in the first wearable device in the form of an electrical signal, so that the acceleration sensor starts and collects the first acceleration. By determining that the first wearable device is in a wearing state and then starting the acceleration sensor in the first wearable device, the power consumption of the first wearable device can be saved. At the same time, since the acceleration sensor collects acceleration data only when the first wearable device is in a wearing state, it is possible to collect first acceleration data that is helpful for fall detection, reduce the collection of invalid first acceleration data, and lay a foundation for improving the accuracy of judging whether a fall has occurred.

[0062] The first wearable device can collect the first acceleration data of the target user in real time through the acceleration sensor, and store the collected first acceleration data in the memory. Further, the first acceleration data of the target duration can be collected in real time, and the target duration and the first acceleration data corresponding to the target duration are stored in the first wearable device. That is to say, the first wearable device in the wearing state can collect the first acceleration data of the target duration all the time, that is, when the first wearable device is in the wearing state, the first acceleration data starts to be collected until the first wearable device is in the off state or the standby state, and then the first acceleration data is stopped. The standby state includes that the first wearable device is not in the wearing state, or is in the wearing state but receives a signal to turn off the acceleration sensor. Wherein, the target duration is a preset time period, for example, the target duration can be 5 seconds, then the first acceleration data within the first 5 seconds is collected, the first 5 seconds time period can be the time period from 15:10:00 to 15:10:05, and the first 5 seconds and the first acceleration data corresponding to the first 5 seconds are stored in the first wearable device.

[0063] As an implementation mode, the second acceleration data sent by the second wearable device in real time is received; when the second fall event is determined to have occurred according to the second acceleration data, the first acceleration data of the second time period collected by the acceleration sensor is obtained, and the second time period includes the time point corresponding to the occurrence of the second fall event. That is to say, after the second acceleration data sent by the second wearable device in real time is received, and the second fall event is determined to have occurred according to the second acceleration data, the first acceleration data of the second time period collected by the acceleration sensor, the second time period can be a time interval including the time point corresponding to the occurrence of the second fall event, for example, if the target user falls at 15:10:04, then the time point corresponding to the occurrence of the second fall event determined according to the second acceleration data is also 15:10:04, if the required second time period is a 10-second time interval, then the second time period only needs to include the time point of 15:10:04 and the duration is a 10-second time interval, that is, the second time period can be a time interval from 15:10:00 to 15:10:10, or a time interval from 15:10:01 to 15:10:11. Since the first acceleration data collected by the first wearable device through the acceleration sensor is stored in the first wearable device, when it is determined that the second fall event has occurred, the first wearable device can directly retrieve the first acceleration data corresponding to the second time period to obtain the first acceleration data.

[0064] By collecting the first acceleration data and storing the first acceleration data corresponding to the target time in the first wearable device, a basis can be provided for the first wearable device to determine whether the target user falls. At the same time, by collecting the first acceleration data corresponding to the target duration, when the first fall event is determined according to the first acceleration data, the time period in which the first fall event occurs can be further determined, so that fall detection can be performed more accurately.

[0065] Step S204: Acquire second acceleration data corresponding to the second wearable device.

[0066] The second wearable device may include an acceleration sensor, and the second wearable device may collect the second acceleration through its own acceleration sensor. In some embodiments, the second wearable device is worn on the head of the target user, and the acceleration data corresponding to the head collected by the acceleration sensor of the second wearable device can be used as the second acceleration data. When the target user falls, in addition to the movement of the hand, there will also be movement of the head. Therefore, when the target user falls, in addition to the first acceleration data corresponding to the hand, the second acceleration data corresponding to the head will also be generated. When the second wearable device is in a wearing state, that is, when the second wearable device is worn on the head of the target user, the second wearable device will collect the second acceleration data so that the first wearable device can obtain the second acceleration data corresponding to the second wearable device.

[0067] In some embodiments, when it is determined that a first fall event has occurred, the second acceleration data corresponding to the second wearable device can be obtained, or the second acceleration data corresponding to the second wearable device can be obtained in real time. The second wearable device collects the second acceleration data in real time, and then sends the real-time collected second acceleration data to the first wearable device, so that the first wearable device obtains the second acceleration data corresponding to the second wearable device.

[0068] Step S206: If it is determined that a first fall event has occurred according to the first acceleration data, and if it is determined that a second fall event has occurred according to the second acceleration data, it is determined that the target user has fallen.

[0069] The first wearable device is worn on the hand of the target user, and the second wearable device is worn on the head of the target user. The acceleration sensor in the first wearable device can collect first acceleration data, and the second wearable device can collect second acceleration data.

[0070] As an implementation mode, according to the first acceleration data, the occurrence of a first fall event is determined, and the first wearable device can determine the first acceleration parameter of the first acceleration data according to the collected first acceleration data, and compare the first acceleration parameter with the first acceleration parameter obtained when the fall occurs, so as to determine whether the first fall event has occurred, wherein the first acceleration parameter can be used to describe the acceleration magnitude and acceleration direction of the first acceleration data. Similarly, according to the second acceleration parameter, the occurrence of a second fall event is determined, and the first wearable device can determine the second acceleration parameter of the second acceleration data according to the second acceleration data, and compare the second acceleration parameter with the second acceleration parameter obtained when the fall occurs, so as to determine whether the second fall event has occurred, wherein the second acceleration parameter can be used to describe the acceleration magnitude and acceleration direction of the second acceleration data.

[0071] In some embodiments, the first wearable device may first obtain the first acceleration data, and after determining that the first fall event has occurred according to the first acceleration data, obtain the second acceleration data, and then determine whether the second fall event has occurred according to the second acceleration data. The first wearable device may also first obtain the second acceleration data, and after determining that the second fall event has occurred according to the second acceleration data, obtain the first acceleration data, and then determine whether the first fall event has occurred according to the first acceleration data. The first wearable device may also simultaneously obtain the first acceleration data and the second acceleration data, and synchronously determine whether the first fall event has occurred and whether the second fall event has occurred.

[0072] The first wearable device obtains the acceleration data corresponding to different body parts of the target user, that is, the first acceleration data and the second acceleration data, and then determines the occurrence of the first fall event based on the first acceleration data, and determines the occurrence of the second fall event based on the second acceleration data. This can reduce the possibility of confirming a fall based on the acceleration data of a body part due to the violent movement of a body part of the target user, thereby misjudging the target user's fall. For example, when the target user is exercising and swinging his arms, the acceleration data of the hand changes dramatically, and the first acceleration data collected by the first wearable device will also change dramatically. If only the first acceleration is used to determine that the target user has fallen, the first wearable device will mistakenly believe that the target user has fallen, but in fact the target user has not fallen, resulting in low accuracy of fall detection.

[0073] As another embodiment, after determining that the target user has fallen, the first wearable device can perform a rescue operation to increase the exposure of the target user's fall, so that rescue work can be carried out in time for the target user who has fallen. The first wearable device also includes a speaker. After determining that the target user has fallen, a fall prompt sound with a decibel value greater than a preset value can be output through the speaker, and / or a distress signal can be sent to a preset terminal. The first wearable device emits a fall prompt sound with a decibel value greater than a preset value through the speaker. For example, a sharper alarm sound can be generated so that people near the target user can notice that the target user has fallen, thereby rescuing the target user. At the same time, the first wearable device can also send a distress signal to a preset terminal, wherein the distress signal can include the location information of the target user, the preset terminal can be a terminal bound in advance by the first wearable device, the first wearable device can be bound to the terminal corresponding to the relatives of the target user, or it can be a terminal corresponding to the hospital where the target user is located. The first wearable device can further increase the rescue opportunity of the target user who has fallen by sending a distress signal to the preset terminal, thereby improving the rescue efficiency of the target user.

[0074] In an embodiment of the present application, first acceleration data collected by an acceleration sensor is obtained; second acceleration data corresponding to the second wearable device is obtained; if a first fall event is determined to have occurred according to the first acceleration data, and if a second fall event is determined to have occurred according to the second acceleration data, then it is determined that a fall has occurred for the target user, and by obtaining different acceleration data, it is determined whether a corresponding fall event has occurred according to the acceleration data, and in the case where the first fall event is determined to have occurred and the second fall event is determined to have occurred, it is determined that the fall has occurred for the target user, which can reduce the situation where the first wearable device erroneously detects that the target user has fallen due to changes in a single acceleration data, thereby improving the accuracy of fall detection.

[0075] Figure 3 FIG. 1 is a flow chart of another fall detection method disclosed in an embodiment of the present application. Figure 3 As shown, the method comprises the following steps:

[0076] Step S302: Acquire first acceleration data collected by the acceleration sensor.

[0077] As an implementation mode, the first wearable device includes an acceleration sensor, and the first wearable device can collect first acceleration data through the acceleration sensor so as to obtain the first acceleration data. Since the first wearable device is worn on the hand of the target user, the first acceleration data collected by the first wearable device can be the acceleration data corresponding to the hand of the target user, wherein the acceleration data corresponding to the hand of the target user can be the acceleration data generated when the target user wears the first wearable device for daily activities.

[0078] Step S304, determining whether a first fall event occurs according to the first acceleration data, if so, executing step S306, if not, continuing to execute step S302.

[0079] In some embodiments, the first wearable device determines whether the first fall event occurs based on the first acceleration. If the first acceleration data is the acceleration data corresponding to the target user's hand, then determining that the first fall event occurs can indicate that the acceleration data corresponding to the target user's hand is abnormal, for example, the value of the acceleration data corresponding to the target user's hand exceeds a preset range. If the first fall event is determined to have occurred based on the first acceleration data, the target user has a greater probability of falling. Therefore, the first wearable device determines that the first fall event has occurred based on the first acceleration data, and then further obtains the second acceleration data to further determine whether the target user has fallen. If it is determined that the first fall event has not occurred based on the first acceleration data, the first acceleration data can continue to be monitored, that is, the first acceleration data collected by the acceleration sensor continues to be obtained, and whether the first fall event has occurred is determined based on the first acceleration data.

[0080] Step S306: Send a collection instruction to the second wearable device, where the collection instruction includes the first time period.

[0081] In some embodiments, after determining that a first fall event has occurred according to the first acceleration data, the first wearable device may send a collection instruction to the second wearable device. A communication connection is established between the first wearable device and the second wearable device. Therefore, the first wearable device may send a collection instruction to the second wearable device according to the established communication connection. Specifically, the collection instruction may be sent to the second wearable device in the form of sending a Bluetooth signal. The collection instruction includes a first time period, wherein the first time period is a time period including the time point when the first fall event occurs.

[0082] As an implementation mode, when it is determined that the first fall event has occurred based on the first acceleration data, a collection instruction is sent to the second wearable device, and the collection instruction includes a first time period; the collection instruction is used to instruct the second wearable device to send the second acceleration data corresponding to the first time period to the first wearable device; the first time period includes the time point corresponding to the occurrence of the first fall event; and the second acceleration data corresponding to the first time period sent by the second wearable device is received. In other words, by acquiring the first acceleration data collected by the acceleration sensor, and then determining that the first fall event has occurred based on the first acceleration data, when it is determined that the first fall event has occurred, a collection instruction can be sent to the second wearable device, and when the second wearable device receives the collection instruction, the second acceleration data corresponding to the first time period is sent to the first wearable device, and the first wearable device receives the second acceleration data corresponding to the first time period that occurred on the second wearable device. Among them, the first time period is a time interval containing the time point corresponding to the occurrence of the first fall event. For example, if the target user falls at time 15:10:04, then the time point corresponding to the occurrence of the first fall event is also 15:10:04 according to the first acceleration data. If the required first time period is a 10-second time interval, then the first time period only needs to contain the time point 15:10:04 and the duration is 110 seconds, that is, the first time period can be a time interval from 15:10:00 to 15:10:10, or a time interval from 15:10:01 to 15:10:11. The collection instruction includes the first time period. Since the first time period includes the time point corresponding to the occurrence of the first fall event, the second acceleration data of the time point corresponding to the occurrence of the first fall event can be obtained according to the instruction of the collection instruction, so that on the basis of determining that the first fall event has occurred, it can be further determined whether the second fall event has occurred through the second acceleration data corresponding to the first time period.

[0083] Step S308: receiving second acceleration data corresponding to the first time period sent by the second wearable device.

[0084] In some embodiments, the second wearable device can be worn on the head of the target user. An acceleration sensor is provided in the second wearable device. Therefore, the acceleration data corresponding to the second wearable device can be the acceleration data generated by the head of the target user during daily activities.

[0085] As an implementation mode, after the second wearable device receives the collection instruction from the first wearable device, the second wearable device can send the second acceleration data corresponding to the first time period to the first wearable device according to the collection instruction, and the first wearable device can receive the second acceleration data corresponding to the first time period sent by the second wearable device. After determining that the first fall event has occurred according to the first acceleration data, the first wearable device can further determine whether the second fall event has occurred by collecting the second acceleration data corresponding to the second wearable device. If it is determined that the second fall event has occurred, it can be determined that the target user has fallen, thereby avoiding the situation where the fall is determined to have occurred based on a single acceleration data and causing a misjudgment of the fall, thereby improving the accuracy of the fall detection.

[0086] Step S310, determining whether a second fall event occurs according to the second acceleration data, if so, executing step S312, if not, continuing to execute step S302.

[0087] In some embodiments, the first wearable device determines whether the second fall event occurs according to the second acceleration. If the second acceleration data is the acceleration data corresponding to the target user's head, then determining that the second fall event occurs may indicate that the acceleration data corresponding to the target user's head is abnormal, for example, the value of the acceleration data corresponding to the target user's head exceeds the preset range. In the case of determining that the first fall event occurs, if the second fall event is determined to occur according to the second acceleration data, it can be explained that the values ​​of the acceleration data corresponding to the target user's hand and the acceleration data corresponding to the head exceed the preset range, and therefore, it can be determined that the target user falls. If it is determined according to the second acceleration data that the second fall event does not occur, it can be explained that the target user performs a large-scale action, causing the first acceleration data to exceed the preset range, for example, the target user performs a large-scale waving action, but the target user does not fall at this time. Therefore, the first wearable device determines that the target user does not fall, and can continue to monitor the first acceleration data collected by the acceleration sensor. The second acceleration data is the acceleration data corresponding to the target user's head. By obtaining the second acceleration data, the second acceleration data is also used as a basis for determining that the target user has fallen. When the target user falls, the first acceleration data corresponding to the target user's hand and the second acceleration data corresponding to the target user's head are used to determine that the target user has fallen, which can further improve the accuracy of fall detection.

[0088] Step S312: determining whether the target user falls.

[0089] As an implementation mode, after determining that a first fall event has occurred according to the first acceleration data, the first wearable device further determines that a second fall event has occurred according to the second acceleration data, thereby determining that the target user has fallen. After the first wearable device determines that the target user has fallen, the first wearable device can emit an alarm through a speaker, or send a distress signal to a preset terminal, thereby realizing a call for help for the target user, so that the target user can be rescued as quickly as possible after falling.

[0090] In an embodiment of the present application, the first wearable device obtains first acceleration data collected by the acceleration sensor, and determines whether a first fall event occurs based on the first acceleration data. If so, a collection instruction is sent to the second wearable device. The first wearable device receives second acceleration data corresponding to the first time period sent by the second wearable device, and determines whether a second fall event occurs based on the second acceleration data. If so, it is determined that the target user has fallen. Determining whether the target user has fallen based on the two types of acceleration data can further improve the accuracy of fall detection.

[0091] Figure 4 FIG. 1 is a flow chart of another fall detection method disclosed in an embodiment of the present application. Figure 4 As shown, the method may include the following steps:

[0092] Step S402: receiving second acceleration data sent in real time by the second wearable device.

[0093] In some embodiments, the second wearable device may be worn on the head of the target user, and the second acceleration data collected by the second wearable device may be acceleration data of the head of the target user.

[0094] As an implementation mode, the second wearable device is provided with an acceleration sensor, which can collect the second acceleration data in real time, the second wearable device can obtain the second acceleration data in real time, and the second wearable device can send the second acceleration data obtained in real time to the first wearable device, so that the first wearable device can receive the second acceleration data sent in real time by the second wearable device.

[0095] Step S404, determining whether a second fall event occurs according to the second acceleration data, if so, executing step S406, if not, continuing to execute step S402.

[0096] As an implementation method, the first wearable device can determine whether the second fall event occurs based on the second acceleration data. If it is determined that the second fall event occurs, it means that the acceleration data of the target user's head exceeds the preset range, and the target user has a greater probability of falling. Therefore, the first acceleration data can be further obtained to determine whether the first fall event occurs, thereby determining whether the target user falls. If it is determined that the second fall event does not occur, the second acceleration data sent in real time by the second wearable device can continue to be monitored.

[0097] Step S406, obtaining first acceleration data of a second time period collected by the acceleration sensor.

[0098] In some embodiments, when the second wearable device acquires the second acceleration data, the first wearable device also acquires the first acceleration data through the acceleration sensor and stores the acquired first acceleration data in the memory.

[0099] As an implementation, after determining that a second fall event has occurred based on the second acceleration data, the first wearable device can obtain the first acceleration data of a second time period by retrieving the first acceleration data stored in the memory, wherein the second time period is a time period including the time point when the second fall event occurred.

[0100] Step S408, determining whether a first fall event occurs according to the first acceleration data, if so, executing step S410, if not, continuing to execute step S402.

[0101] As an implementation method, the first wearable device determines whether the first fall event has occurred based on the first acceleration data. If it is determined that the first fall event has occurred, it means that the acceleration data of the target user's hand and the acceleration data of the head are both beyond the preset range. Therefore, the first wearable device can determine that the target user has fallen. If it is determined that the first fall event has not occurred, it means that the acceleration data of the target user's head is beyond the preset range, but the acceleration data of the target user's hand is not beyond the preset range. It may be due to the second acceleration data generated by the target user's large-scale head movement, not the occurrence of a fall. Therefore, the received second acceleration data can continue to be monitored to perform real-time fall detection on the target user.

[0102] Step S410: determining whether the target user falls.

[0103] The description of step S410 may refer to the relevant description of step S312 in the above embodiment, which will not be repeated here.

[0104] In the embodiment of the present application, the first wearable device receives the second acceleration data sent in real time by the second wearable device, and determines whether the second fall event occurs according to the second acceleration data. If so, the first acceleration data of the second time period collected by the acceleration sensor is obtained, and then the first fall event is determined according to the first acceleration data. If so, it is determined that the target user has fallen. By determining whether the target user has fallen according to the two acceleration data, the accuracy of fall detection can be further improved.

[0105] Figure 5 is a flow chart of determining whether a first fall event has occurred according to first acceleration data disclosed in an embodiment of the present application. Figure 5 As shown, the step of determining whether a first fall event occurs according to the first acceleration data includes the following steps:

[0106] Step S502, calculating first fall data corresponding to each acceleration direction according to the first acceleration data within the target duration; the first fall data includes a first acceleration average value or a first acceleration maximum value corresponding to the acceleration direction.

[0107] As an implementation mode, after obtaining the first acceleration data collected by the acceleration sensor, the first fall data corresponding to each acceleration direction can be calculated according to the first acceleration data within the target duration, wherein the target duration is a preset time interval, for example, the target duration can be set to 5 seconds, then the first acceleration data is grouped into 5 seconds each, the first acceleration data is divided into multiple parts according to the target duration, and then the first fall data corresponding to each acceleration direction is calculated according to the first acceleration data within each target duration. If the first acceleration data includes the first acceleration corresponding to multiple acceleration directions, then one first acceleration data can correspond to multiple different first fall data.

[0108] If the acceleration directions included in the first acceleration data are direction A and direction B, the first fall data corresponding to each acceleration direction is calculated according to the first acceleration data within the target duration, that is, according to the first acceleration data, the first acceleration corresponding to direction A within the target duration is extracted, and then the average value or maximum value of the acceleration data corresponding to direction A within the target duration is calculated, and the average value or maximum value is used as the first fall data corresponding to direction A. At the same time, according to the first acceleration data, the first acceleration corresponding to direction B within the target duration is extracted, and then the average value or maximum value of the acceleration data corresponding to direction B within the target duration is calculated, and the average value or maximum value is used as the first fall data corresponding to direction B. Finally, the first fall data corresponding to the first acceleration data within the target duration can be obtained, which are the first fall data corresponding to direction A and the first fall data corresponding to direction B. For example, the first acceleration data within the target duration is shown in Table 1:

[0109] Table 1

[0110] Acceleration direction First second Second second The third second Fourth second Fifth second Direction A 1.5 1.3 1.4 1.6 0.9 Direction B 1.2 1.5 1.6 1.7 1.9

[0111] Then, according to the first acceleration data within the target duration, the average value of the acceleration data corresponding to direction A is calculated as: The maximum value of the acceleration data corresponding to direction A is 1.6, and the value of the first fall data corresponding to direction A may be 1.34 or 1.6.

[0112] In some embodiments, the first wearable device can collect the first acceleration data in real time, and calculate the first acceleration data within each target duration in real time, and calculate the corresponding first fall data in real time according to the first acceleration data, so as to determine whether the first fall event occurs according to the first fall data. If there is invalid first acceleration data in the first acceleration data collected within the target duration, the invalid first acceleration data can be removed, and then the corresponding first fall data can be calculated based on the first acceleration data with the invalid value removed. Among them, the invalid first acceleration data can be first acceleration data with a value of 0, or acceleration data with a value of the first acceleration data much greater than a preset value, or acceleration data with a value of the first acceleration data being empty.

[0113] Step S504: if it is detected that the first fall data corresponding to the first direction is greater than the first acceleration threshold corresponding to the first direction, it is determined that a first fall event occurs; the first direction is any of the acceleration directions.

[0114] As an implementation mode, after calculating the first fall data corresponding to the first acceleration data, it can be detected whether the first fall data corresponding to the first direction is greater than the first acceleration threshold corresponding to the first direction. If it is detected that the first fall data corresponding to the first direction is greater than the acceleration threshold corresponding to the first direction, it can be determined that the first fall event has occurred. Wherein, the first direction is any acceleration direction, and further, it can also be all acceleration directions contained in the first acceleration data. For example, if the first acceleration data contains direction A, direction B and direction C, then the first direction can be any acceleration direction in direction A, direction B and direction C. . The first acceleration threshold is a threshold obtained according to the training data. The first acceleration threshold can be the upper limit of the acceleration data generated by the hand of the target user in daily activities. If the first fall data corresponding to the first direction is greater than the first acceleration threshold corresponding to the first direction, it indicates that the target user has a greater probability of falling. In other words, as long as the first fall data corresponding to any direction in the acceleration direction contained in the first acceleration data is detected to be greater than the first acceleration threshold corresponding to the direction, it can be determined that the first fall event has occurred.

[0115] In an embodiment of the present application, the first fall data corresponding to each acceleration direction is calculated based on the first acceleration data within the target time length. If it is detected that the first fall data corresponding to the first direction is greater than the first acceleration threshold corresponding to the first direction, it is determined that a first fall event has occurred. By determining whether the first fall event has occurred through the first fall data corresponding to multiple directions of the first acceleration data, it is possible to more accurately judge whether the first fall event has occurred, thereby improving the accuracy of fall detection.

[0116] Figure 6 is a flow chart of determining whether a second fall event has occurred according to the second acceleration data disclosed in the embodiment of the present application. Figure 6 As shown, the step of determining whether a second fall event occurs according to the second acceleration data includes:

[0117] Step S602, calculating second fall data corresponding to each acceleration direction according to the second acceleration data within the target duration; the second fall data includes a second acceleration average value or a second acceleration maximum value corresponding to the acceleration direction.

[0118] As an implementation method, the second acceleration data includes second accelerations corresponding to multiple acceleration directions. The first wearable device can calculate the second fall data corresponding to each acceleration direction based on the second acceleration data within the target duration. The second fall data can be the average acceleration value or the maximum acceleration value corresponding to the corresponding acceleration direction. For example, when the target duration is 5 seconds, the second acceleration includes the second acceleration data corresponding to direction A. The second acceleration corresponding to direction A can be [1.1, 1.2, 0.9, 0.5, 0.3]. Then the average value of the second acceleration corresponding to direction A is: The maximum value of the second acceleration corresponding to direction A is 1.2, so the second fall data corresponding to direction A can be 0.8 or 1.2.

[0119] In some embodiments, the first wearable device can receive the second acceleration data corresponding to the second wearable device in real time, and then calculate the second fall data corresponding to the second acceleration data within the target duration in real time, so that it can be determined in real time whether the second fall event occurs based on the second fall data. If there is invalid second acceleration data in the second acceleration data collected within the target duration, the invalid second acceleration data can be removed, and then the corresponding second fall data can be calculated based on the second acceleration data with the invalid value removed. Among them, the invalid second acceleration data can be second acceleration data with a value of 0, or acceleration data with a value of the second acceleration data much greater than a preset value, or acceleration data with a value of the second acceleration data being empty.

[0120] Step S604: if it is detected that the second fall data corresponding to the second direction is greater than the second acceleration threshold corresponding to the second direction, it is determined that a second fall event occurs; the second direction is any acceleration direction.

[0121] As an implementation method, after obtaining the second fall data, it is possible to detect whether the second fall data corresponding to the second direction is the second acceleration threshold corresponding to the second direction. If it is detected that the second fall data corresponding to the second direction is greater than the second acceleration threshold corresponding to the second direction, it is determined that a second fall event has occurred. Wherein, the second direction is any acceleration direction, that is, any direction of the multiple acceleration directions contained in the second acceleration, the second acceleration threshold is obtained through training data, and the second acceleration threshold indicates the maximum value of the acceleration data corresponding to the head generated by the target user during daily activities. If the acceleration data of the target user's head forward in daily life is not greater than 3, then if the data is greater than 3 when the second fall forward is detected, the target user is likely to have a head tilt forward and is at risk of falling. Therefore, it can be determined that a second fall event has occurred.

[0122] In an embodiment of the present application, second fall data corresponding to each acceleration direction is calculated based on the second acceleration data within the target time length. If it is detected that the second fall data corresponding to the second direction is greater than the second acceleration threshold corresponding to the second direction, it is determined that a second fall event has occurred. Whether a second fall event has occurred is determined based on multiple second fall data corresponding to the second acceleration data, and the second acceleration data is different from the first acceleration data. Whether the target user has fallen is detected based on different types of acceleration data, which can further improve the accuracy of fall detection.

[0123] Figure 7 is a schematic diagram of a process for determining a first acceleration threshold and a second acceleration threshold disclosed in an embodiment of the present application. Figure 7 As shown, the steps of determining the first acceleration threshold and the second acceleration threshold include:

[0124] Step S702, obtaining a first sample acceleration set and a second sample acceleration set, wherein the first sample acceleration set includes multiple first sample accelerations and a fall occurrence label corresponding to each first sample acceleration, and the second sample acceleration set includes multiple second sample accelerations and a fall occurrence label corresponding to each second sample acceleration, wherein the first sample acceleration is collected by a wearable device worn on the user's hand, and the second sample acceleration is collected by a wearable device worn on the user's head.

[0125] As an implementation method, obtaining the first sample acceleration set is used to determine the first acceleration threshold, wherein the first sample acceleration set includes multiple first sample accelerations and a fall occurrence label corresponding to each sample acceleration, wherein the first sample acceleration can be collected by a wearable device worn on the user's hand, wherein the wearable device on the user's hand is provided with an acceleration sensor, and the first sample acceleration can be collected by the acceleration sensor in the wearable device. At the same time, corresponding fall occurrence labels can be artificially labeled on multiple first sample accelerations, and the fall occurrence labels corresponding to the first sample acceleration can be divided into "fall occurred" and "no fall occurred", and the "fall occurred" label can indicate that the user corresponding to the collected first sample acceleration has fallen, and the "no fall occurred" label can indicate that the user corresponding to the collected first sample acceleration has not fallen. Similarly, the second sample acceleration set includes the second sample acceleration and the fall occurrence label corresponding to the second sample acceleration, wherein the second sample acceleration can be collected by a wearable device worn on the user's head, wherein the wearable device worn on the user's head is provided with an acceleration sensor, and the second sample acceleration can be collected by the acceleration sensor. After collecting multiple second sample accelerations, the multiple second sample accelerations can be manually labeled with corresponding fall occurrence labels. The fall occurrence labels can also be divided into two categories: "fall occurred" and "no fall occurred", corresponding to two fall occurrence scenarios respectively.

[0126] Step S704: determining first acceleration thresholds corresponding to various acceleration directions according to the first sample acceleration set.

[0127] As an implementation method, the first sample acceleration set includes multiple first sample accelerations and fall occurrence labels corresponding to the first sample accelerations. By comparing the multiple first sample accelerations and the fall occurrence labels corresponding to each first sample acceleration, the lower limit of the first sample acceleration corresponding to the "fall occurred" label, that is, the minimum acceleration value corresponding to the hand when the user falls, can be determined, as well as the lower limit of the first sample acceleration corresponding to the "no fall occurred" label, and the maximum acceleration value corresponding to the hand when the user does not fall. The first acceleration threshold can be determined based on the upper limit and the lower limit, and further, the average value of the upper limit and the lower limit can be used as the first acceleration threshold.

[0128] Step S706: determining second acceleration thresholds corresponding to each acceleration direction according to the second sample acceleration set.

[0129] As an implementation method, the second sample acceleration set includes multiple second sample accelerations and fall occurrence labels corresponding to the second sample accelerations. By comparing the multiple second sample accelerations and the fall occurrence labels corresponding to each second sample acceleration, the lower limit of the second sample acceleration corresponding to the "fall occurred" label, that is, the minimum acceleration value of the hand when the user falls, can be determined, and the lower limit of the second sample acceleration corresponding to the "no fall occurred" label, and the maximum acceleration value of the hand when the user does not fall, can be determined. The second acceleration threshold can be determined based on the upper limit and the lower limit, and further, the average value of the upper limit and the lower limit can be used as the second acceleration threshold.

[0130] As another implementation, the same user may wear a wearable device on the hand and a wearable device on the head at the same time, and then collect a first sample acceleration based on the wearable device on the hand, and collect a second sample acceleration based on the wearable device on the head. The collected first sample acceleration and second sample acceleration correspond to the same fall occurrence label.

[0131] A hand fall model to be trained and a head fall model to be trained can be established. The hand fall model that has been trained can determine the occurrence of a first fall event based on the first acceleration data, and the parameter corresponding to the hand fall model is the first acceleration threshold; the head fall model that has been trained can determine the occurrence of a second fall event based on the second acceleration data, and the parameter corresponding to the head fall model is the second acceleration threshold. The hand fall model to be trained can judge the input first sample acceleration, thereby determining the first predicted event corresponding to the first sample data; at the same time, the head fall model to be trained can judge the input second sample acceleration, thereby determining the second predicted event corresponding to the second sample data. If the first predicted event is determined to occur based on the first sample acceleration, and the second predicted event is determined to occur based on the second sample acceleration, the sample detection result of the user can be determined, and the first acceleration threshold and the second acceleration threshold are adjusted based on the error between the sample detection result and the fall occurrence label, and finally the trained hand fall model and head fall model are obtained. The first acceleration threshold can be determined based on the parameters of the hand fall model, and the second acceleration threshold can be determined based on the head fall model. Among them, the sample detection results can be whether a fall occurred or not.

[0132] In an embodiment of the present application, a first sample acceleration set and a second sample acceleration set are obtained, and then a first acceleration threshold is determined according to the first sample acceleration set, and a second acceleration threshold is determined according to the second sample acceleration. It is possible to accurately determine whether a first fall event has occurred based on the first acceleration threshold according to the first acceleration data, and it is possible to accurately determine whether a second fall event has occurred based on the second acceleration threshold according to the second acceleration data. Determining reasonable first acceleration threshold and second acceleration threshold can ensure the accuracy of fall detection.

[0133] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a fall detection device disclosed in an embodiment of the present application. . The device can be applied to the first wearable device mentioned above. Figure 8 As shown, the fall detection device 800 may include: a first acquisition module 801 , a first acquisition module 802 , and a determination module 803 .

[0134] A first acquisition module 801 is used to acquire first acceleration data collected by an acceleration sensor;

[0135] A first acquisition module 802, configured to acquire second acceleration data corresponding to the second wearable device;

[0136] The determination module 803 is configured to determine that the target user has fallen if a first fall event is determined to have occurred according to the first acceleration data and a second fall event is determined to have occurred according to the second acceleration data.

[0137] In one embodiment, the second acquisition module 802 is also used for: when it is determined that a first fall event has occurred according to the first acceleration data, sending a collection instruction to the second wearable device, the collection instruction including a first time period; the collection instruction is used to instruct the second wearable device to send the second acceleration data corresponding to the first time period to the first wearable device; the first time period includes the time point corresponding to the occurrence of the first fall event; receiving the second acceleration data corresponding to the first time period sent by the second wearable device.

[0138] In one embodiment, the second acquisition module 802 is further used to: receive second acceleration data sent in real time by the second wearable device; the first acquisition module 801 is further used to: when it is determined that a second fall event has occurred based on the second acceleration data, obtain first acceleration data of a second time period collected by the acceleration sensor, and the second time period includes the occurrence time point corresponding to the second fall event.

[0139] In some embodiments, the fall detection device 800 further includes a first calculation module and a first detection module:

[0140] A first calculation module is used to calculate first fall data corresponding to each acceleration direction according to the first acceleration data within the target duration; the first fall data includes a first acceleration average value or a first acceleration maximum value corresponding to the acceleration direction;

[0141] A first detection module is used to determine that a first fall event occurs if it is detected that the first fall data corresponding to the first direction is greater than the first acceleration threshold corresponding to the first direction; the first direction is any acceleration direction;

[0142] The second calculation module is further used to calculate the second fall data corresponding to each of the acceleration directions according to the second acceleration data within the target duration; the second fall data includes the second acceleration average value or the second acceleration maximum value of the corresponding acceleration direction;

[0143] The second detection module is used to determine that a second fall event occurs if it is detected that the second fall data corresponding to the second direction is greater than the second acceleration threshold corresponding to the second direction; the second direction is any acceleration direction.

[0144] In some embodiments, the fall detection device 800 further includes:

[0145] A sample acquisition module, used to acquire a first sample acceleration set and a second sample acceleration set, wherein the first sample acceleration set includes a plurality of first sample accelerations and a fall occurrence label corresponding to each first sample acceleration, and the second sample acceleration set includes a plurality of second sample accelerations and a fall occurrence label corresponding to each second sample acceleration, wherein the first sample acceleration is acquired by a wearable device worn on a user's hand, and the second sample acceleration is acquired by a wearable device worn on a user's head;

[0146] A first determination module, configured to determine first acceleration thresholds corresponding to various acceleration directions according to a first sample acceleration set;

[0147] The second determination module is used to determine the second acceleration threshold corresponding to each acceleration direction according to the second sample acceleration set.

[0148] In some embodiments, the fall detection device 800 is further used to: output a fall warning sound with a decibel value greater than a preset value through a speaker, and / or send a distress signal to a preset terminal.

[0149] In some embodiments, the first wearable device is worn on a hand of the target user, and the second wearable device is worn on a head of the target user.

[0150] See also Fig. 9 , Fig. 9 Schematic diagram of the structure of an electronic device disclosed in the embodiment of the present application. Fig. 9As shown, the first wearable device 900 may include:

[0151] A memory 901 storing executable program codes;

[0152] A processor 902 coupled to the memory 901;

[0153] The processor 902 calls the executable program code stored in the memory 901 to execute any fall detection method disclosed in the embodiments of the present application.

[0154] An embodiment of the present application discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by the processor, the processor implements any one of the fall detection methods disclosed in the embodiments of the present application.

[0155] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. Those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required for the present application.

[0156] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the above-mentioned processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0157] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0158] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0159] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for a computer device (which can be a personal computer, a server or a network device, etc., specifically a processor in a computer device) to perform some or all of the steps of the above-mentioned methods of various embodiments of the present application.

[0160] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, the storage medium including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0161] The above is a detailed introduction to a fall detection switching method, device, electronic device and storage medium disclosed in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those of ordinary skill in the art, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A fall detection method, characterized in that: Applied to a first wearable device, the first wearable device is communicatively connected with a second wearable device; both the first wearable device and the second wearable device are worn by a target user; the method includes: Acquire first acceleration data collected by the acceleration sensor; Acquire second acceleration data corresponding to the second wearable device; If a first fall event is determined to have occurred according to the first acceleration data, and a second fall event is determined to have occurred according to the second acceleration data, then it is determined that the target user has fallen.

2. The method according to claim 1, characterized in that: The acquiring the second acceleration data of the second wearable device includes: In the case where a first fall event is determined to have occurred according to the first acceleration data, sending a collection instruction to the second wearable device, the collection instruction including a first time period; the collection instruction is used to instruct the second wearable device to send the second acceleration data corresponding to the first time period to the first wearable device; the first time period includes a time point corresponding to the occurrence of the first fall event; Receive second acceleration data corresponding to the first time period sent by the second wearable device.

3. The method according to claim 1, characterized in that The obtaining second acceleration data corresponding to the second wearable device includes: Receiving second acceleration data sent in real time by the second wearable device; The obtaining of first acceleration data collected by the acceleration sensor includes: When it is determined that a second fall event has occurred according to the second acceleration data, first acceleration data of a second time period collected by the acceleration sensor is acquired, where the second time period includes a time point corresponding to an occurrence of the second fall event.

4. The method according to claim 1, characterized in that: The first acceleration data includes first accelerations corresponding to a plurality of acceleration directions respectively; the second acceleration data includes second accelerations corresponding to the plurality of acceleration directions respectively; After acquiring the first acceleration data collected by the acceleration sensor, the method further includes: Calculating first fall data corresponding to each of the acceleration directions according to the first acceleration data within the target duration; the first fall data includes a first acceleration average value or a first acceleration maximum value corresponding to the acceleration direction; If it is detected that the first fall data corresponding to the first direction is greater than the first acceleration threshold corresponding to the first direction, it is determined that the first fall event occurs; the first direction is any of the acceleration directions; After acquiring the second acceleration data corresponding to the second wearable device, the method further includes: Calculating second fall data corresponding to each of the acceleration directions according to the second acceleration data within the target duration; the second fall data includes a second acceleration average value or a second acceleration maximum value corresponding to the acceleration direction; If it is detected that the second fall data corresponding to the second direction is greater than the second acceleration threshold corresponding to the second direction, it is determined that the second fall event occurs; the second direction is any of the acceleration directions.

5. The method according to claim 4, characterized in that Before acquiring the first acceleration data collected by the acceleration sensor, the method further includes: Obtain a first sample acceleration set and a second sample acceleration set, wherein the first sample acceleration set includes a plurality of first sample accelerations and a fall occurrence label corresponding to each first sample acceleration, and the second sample acceleration set includes a plurality of second sample accelerations and a fall occurrence label corresponding to each second sample acceleration, wherein the first sample acceleration is collected by a wearable device worn on a user's hand, and the second sample acceleration is collected by a wearable device worn on a user's head; Determine a first acceleration threshold corresponding to each of the acceleration directions according to the first sample acceleration set; A second acceleration threshold corresponding to each of the acceleration directions is determined according to the second sample acceleration set.

6. The method according to claim 1, characterized in that The first wearable device further includes a speaker; after determining that the target user falls, the method further includes: A fall warning sound with a decibel value greater than a preset value is output through a speaker, and / or a distress signal is sent to a preset terminal.

7. The method according to any one of claims 1 to 6, characterized in that: The first wearable device is worn on the hand of the target user, and the second wearable device is worn on the head of the target user.

8. A fall detection device, characterized in that: Applied to a first wearable device, the first wearable device is communicatively connected with a second wearable device; the first wearable device and the second wearable device are both worn by a target user, and the device includes: A first acquisition module, used to acquire first acceleration data collected by the acceleration sensor; A second acquisition module, used to acquire second acceleration data corresponding to the second wearable device; A determination module is used to determine that the target user has fallen if a first fall event is determined to have occurred according to the first acceleration data and a second fall event is determined to have occurred according to the second acceleration data.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images