Fall detection method and fall detection system

Abstract

A fall detection method and system are disclosed. The method includes: acquiring a first motion signal collected by a first motion sensor worn on a user's torso, and acquiring a second motion signal collected by a second motion sensor worn on the user's arm; processing the first motion signal to obtain a first processing result, the first processing result including first waveform change information and first posture change information, the first waveform change information including at least first acceleration change information; processing the second motion signal to obtain a second processing result, the second processing result including at least one of second waveform change information and second posture change information, the second waveform change information including at least second acceleration change information; determining whether the user has fallen based on the first processing result and the second processing result, and issuing a fall alarm when the user is determined to have fallen. This solution can improve the accuracy of fall detection.

Description

[0001] This application is a divisional application of the patent application filed on December 9, 2021, with application number 2021115008720 and entitled "Fall Detection Method and Fall Detection System". Technical Field

[0002] This invention relates generally to the field of medical device technology, and more specifically to a fall detection method and a fall detection system. Background Technology

[0003] With social and economic development, the aging population trend is becoming increasingly apparent, and the scenarios and market for elderly care are expanding. Among various ailments in the elderly, the incidence of strokes and fractures due to falls caused by a lack of timely care is increasing. Therefore, timely and accurate fall detection is of great value.

[0004] Existing fall detection equipment typically uses a single motion sensor to detect falls based on the motion signals collected by that single sensor. However, due to the diverse causes of falls, existing fall detection equipment is prone to false positives or false negatives. Summary of the Invention

[0005] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. The summary section of this invention is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0006] A first aspect of this invention provides a fall detection method, the method comprising: acquiring a first motion signal collected by a first motion sensor worn on a user's torso, and acquiring a second motion signal collected by a second motion sensor worn on the user's arm; processing the first motion signal to obtain a first processing result, the first processing result including first waveform change information and first posture change information, the first waveform change information including at least first acceleration change information; processing the second motion signal to obtain a second processing result, the second processing result including at least one of second waveform change information and second posture change information, the second waveform change information including at least second acceleration change information; determining whether the user has fallen based on the first processing result and the second processing result, and issuing a fall alarm when it is determined that the user has fallen.

[0007] In one embodiment, the second processing result includes the second waveform change information, and the step of determining whether the user has fallen based on the first processing result and the second processing result includes: if the first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, and the first posture change information conforms to a first preset posture change characteristic, then it is determined that the user has fallen.

[0008] In one embodiment, the second processing result includes the second waveform change information and the second posture change information. The step of determining whether the user has fallen based on the first processing result and the second processing result includes: if the first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, the first posture change information conforms to a first preset posture change characteristic, and the second posture change information conforms to a second preset posture change characteristic, then it is determined that the user has fallen.

[0009] In one embodiment, the first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, including at least one of the following: the first waveform change information sequentially includes waveform change characteristics of a weightlessness stage, a hypergravity stage, and a subsequent stage; in the weightlessness stage, the first acceleration is less than the gravitational acceleration; in the hypergravity stage, the first acceleration is greater than the gravitational acceleration; and in the subsequent stage, the components of the first acceleration on the three axes continuously change; the second waveform change information sequentially includes waveform change characteristics of a weightlessness stage, a hypergravity stage, and a subsequent stage; in the weightlessness stage, the second acceleration is less than the gravitational acceleration; in the hypergravity stage, the second acceleration is greater than the gravitational acceleration; and in the subsequent stage, the components of the second acceleration on the three axes continuously change.

[0010] In one embodiment, the first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, and further include: in the weightlessness stage, the change amplitude of the first waveform change information is greater than the change amplitude of the second waveform change information; in the overweight stage, the change amplitude of the second waveform change information is greater than the change amplitude of the first waveform change information.

[0011] In one embodiment, the second processing result includes the second posture change information, and the step of determining whether the user has fallen based on the first processing result and the second processing result includes: if the first waveform change information conforms to a preset waveform change feature, the first posture change information conforms to a first preset posture change feature, and the second posture change information conforms to a second preset posture change feature, then it is determined that the user has fallen.

[0012] In one embodiment, the first waveform change information conforms to preset waveform change characteristics, including: the first waveform change information sequentially includes waveform change characteristics of a weightlessness stage, a hypergravity stage, and a subsequent stage; in the weightlessness stage, the first acceleration is less than the gravitational acceleration; in the hypergravity stage, the first acceleration is greater than the gravitational acceleration; and in the subsequent stage, the components of the first acceleration on the three axes continuously change.

[0013] In one embodiment, when it is determined that the user has fallen, the method further includes: determining the fall type based on the first processing result and the second processing result; and outputting the fall type.

[0014] In one embodiment, the fall type includes falling forward, falling backward, and falling to the side. Determining the fall type based on the first processing result and the second processing result includes: if the first posture change information corresponds to a change in the user's torso posture from an upright state to a lying state, then the fall type is determined to be a falling forward; if the first posture change information corresponds to a change in the user's torso posture from an upright state to a supine state, then the fall type is determined to be a falling backward; if the first posture change information corresponds to a change in the user's torso posture from an upright state to a sideways state, then the fall type is determined to be a falling to the side.

[0015] In one embodiment, the fall type includes conscious fall and unconscious fall, and determining the fall type based on the first processing result and the second processing result includes: determining the first moment when the user's torso is impacted based on the first processing result; determining the second moment when the user's arm is impacted based on the second processing result; if the first moment is before the second moment, then the fall type is determined to be an unconscious fall; if the first moment is after the second moment, then the fall type is determined to be a conscious fall.

[0016] In one embodiment, the method further includes: generating a fall process description based on the first processing result and the second processing result, the fall process description including at least information related to the fall type; and outputting the fall process description.

[0017] In one embodiment, the first waveform change information further includes first velocity change information, and the second waveform change information further includes second velocity change information. The first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, and further include at least one of the following: in the weightlessness stage, the first velocity gradually increases with time, and in the overweight stage, the first velocity gradually decreases with time; in the weightlessness stage, the second velocity gradually increases with time, and in the overweight stage, the second velocity gradually decreases with time.

[0018] A second aspect of this invention provides a fall detection method, the method comprising: acquiring a first motion signal collected by a first motion sensor worn on a user's torso, and acquiring a second motion signal collected by a second motion sensor worn on the user's upper or lower limb; processing the first motion signal to obtain a first processing result, the first processing result including at least one of first waveform change information and first posture change information, the first waveform change information including at least first acceleration change information; processing the second motion signal to obtain a second processing result, the second processing result including second waveform change information and second posture change information, the second waveform change information including at least second acceleration change information; determining whether the user has fallen based on the first processing result and the second processing result, and issuing a fall alarm when it is determined that the user has fallen.

[0019] In one embodiment, the first processing result includes the first waveform change information, and the step of determining whether the user has fallen based on the first processing result and the second processing result includes: if the first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, and the second posture change information conforms to a second preset posture change characteristic, then it is determined that the user has fallen.

[0020] In one embodiment, the first processing result includes the first waveform change information and the first posture change information. The step of determining whether the user has fallen based on the first processing result and the second processing result includes: if the first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, the first posture change information conforms to a first preset posture change characteristic, and the second posture change information conforms to a second preset posture change characteristic, then it is determined that the user has fallen.

[0021] In one embodiment, the first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, including at least one of the following: the first waveform change information sequentially includes waveform change characteristics of a weightlessness stage, a hypergravity stage, and a subsequent stage; in the weightlessness stage, the first acceleration is less than the gravitational acceleration; in the hypergravity stage, the first acceleration is greater than the gravitational acceleration; and in the subsequent stage, the components of the first acceleration on the three axes continuously change; the second waveform change information sequentially includes waveform change characteristics of a weightlessness stage, a hypergravity stage, and a subsequent stage; in the weightlessness stage, the second acceleration is less than the gravitational acceleration; in the hypergravity stage, the second acceleration is greater than the gravitational acceleration; and in the subsequent stage, the components of the second acceleration on the three axes continuously change.

[0022] In one embodiment, the first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, and further include: in the weightlessness stage, the change amplitude of the first waveform change information is greater than the change amplitude of the second waveform change information; in the overweight stage, the change amplitude of the second waveform change information is greater than the change amplitude of the first waveform change information.

[0023] In one embodiment, the first processing result includes the first posture change information, and the step of determining whether the user has fallen based on the first processing result and the second processing result includes: the first posture change information conforms to a first preset posture change feature, the second waveform change information conforms to a preset waveform change feature, and the second posture change information conforms to a second preset posture change feature, then it is determined that the user has fallen.

[0024] In one embodiment, the second waveform change information conforms to preset waveform change characteristics, including: the second waveform change information sequentially includes waveform change characteristics of a weightlessness stage, a hypergravity stage, and a subsequent stage; in the weightlessness stage, the second acceleration is less than the gravitational acceleration; in the hypergravity stage, the second acceleration is greater than the gravitational acceleration; and in the subsequent stage, the components of the second acceleration on the three axes continuously change.

[0025] In one embodiment, the first waveform change information further includes first velocity change information, and the second waveform change information further includes second velocity change information. The first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, and further include at least one of the following: in the weightlessness stage, the first velocity gradually increases with time, and in the overweight stage, the first velocity gradually decreases with time; in the weightlessness stage, the second velocity gradually increases with time, and in the overweight stage, the second velocity gradually decreases with time.

[0026] A third aspect of this invention provides a fall detection method, the method comprising: acquiring a first motion signal collected by a first motion sensor worn on a user's torso, and acquiring a second motion signal collected by a second motion sensor worn on the user's upper or lower limb; processing the first motion signal to obtain a first processing result, the first processing result including at least one of first waveform change information and first posture change information; processing the second motion signal to obtain a second processing result, the second processing result including at least one of second waveform change information and second posture change information; determining whether the user has fallen based on the first processing result and the second processing result, and issuing a fall alarm when it is determined that the user has fallen.

[0027] A fourth aspect of this invention provides a fall detection system, comprising: a first motion sensor worn on a user's torso for collecting a first motion signal; a second motion sensor worn on the user's arm for collecting a second motion signal; and a processor connected to the first and second motion sensors for executing the fall detection method described above. The fall detection system includes a first mobile monitoring device and a second mobile monitoring device. The first mobile monitoring device is worn on the user's torso, and the first motion sensor is disposed within the first mobile monitoring device. The second mobile monitoring device is worn on the user's arm, and the second motion sensor is disposed within the second mobile monitoring device. The first mobile monitoring device further includes a first physiological sensor for collecting a first physiological signal, and the second mobile monitoring device further includes a second physiological sensor for collecting a second physiological signal. The first and second physiological signals are physiological signals of different types.

[0028] In one embodiment, the first mobile monitoring device has a first external communication interface for providing a first external communication connection between the first mobile monitoring device and the external processor, and the first mobile monitoring device is configured to send the first physiological signal and the first motion signal to the processor through the first external communication connection; the second mobile monitoring device has a second external communication interface for providing a second external communication connection between the second mobile monitoring device and the external processor, and the second mobile monitoring device is configured to send the second physiological signal and the second motion signal to the processor through the second external communication connection.

[0029] In one embodiment, the first mobile monitoring device and the second mobile device each have an internal communication interface for providing an internal communication connection between the first mobile monitoring device and the second mobile monitoring device; the first mobile monitoring device is configured to send the first physiological signal and the first motion signal to the second mobile monitoring device through the internal communication connection; the second mobile monitoring device has an external communication interface for providing an external communication connection between the second mobile monitoring device and the external processor; the second mobile monitoring device is configured to send the first physiological signal, the first motion signal, the second physiological signal, and the second motion signal to the external processor through the external communication connection; or, the second mobile monitoring device is configured to send the second physiological signal and the second motion signal to the first mobile monitoring device through the internal communication connection; the first mobile monitoring device has an external communication interface for providing an external communication connection between the first mobile monitoring device and the external processor; the first mobile monitoring device is configured to send the first physiological signal, the first motion signal, the second physiological signal, and the second motion signal to the external processor through the external communication connection.

[0030] In one embodiment, the first mobile monitoring device has an internal communication interface for providing an internal communication connection between the first mobile monitoring device and the second mobile monitoring device; the first mobile monitoring device is configured to send the first physiological signal and the first motion signal to the second mobile monitoring device through the internal communication connection, and the processor is disposed in the second mobile monitoring device; or, the second mobile monitoring device is configured to send the second physiological signal and the second motion signal to the first mobile monitoring device through the internal communication connection, and the processor is disposed in the first mobile monitoring device.

[0031] In one embodiment, the first motion sensor includes a first accelerometer, or the first motion sensor includes both a first accelerometer and a first gyroscope; the second motion sensor includes a second accelerometer, or the second motion sensor includes both a second accelerometer and a second gyroscope.

[0032] In one embodiment, at least one of the first motion sensor and the second motion sensor includes an accelerometer, and at least one of the first motion sensor and the second motion sensor includes a gyroscope.

[0033] The fall detection method and device of the present invention determine whether a user has fallen based on motion signals from the user's torso and arms, thereby improving the accuracy of fall detection. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 A schematic flowchart of a fall detection method according to an embodiment of the present invention is shown; Figure 2 A schematic diagram of a first acceleration signal and a second acceleration signal according to an embodiment of the present invention is shown; Figure 3 A schematic diagram of the combined acceleration signal of a first acceleration signal and a second acceleration signal according to an embodiment of the present invention is shown; Figure 4 A schematic block diagram of a fall detection system according to an embodiment of the present invention is shown; Figure 5 A schematic diagram of a first mobile monitoring device and a second mobile monitoring device according to an embodiment of the present invention is shown; Figure 6 A schematic flowchart of a fall detection method according to another embodiment of the present invention is shown. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely a part of the embodiments of the present invention, and not all of the embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of the present invention.

[0037] In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the invention. However, it will be apparent to those skilled in the art that the invention can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described in order to avoid obscuring the invention.

[0038] It should be understood that the invention can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0039] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. When used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and / or “including,” when used in this specification, identify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term “and / or” includes any and all combinations of the associated listed items.

[0040] To fully understand this invention, a detailed structure will be presented in the following description to illustrate the technical solution proposed by this invention. Optional embodiments of the invention are described in detail below; however, in addition to these detailed descriptions, the invention may have other embodiments.

[0041] In this embodiment of the invention, falls are classified into the following types based on their type and mechanism of action: The first type of fall occurs when a person is standing or walking and trips, resulting in a forward fall, a backward fall, or a fall to the left or right due to being pushed. This type of fall is relatively rapid and can therefore be called a rapid fall. The second type of fall occurs due to blurred vision or instability while standing up. This type of fall is relatively slow and can therefore be called a slow fall. In addition, there are also special types of falls, such as falling from a bed.

[0042] Existing fall detection solutions typically rely on motion signals collected by a single motion sensor for fall detection. For example, chest strap-based fall detection solutions usually rely on motion signals collected by a motion sensor located on the user's chest. This solution can detect rapid falls but struggles to detect slow falls involving gradual torso shifts. Wristband-based fall detection solutions typically rely on motion signals collected by a motion sensor located on the user's wrist. This solution can detect rapid falls or slow falls involving rapid arm strikes, but sudden arm movements can easily lead to false positives. In contrast, the fall detection method and system of this invention determine whether a user has fallen by combining motion signals from both the user's torso and arms, thus improving the accuracy of fall detection.

[0043] Below, first refer to Figure 1 A fall detection method according to an embodiment of the present invention is described. Figure 1 A schematic flowchart of a fall detection method 100 according to an embodiment of the present invention is shown.

[0044] like Figure 1As shown, the fall detection method 100 of this embodiment includes the following steps: In step S110, a first motion signal is acquired by a first motion sensor worn on the user's torso, and a second motion signal is acquired by a second motion sensor worn on the user's arm. In step S120, the first motion signal is processed to obtain a first processing result. The first processing result includes the first waveform change information and the first attitude change information. The first waveform change information includes at least the first acceleration change information. In step S130, the second motion signal is processed to obtain a second processing result. The second processing result includes at least one of second waveform change information and second attitude change information. The second waveform change information includes at least the second acceleration change information. In step S140, it is determined whether the user has fallen based on the first processing result and the second processing result, and a fall alarm is triggered when it is determined that the user has fallen.

[0045] Specifically, the first motion sensor and the second motion sensor are respectively worn on the user's torso and arm. The torso refers to the human body, specifically the part of the body excluding the limbs and head, including the neck, chest, and abdomen. The arm refers to the upper limb, specifically the part of the body below the shoulders and above the wrist, including the upper arm, elbow, forearm, or wrist. In one example, the first motion sensor can be worn on the user's chest, and the second motion sensor can be worn on the user's wrist. The first and second motion sensors can be directly attached to the user's body or clothing, or they can be integrated into other devices. The first and second motion sensors collect motion signals in real time. In step S110, the first motion signal collected by the first motion sensor worn on the user's torso and the second motion signal collected by the second motion sensor worn on the same user's arm are acquired. The first and second motion signals are acquired synchronously. Since the motion characteristics of the torso and the wrist differ significantly during a fall, detecting falls based on motion signals collected by the motion sensors at the torso and arm can improve the comprehensiveness of fall detection and avoid missed detections.

[0046] The first motion sensor and the second motion sensor are sensors used to sense user motion. They can be of the same or different types. For example, the first motion sensor may include a first accelerometer for acquiring a first acceleration signal, or it may include both a first accelerometer and a first gyroscope for acquiring the first acceleration signal and a first velocity signal, respectively. The second motion sensor may include a second accelerometer for acquiring a second acceleration signal, or it may include both a second accelerometer and a second gyroscope for acquiring the second acceleration signal and the second velocity signal, respectively. An accelerometer can sense linear acceleration and tilt angle, has good low-frequency characteristics, and can measure low-speed static acceleration. Specifically, an accelerometer may be a three-axis accelerometer, a six-axis accelerometer, etc. A gyroscope can sense the rotational angular velocity of a single axis or multiple axes, and can accurately sense complex movements in free space. Specifically, a gyroscope may be a three-axis gyroscope, a six-axis gyroscope, etc. In addition to accelerometers and gyroscopes, the first and second motion sensors may also include other types of motion sensors such as electronic compasses.

[0047] For example, the first motion sensor and the second motion sensor can be disposed in the mobile monitoring device, forming part of the medical monitoring system. For instance, the first motion sensor and the second motion sensor can be disposed within the housings of the first and second mobile monitoring devices, specifically on a circuit board within the housing. The mobile monitoring device is a monitoring device capable of monitoring a user while they are in motion. In this embodiment, the mobile monitoring device is a wearable mobile monitoring device worn on the user's body, used to continue monitoring the user's physiological state in real time after the user leaves the bed. The mobile monitoring device can also communicate with bedside monitoring devices such as monitors or a central monitoring system, transmitting the user's status to the bedside monitoring device or the central monitoring system for display.

[0048] The mobile monitoring device of this invention integrates a motion sensor, enabling it to perform both monitoring and fall detection functions. Exemplarily, the mobile monitoring device includes a first mobile monitoring device and a second mobile monitoring device, which are respectively worn on the torso and arm of the same user. The first mobile monitoring device is equipped with the aforementioned first motion sensor, and the second mobile monitoring device is equipped with the aforementioned second motion sensor. The first mobile monitoring device can communicate with the second mobile monitoring device; for example, the second mobile monitoring device can send a second motion signal to the first mobile monitoring device, which then performs fall detection based on the first and second motion signals. Alternatively, the first and second mobile monitoring devices can respectively send the first and second motion signals to a third-party device, which then performs fall detection based on the first and second motion signals.

[0049] The mobile monitoring device of this invention includes at least two types of physiological sensors, each used to detect different types of physiological signals, to achieve more comprehensive monitoring. Specifically, the first mobile monitoring device is equipped with a first physiological sensor for collecting a first physiological signal; the second mobile monitoring device is equipped with a second physiological sensor for collecting a second physiological signal. The first and second physiological signals are different types of physiological signals, including but not limited to electrocardiogram signals, respiratory signals, body temperature signals, blood oxygen signals, invasive blood pressure signals, and non-invasive blood pressure signals.

[0050] In other embodiments, the first and second motion sensors can also be integrated into other wearable devices besides the mobile monitoring device, such as third-party consumer-grade wearable devices like wristbands, watches, and chest straps. Optionally, the first and second motion sensors can also be dedicated motion sensor devices, rather than integrated into other devices. The standalone motion sensors or the first and second motion sensors integrated into third-party devices can transmit the collected motion signals to the mobile monitoring device for further processing, or they can transmit the motion signals to other processors for further processing.

[0051] After obtaining the first motion signal and the second motion signal, the first motion signal and the second motion signal are processed respectively to obtain the first processing result and the second processing result. Based on the first processing result and the second processing result, it is determined whether the user has fallen. Since the first processing result is obtained based on the first motion signal from the torso, reflecting the motion characteristics of the torso, and the second processing result is obtained based on the second motion signal from the arm, reflecting the motion characteristics of the arm, judging whether the user has fallen based on the first processing result and the second processing result together can improve the accuracy of fall detection and avoid missed or false detections.

[0052] In this embodiment of the invention, fall detection is primarily based on waveform change information of the motion signal and user posture change information obtained from the motion signal. Specifically, the first processing result includes first waveform change information of the first motion signal and first posture change information of the user's torso posture, wherein the first waveform change information includes at least first acceleration change information. The second processing result includes at least one of second waveform change information of the second motion signal and second posture change information of the user's arm posture, wherein the second waveform change information includes at least second acceleration change information. The user's posture can be obtained from the integral of velocity over time, or from the relative magnitude of the components of acceleration on the three axes or the relative magnitude of velocity. Since the motion at the torso is relatively stable, while the motion at the arm fluctuates more, the first processing result has a smaller error and can be used as the primary judgment criterion, while the second processing result has a larger error and can be used as an auxiliary judgment criterion. Waveform change information better reflects fall characteristics than posture change information; therefore, the first processing result includes both first waveform change information and first posture change information, and the second processing result includes at least one of second waveform change information and second posture change information. Here, the "three axes" refer to the three coordinate axes corresponding to the sensor used to measure acceleration in the spatial coordinate system.

[0053] For example, when the second processing result includes second waveform change information of the second motion signal, if at least one of the first waveform change information and the second waveform change information conforms to a preset waveform change characteristic, and the first posture change information conforms to a first preset posture change characteristic, then it is determined that the user has fallen. When the second processing result includes second posture change information of the user's arm posture, if the first waveform change information conforms to a preset waveform change characteristic, the first posture change information conforms to the first preset posture change characteristic, and the second posture change information conforms to the second preset posture change characteristic, then it is determined that the user has fallen.

[0054] The preset waveform change characteristics and preset posture change characteristics are obtained based on the characteristics of falling. Through analysis of fall morphology, this embodiment of the invention divides the fall process into the following stages: The first stage is the weightlessness stage, which is the stage from when the body is upright to when it falls to the ground due to slipping, tripping, being pushed by other forces, etc. During this stage, the body is in a weightless state, and its vertical acceleration is less than the acceleration due to gravity, and the speed increases. The second stage is the hypergravity stage, which is the stage when the human body falls and hits the ground. In this stage, the human body is subjected to strong upward acceleration due to the strong impact. Its vertical acceleration is greater than the acceleration due to gravity, and its downward velocity decreases rapidly. The third stage is the subsequent stage, which is when the body's physiological state is regulated after a fall, resulting in shaking or other states.

[0055] At the same time, the body's posture will change before and after a fall, changing from an upright, sitting, or walking posture to a lying posture.

[0056] In summary, both the waveform of the motion signal and the posture of the human body undergo significant changes during a fall. Therefore, fall identification can be based on the waveform and posture change characteristics of the motion signal. However, considering that the torso sometimes lands first and sometimes the arms, the waveform changes of the motion signal at the arm are more pronounced in some falls, while those at the torso are more pronounced in others. Therefore, this embodiment of the invention uses both the motion signals from the torso and arms to determine if a fall has occurred.

[0057] See Figure 2 ,like Figure 2 These are the first and second acceleration signals generated when a fall occurs during walking. Figure 2 It can be seen that before the fall, both the first and second acceleration signals exhibited waveforms typical of walking, with relatively small amplitude changes and strong regularity. At the moment of the fall, both the first and second acceleration signals underwent significant changes. Figure 3 The combined acceleration signal of the first and second acceleration signals is shown. Figure 3 The waveforms of the first and second acceleration signals shown clearly demonstrate the falling pattern described above: During the weightlessness phase 1, the combined acceleration of the first and second acceleration signals is less than the gravitational acceleration g, indicating that the torso and arms are accelerating downwards. During phase 2 of the G-force, i.e., the fall and impact with the ground, the body experiences a strong upward acceleration due to the intense impact. This vertical acceleration exceeds the acceleration due to gravity, while the downward velocity rapidly decreases. Figure 3 As can be seen from this, the resultant acceleration of the first acceleration signal and the second acceleration signal is greater than the gravitational acceleration g, and is greater than 2g or even 4g; In the subsequent stage 3, through Figure 2 The relative magnitudes of the X, Y, and Z axis accelerations of the first and second acceleration signals shown can be seen to indicate that the relative magnitudes of the X, Y, and Z axis accelerations have changed, corresponding to a change in the human body's posture. The Z axis is perpendicular to the cross-section of the human body, and the relative change in the Z axis acceleration indicates that the human torso has changed from an upright posture to a supine posture.

[0058] Based on the above analysis of fall patterns, at least one of the first and second waveform change information conforms to preset waveform change characteristics, including at least one of the following: the first waveform change information sequentially includes a weightlessness phase, a gravitational acceleration phase, and a subsequent phase; in the weightlessness phase, the first acceleration is less than the gravitational acceleration; in the gravitational acceleration phase, the first acceleration is greater than the gravitational acceleration; and in the subsequent phase, the components of the first acceleration along the three axes continuously change. Similarly, the second waveform change information sequentially includes a weightlessness phase, a gravitational acceleration phase, and a subsequent phase; in the weightlessness phase, the second acceleration is less than the gravitational acceleration; in the gravitational acceleration phase, the second acceleration is greater than the gravitational acceleration; and in the subsequent phase, the components of the second acceleration along the three axes continuously change. For example, in the subsequent phase, the continuous change in the components of the second acceleration along the three axes does not exceed a preset amplitude, manifested as a small change in the user's limbs.

[0059] Furthermore, at least one of the first waveform change information and the second waveform change information conforms to preset waveform change characteristics, further including: during the weightlessness phase, the change amplitude of the first waveform change information is greater than the change amplitude of the second waveform change information; during the hypergravity phase, the change amplitude of the second waveform change information is greater than the change amplitude of the first waveform change information. (Continue to see...) Figure 3 During weightlessness, the changes in the primary acceleration signal at the torso are more pronounced than the changes in the secondary acceleration signal at the arms. Conversely, during weightlessness, the changes in the secondary acceleration signal at the arms are more pronounced than the changes in the primary acceleration signal at the arms. It should be noted that... Figure 3 The image shows the first and second acceleration signals when the arm lands first. If the user falls uncontrollably, i.e., the torso lands first, the first acceleration signal at the torso will change more significantly than the second acceleration signal at the arm during the overweight phase because the torso is hit more violently by the ground. In other words, the amplitude of the change in the first waveform information is greater than the amplitude of the change in the second waveform information.

[0060] The first and second preset posture change characteristics can also be obtained based on the above analysis of fall patterns. For example, the first preset posture change characteristic corresponds to the user's torso posture changing from an upright to a supine position. The second preset posture change characteristic corresponds to the user's arm posture changing from an upright to a supine position. A supine position means that the torso or arm is in contact with the ground, and their horizontal heights are essentially the same.

[0061] Since the downward velocity gradually increases during the weightlessness phase and rapidly decreases during the gravitational phase, in some embodiments, the first waveform change information also includes first velocity change information, and the second waveform change information also includes second velocity change information. At least one of the first waveform change information and the second waveform change information conforms to a preset waveform change characteristic, and further includes at least one of the following: during the weightlessness phase, the first velocity gradually increases with time, and during the gravitational phase, the first velocity gradually decreases with time; during the weightlessness phase, the second velocity gradually increases with time, and during the gravitational phase, the second velocity gradually decreases with time.

[0062] In some embodiments, to improve the accuracy of fall detection, a first barometer worn on the user's torso and a second barometer worn on the user's arm can be acquired. A first height of the user's torso position is determined based on the first barometer signal, and a second height of the user's arm position is determined based on the second barometer signal. After determining that a fall has occurred, if the first and second heights are detected to drop to the same level and the descent speed is greater than a preset speed, it indicates that the user has rapidly transitioned to a fallen state, and therefore the determination that the user has fallen based on the first and second motion signals is accepted. Otherwise, the determination that the user has fallen is not accepted.

[0063] Based on the above steps, a final judgment can be obtained as to whether the user has fallen. When a fall is determined to have occurred, a fall alarm is triggered to alert medical personnel to provide assistance. Optionally, the fall alarm can be in one or more forms, including sound, light, and characters. For example, the fall alarm can be output by a mobile monitoring device or a bedside monitoring device that is communicatively connected to the mobile monitoring device.

[0064] When a user is determined to have fallen, the system can further determine the fall type based on the first and second processing results, and output the fall type. The fall type can be output by sending information containing the fall type to external devices such as monitoring equipment or mobile terminals, or by providing fall type prompts through voice prompts, text prompts, or other means.

[0065] Falls can be categorized in several ways. For example, fall types can include forward falls, backward falls, and side falls. Forward, backward, and side falls primarily involve changes in the user's torso posture; therefore, the type of fall can be determined based on the initial posture change information of the user's torso. Specifically, if the initial posture change corresponds to a change in the user's torso posture from an upright to a lying position, the fall type is determined to be a forward fall; if the initial posture change corresponds to a change in the user's torso posture from an upright to a supine position, the fall type is determined to be a backward fall; and if the initial posture change corresponds to a change in the user's torso posture from an upright to a sideways position, the fall type is determined to be a side fall.

[0066] Fall types can also be categorized into conscious and unconscious falls. During a fall, if it's conscious, such as a trip, the arm usually hits the ground first; if it's unconscious, such as fainting, the torso usually hits the ground first. Therefore, to determine whether a user's fall was conscious or unconscious, the first moment of impact on the torso can be determined based on the first processing result, and the second moment of impact on the arm can be determined based on the second processing result. The fall type is then determined based on the chronological relationship between the first and second moments: if the first moment is before the second moment, it indicates the torso hit the ground first, classifying the fall as unconscious; if the first moment is after the second moment, it indicates the arm hit the ground first, classifying the fall as conscious. Distinguishing between conscious and unconscious falls is helpful in deciding on subsequent treatment or care. For example, if a user loses consciousness after a fall, medical personnel can quickly determine whether the loss of consciousness caused the fall or the fall caused the loss of consciousness, allowing for timely follow-up treatment.

[0067] In some embodiments, falls can also be classified into rapid falls, slow falls, and special falls. Rapid falls include forward falls due to tripping while standing or walking, backward falls due to slipping, or falls to the left or right due to being pushed. Rapid falls are characterized by large ranges of motion in the torso and arms, and rapid speed of movement. Slow falls are caused by dizziness or instability while standing up; in this type of fall, the torso does not undergo drastic changes, but the arms do. Special falls include, for example, falling from a bed. When classifying falls according to the categories of rapid, slow, and special falls, the fall type can be determined based on the range of the first acceleration, second acceleration, first velocity, and second velocity.

[0068] In some embodiments, based on the above analysis of the fall process, when it is determined that a user has fallen, a fall process description can be generated according to the first processing result and the second processing result, and output to external devices such as monitoring devices or mobile terminals. The fall process description may include, for example, the start and end times of the weightlessness phase, the weightlessness phase, and the subsequent phase, as well as the movement direction and posture changes of the user's arms and torso in each phase. Outputting the fall process description helps caregivers determine the cause of the fall.

[0069] The fall detection method 100 of the present invention determines whether a user has fallen based on motion signals from the user's torso and arms, thereby improving the accuracy of fall detection.

[0070] In the above embodiments, considering that the movement at the torso is relatively stable while the movement at the arm fluctuates more, the first processing result obtained from the first motion signal at the torso has a smaller error and is used as the primary judgment criterion. The second processing result obtained from the second motion signal at the arm has a larger error and is used as an auxiliary judgment criterion. Furthermore, the first processing result simultaneously includes first waveform change information and first posture change information, and the second processing result includes at least one of second waveform change information and second posture change information. In a modified embodiment, the first processing result obtained from the first motion signal at the torso can still be used as the primary judgment criterion, and the second processing result obtained from the second motion signal at the upper or lower limb can be used as an auxiliary judgment criterion. However, unlike the above embodiments, the first processing result can include only one of the first waveform change information and first posture change information, while the second processing result includes both second waveform change information and second posture change information. The fall judgment performed after obtaining the first and second processing results is similar in principle to the above embodiments and will not be repeated here. In one modified embodiment, the second processing result obtained from the second motion signal at the upper or lower limb can be used as the primary judgment basis, and the first processing result obtained from the first motion signal at the torso can be used as the auxiliary judgment basis. The fall judgment is performed after obtaining the first and second processing results. The principle is similar to that of the above embodiment, and will not be repeated here.

[0071] Below, please refer to the appendix. Figure 4 A fall detection system 400 according to one embodiment of the present invention will be described. The fall detection system of this embodiment includes a first motion sensor 410, a second motion sensor 420, and a processor 430. The first motion sensor 410 is worn on the user's torso to collect a first motion signal; the second motion sensor is worn on the user's arm to collect a second motion signal; the processor 430 is connected to the first motion sensor 410 and the second motion sensor 420 to execute the steps of the fall detection method 100 described above.

[0072] The fall detection system 400 of this invention collects a first motion signal by a first motion sensor 410 worn on the user's torso, and simultaneously collects a second motion signal by a second motion sensor 420 worn on the user's arm. The system determines whether the user has fallen based on the first and second motion signals, thereby improving the accuracy of fall detection.

[0073] The first motion sensor 410 and the second motion sensor 420 are sensors used to sense user motion. They can be of the same or different types. For example, the first motion sensor 410 may include a first accelerometer, or it may include both a first accelerometer and a first gyroscope. The second motion sensor 420 may include a second accelerometer, or it may include both a second accelerometer and a second gyroscope. An accelerometer can sense linear acceleration and tilt angle, has good low-frequency characteristics, and can measure low-speed static acceleration. Specifically, an accelerometer can be a three-axis accelerometer, a six-axis accelerometer, etc. A gyroscope can sense single-axis or multi-axis rotational angular velocity and can accurately sense complex movements in free space. Specifically, a gyroscope can be a three-axis gyroscope, a six-axis gyroscope, etc. In addition to accelerometers and gyroscopes, the first and second motion sensors may also include other types of motion sensors such as electronic compasses.

[0074] Because accelerometers measure inertial forces, which can be caused by gravity or the acceleration of the device, they are sensitive to vibration and mechanical noise. Gyroscopes detect rotational angular velocity, thus they are less sensitive to linear mechanical motion. Using both gyroscopes and accelerometers to detect motion signals can make the accelerometer output smoother. When both the first motion sensor 410 and the second motion sensor 420 include accelerometers and gyroscopes, calculating the average value of the accelerometer and gyroscope readings yields more accurate first and second motion signals, improving the accuracy of fall detection.

[0075] Processor 430 may be a central processing unit (CPU), a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other processing unit with data processing and / or instruction execution capabilities, and may control other components in the monitoring system to perform desired functions. For example, the processor may include one or more embedded processors, processor cores, microprocessors, logic circuits, hardware finite state machines (FSMs), digital signal processors (DSPs), graphics processing units (GPUs), or combinations thereof. Processor 430 may be used to execute program instructions stored in memory, causing processor 430 to perform fall detection method 100.

[0076] In some embodiments, the first motion sensor 410 and the second motion sensor 420 can be disposed in the mobile monitoring device, forming part of the medical monitoring system. For example, the first motion sensor 410 and the second motion sensor 420 can be disposed respectively within the housing of the first and second mobile monitoring devices, specifically on a circuit board within the housing. The mobile monitoring device is a monitoring device capable of providing mobile monitoring of a user. In this embodiment, the first and second mobile monitoring devices are wearable mobile monitoring devices worn on the user's body, used to continue monitoring the user's physiological state in real time after the user leaves the bed. The first and second mobile monitoring devices can be worn by attaching them to the body via a wristband, strap, or other means, or by placing them in a clothing pocket, attaching them to the user's body surface, clipping them to the user's clothing, or any combination thereof. At least one of the first and second mobile monitoring devices can also communicate with bedside monitoring devices such as a monitor or a central monitoring system to transmit the user's status to the bedside monitoring device or the central monitoring system for display.

[0077] This invention integrates a motion sensor into a first mobile monitoring device and a second mobile monitoring device, enabling both the first and second mobile monitoring devices to perform both monitoring and fall detection functions. For example, see [link to example]. Figure 5 The mobile monitoring device includes a first mobile monitoring device 510 and a second mobile monitoring device 520, which are respectively worn on the torso and arm of the same user. The first mobile monitoring device 510 is equipped with a first motion sensor 410, and the second mobile monitoring device 520 is equipped with a second motion sensor 420. The first mobile monitoring device 510 can communicate with the second mobile monitoring device 520. For example, the second mobile monitoring device 520 can send a second motion signal to the first mobile monitoring device 510, and the processor 430 of the first mobile monitoring device 510 can perform fall detection based on the first and second motion signals. Alternatively, the first and second mobile monitoring devices 510 and 520 can also send the first and second motion signals to a third-party device, where the processor 430 can perform fall detection based on the first and second motion signals.

[0078] The first mobile monitoring device 510 and the second mobile monitoring device 520 of this invention include different types of physiological sensors, each used to detect different types of physiological signals, to achieve more comprehensive monitoring of the user. Specifically, the first mobile monitoring device 510 is equipped with a first physiological sensor for collecting first physiological signals; the second mobile monitoring device 520 is equipped with a second physiological sensor for collecting second physiological signals. The first and second physiological signals are different types of physiological signals, including but not limited to electrocardiogram signals, respiratory signals, body temperature signals, blood oxygen signals, invasive blood pressure signals, and non-invasive blood pressure signals.

[0079] In one example, see [link to example]. Figure 5 The first mobile monitoring device 510 is worn on the user's torso. The first physiological sensor in the first mobile monitoring device 510 is an electrocardiogram (ECG) signal sensor, and the first physiological signal it collects is an ECG signal. The second mobile monitoring device 520 is worn on the user's arm. The second physiological sensor in the second mobile monitoring device 520 is a blood oxygen signal sensor, and the second physiological signal it collects is a blood oxygen signal. The first and second mobile monitoring devices 510 and 520 are also connected in series with multiple electrode pads, which are worn on different parts of the user's body. For example, the ECG signal sensor can be connected in series with at least some of the electrode pads. The blood oxygen signal sensor in the second mobile monitoring device 520 includes a blood oxygen probe, which can be a clip-on structure for clamping onto the user's finger to measure blood oxygen parameters, such as blood oxygen concentration, using light intensity signals. The first and second mobile monitoring devices may also include other types of physiological sensors besides the ECG signal sensor and the blood oxygen signal sensor. For example, the second mobile monitoring device 520 may also integrate a blood pressure signal sensor, which may also be set up separately and connected to the second mobile monitoring device; at least some of the electrode pads may also constitute a respiratory signal sensor, and the respiratory signal sensor and the electrocardiogram signal sensor may share the same electrode pads; the first mobile monitoring device 510 may also integrate a temperature signal sensor, which includes a body temperature probe led out from the first mobile monitoring device 510 and extended to the user's armpit, so as to facilitate the measurement of the user's armpit temperature.

[0080] In some embodiments, the first mobile monitoring device 510 and the second mobile monitoring device 520 can each transmit the collected physiological signals, motion signals, etc., to an external processor 430, which processes the signals, thereby reducing the size and weight of the first mobile monitoring device 510 and the second mobile monitoring device 520 and improving the portability and wearing comfort of the devices. The external device can be a bedside monitor, a central station, or other monitoring equipment, or it can be a mobile phone, computer, cloud server, etc. Specifically, the first mobile monitoring device 510 has a first external communication interface for providing a first external communication connection between the first mobile monitoring device 510 and the external processor 430. The first mobile monitoring device 510 is configured to transmit the first physiological signal and the first motion signal to the processor 430 through the first external communication connection. The second mobile monitoring device 520 has a second external communication interface for providing a second external communication connection between the second mobile monitoring device 520 and the external processor 430. The second mobile monitoring device 520 is configured to transmit the second physiological signal and the second motion signal to the processor 430 through the second external communication connection. The first external communication interface and the second external communication interface can be wireless communication interfaces of any communication protocol, such as one or more wireless interfaces including infrared, Bluetooth, Wi-Fi, and Wireless Medical Telemetry Service (WMTS) communication, one or more local area network interfaces consisting of Ethernet, Token Ring, Token Bus, and Fiber Distributed Data Interface (FDDI) which serves as the backbone of these three networks, or one or more wired data connection interfaces such as asynchronous transmission standard interface and Universal Serial Bus.

[0081] In another embodiment, one of the first mobile monitoring device 510 and the second mobile monitoring device 520 can be used as a master device and the other can be used as a slave device. The master device is used to acquire the motion signals and physiological signals collected by the slave device and forward them together with the motion signals and physiological signals collected by itself to the external processor 430, thereby reducing the power consumption of the slave device and saving the size and cost of the device.

[0082] Specifically, the first mobile monitoring device 510 and the second mobile monitoring device 520 each have an internal communication interface for providing an internal communication connection between the two devices. The internal communication interface can be a wireless communication interface or a wired communication interface using any communication protocol. As one implementation, the second mobile monitoring device 520 can be used as the master device. The first mobile monitoring device 510 is configured to send a first physiological signal and a first motion signal to the second mobile monitoring device 520 via the internal communication connection. The second mobile monitoring device 520 has an external communication interface for providing an external communication connection between the second mobile monitoring device 520 and an external processor 430. The second mobile monitoring device 520 is configured to send the first physiological signal, the first motion signal, the second physiological signal, and the second motion signal to the external processor 430 via the external communication connection. As another implementation, the first mobile monitoring device 510 can be used as the main device, and the second mobile monitoring device 520 can be configured to send the second physiological signal and the second motion signal to the first mobile monitoring device 510 through an internal communication connection. The first mobile monitoring device 510 has an external communication interface for providing an external communication connection between the first mobile monitoring device 510 and an external processor 430. The first mobile monitoring device 510 is configured to send the first physiological signal, the first motion signal, the second physiological signal, and the second motion signal to the external processor through the external communication connection.

[0083] The processor 430 can also be the processor of the first mobile monitoring device 510 or the second mobile monitoring device 520 itself. Specifically, the first mobile monitoring device 510 and the second mobile monitoring device 520 each have an internal communication interface for providing an internal communication connection between the first mobile monitoring device 510 and the second mobile monitoring device 520; the first mobile monitoring device 510 is configured to send a first physiological signal and a first motion signal to the second mobile monitoring device 520 through the internal communication connection, and the processor 430 is located in the second mobile monitoring device 520, whereby the processor 430 of the second mobile monitoring device 520 performs fall detection based on the first motion signal and the second motion signal, and performs monitoring based on the first physiological signal and the second physiological signal; or, the second mobile monitoring device 520 is configured to send a second physiological signal and a second motion signal to the first mobile monitoring device 510 through the internal communication connection, and the processor 430 is located in the first mobile monitoring device 510, whereby the processor 430 of the first mobile monitoring device 510 performs fall detection based on the first motion signal and the second motion signal, and performs monitoring based on the first physiological signal and the second physiological signal.

[0084] When fall detection is performed by the processor 430 of the first mobile monitoring device 510 or the second mobile monitoring device 520, the mobile monitoring device can perform fall detection in real time without communicating with other external devices, so that the fall detection system 400 can operate normally without relying on external communication connections.

[0085] For example, at least one of the first mobile monitoring device 510 and the second mobile monitoring device 520 further includes an alarm device, such as a buzzer and an alarm light electrically connected to the processor 430, for providing an audible and visual alarm when the processor 430 detects that the user has fallen.

[0086] In some embodiments, the fall detection system 400 further includes a first barometer and a second barometer, which are connected to a processor 430. The first barometer is worn on the user's torso to collect a first barometer signal, and the second barometer is worn on the user's torso to collect a second barometer signal. If the user falls, the first and second barometer signals will change significantly. After the fall, the torso and arms will drop to the same horizontal level, so the first and second barometer signals will eventually become essentially the same. Based on these characteristics, the processor 430 can use the first and second barometer signals to help determine whether the user has fallen, improving the accuracy of fall detection. Exemplarily, the first barometer can be integrated into a first mobile monitoring device, and the second barometer can be integrated into a second mobile monitoring device.

[0087] In other embodiments, the first motion sensor 410 and the second motion sensor 420 can also be integrated into other wearable devices besides the mobile monitoring device, such as into consumer-grade wearable third-party devices like wristbands, watches, and chest straps. Alternatively, the first motion sensor 410 and the second motion sensor 420 can be dedicated motion sensor devices instead of being integrated into other devices. The independent first motion sensor 410 and the second motion sensor 420, or the first motion sensor 410 and the second motion sensor 420 integrated into a third-party device, can transmit the collected motion signals to the mobile monitoring device for further processing, or they can transmit the motion signals to the processor 430 of other devices for further processing.

[0088] In summary, the fall detection system 400 of the present invention includes a first motion sensor worn on the user's torso and a second motion sensor worn on the user's arm, which can jointly determine whether the user has fallen based on the motion signals from the user's torso and arm, thereby improving the accuracy of fall detection.

[0089] Below, first refer to Figure 6 A fall detection method according to an embodiment of the present invention is described. Figure 6A schematic flowchart of a fall detection method 600 according to an embodiment of the present invention is shown.

[0090] like Figure 6 As shown, the fall detection method 600 of this embodiment includes the following steps: In step S610, a first motion signal is acquired by a first motion sensor worn on the user's torso, and a second motion signal is acquired by a second motion sensor worn on the user's upper or lower limbs. In step S620, the first motion signal is processed to obtain a first processing result, the first processing result including at least one of first waveform change information and first posture change information; In step S630, the second motion signal is processed to obtain a second processing result, the second processing result including at least one of second waveform change information and second posture change information; In step S640, it is determined whether the user has fallen based on the first processing result and the second processing result, and a fall alarm is triggered when it is determined that the user has fallen.

[0091] Similar to the fall detection method 100 described above, the fall detection method 600 in this embodiment also performs fall detection based on motion signals collected by motion sensors worn on different parts of the user's body, thereby improving the accuracy of fall detection. The main difference from fall detection method 100 is that in fall detection method 600, the second motion sensor can be worn on either the user's upper limb or lower limb. Correspondingly, the second posture change information can be either upper limb posture change information or lower limb posture change information. When a user falls, the lower limbs usually land before the torso, and the knee or hip experiences a violent impact, causing corresponding changes in the waveform of the second motion signal and the posture of the user's lower limbs. Therefore, when the second motion sensor is worn on the user's lower limb, the second motion signal collected by the second motion sensor can also improve the accuracy of fall detection. Other specific details of fall detection method 600 can be found in the relevant descriptions in fall detection method 100, and will not be repeated here.

[0092] In addition, embodiments of the present invention also provide a computer storage medium on which a computer program is stored. One or more computer program instructions may be stored on the computer-readable storage medium, and a processor may execute the program instructions stored in the storage device to implement the functions (implemented by the processor) in the embodiments of the present invention and / or other desired functions, such as performing corresponding steps of the fall detection method according to embodiments of the present invention. Various applications and various data may also be stored in the computer-readable storage medium, such as various data used and / or generated by the applications.

[0093] For example, computer storage media may include a memory card for a smartphone, a storage component for a tablet computer, a hard disk for a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media.

[0094] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of the invention. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of the invention. All such changes and modifications are intended to be included within the scope of the invention as claimed in the appended claims.

[0095] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0096] In the several embodiments provided by this invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0097] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0098] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of the invention. However, this approach should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with fewer features than all of those in a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0099] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus so disclosed can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature serving the same, equivalent, or similar purpose.

[0100] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0101] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules according to embodiments of the present invention. The present invention can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing some or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0102] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

Claims

1. A fall detection method, characterized in that, The method includes: Acquire a first motion signal from a first motion sensor worn on the user's torso, and acquire a second motion signal from a second motion sensor worn on the user's arm; The first motion signal is processed to obtain a first processing result, the first processing result including first waveform change information and first attitude change information, the first waveform change information including at least first acceleration change information; The second motion signal is processed to obtain a second processing result, the second processing result including at least one of second waveform change information and second attitude change information, the second waveform change information including at least second acceleration change information; Based on the first processing result and the second processing result, determine whether the user has fallen, and issue a fall alarm when it is determined that the user has fallen; wherein, when it is determined that the user has fallen, the method further includes: The type of fall is determined based on the first processing result and the second processing result; And, output the fall type, where, The types of falls include falling forward, falling backward, and falling to the side, or the types of falls include falls that are not under conscious control and falls that are under conscious control.

2. The method according to claim 1, characterized in that, The second processing result includes the second waveform change information. The step of determining whether the user has fallen based on the first processing result and the second processing result includes: If the first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, and the first posture change information conforms to a first preset posture change characteristic, then it is determined that the user has fallen.

3. The method according to claim 1, characterized in that, The second processing result includes the second waveform change information and the second posture change information. The step of determining whether the user has fallen based on the first processing result and the second processing result includes: If the first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, the first posture change information conforms to the first preset posture change characteristics, and the second posture change information conforms to the second preset posture change characteristics, then it is determined that the user has fallen.

4. The method according to claim 2 or 3, characterized in that, The first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, including at least one of the following: The first waveform change information includes waveform change characteristics of the weightlessness stage, the hypergravity stage, and the subsequent stage in sequence; During the weightlessness phase, the first acceleration is less than the gravitational acceleration; during the hypergravity phase, the first acceleration is greater than the gravitational acceleration; and in the subsequent phases, the components of the first acceleration along the three axes continuously change. The second waveform change information sequentially includes waveform change characteristics of the weightlessness stage, the hypergravity stage, and the subsequent stage; During the weightlessness phase, the second acceleration is less than the gravitational acceleration; during the hypergravity phase, the second acceleration is greater than the gravitational acceleration; and in the subsequent phases, the components of the second acceleration along the three axes continuously change.

5. The method according to claim 4, characterized in that, The first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, and further include: During the weightlessness phase, the magnitude of the change in the first waveform information is greater than the magnitude of the change in the second waveform information. During the overweight phase, the magnitude of the change in the second waveform information is greater than the magnitude of the change in the first waveform information.

6. The method according to claim 1, characterized in that, The second processing result includes the second posture change information. The step of determining whether the user has fallen based on the first processing result and the second processing result includes: If the first waveform change information conforms to the preset waveform change characteristics, the first posture change information conforms to the first preset posture change characteristics, and the second posture change information conforms to the second preset posture change characteristics, then it is determined that the user has fallen.

7. The method according to claim 6, characterized in that, The first waveform change information conforms to preset waveform change characteristics, including: The first waveform change information sequentially includes waveform change characteristics of a weightlessness stage, a hypergravity stage, and a subsequent stage; in the weightlessness stage, the first acceleration is less than the gravitational acceleration; in the hypergravity stage, the first acceleration is greater than the gravitational acceleration; and in the subsequent stage, the components of the first acceleration on the three axes continuously change.

8. The method according to claim 1, characterized in that, When the fall type includes forward fall, backward fall, and side fall, the step of determining the fall type based on the first processing result and the second processing result includes: If the first posture change information corresponds to the user's torso posture changing from an upright state to a lying state, then the fall type is determined to be a forward fall; If the first posture change information corresponds to the user's torso posture changing from an upright state to a supine state, then the fall type is determined to be a backward fall; If the first posture change information corresponds to a change in the user's torso posture from an upright state to a sideways state, then the fall type is determined to be a sideways fall.

9. The method according to claim 1, characterized in that, When the fall type includes both conscious and unconscious falls, determining the fall type based on the first processing result and the second processing result includes: The first moment when the user's torso was impacted is determined based on the first processing result; The second moment when the user's arm was struck is determined based on the second processing result; If the first moment is before the second moment, the fall type is determined to be an uncontrolled fall; if the first moment is after the second moment, the fall type is determined to be a controlled fall.

10. The method according to claim 1, characterized in that, The method further includes: A fall process description is generated based on the first processing result and the second processing result, and the fall process description includes at least information related to the fall type; And output a description of the fall process.

11. The method according to claim 4, characterized in that, The first waveform change information further includes first velocity change information, and the second waveform change information further includes second velocity change information. The first waveform change information and the second waveform change information at least partially conform to preset waveform change characteristics, and further include at least one of the following: During the weightlessness phase, the first velocity gradually increases over time; during the gravitational phase, the first velocity gradually decreases over time. During the weightlessness phase, the second velocity gradually increases over time, and during the gravitational phase, the second velocity gradually decreases over time.

Images