CN108175388A - Behavior monitoring method and device based on wearable device - Google Patents

Abstract

Embodiments of the present invention provide a wearable device-based behavior monitoring method and device. According to the user's acceleration information monitored by the wearable device in real time, the embodiment of the present invention determines the first moment when the amplitude of the user's acceleration is greater than the preset amplitude and the peak value of the acceleration corresponding to the first moment, and calculates the acceleration after the first moment. The difference in the magnitude of the user's acceleration corresponding to adjacent moments within the preset time period is based on the user's acceleration vector corresponding to the historical moment before the first moment, and the user's acceleration vector corresponding to the second moment after the first moment , to determine the change of the user's azimuth angle between the historical moment and the second moment, according to the difference in the amplitude of the user's acceleration corresponding to the adjacent moment in the preset time period after the first moment, and the historical moment and the second moment Changes in the azimuth angles of the users between them determine the behavior information of the users and improve the accuracy of monitoring the behavior information of the users.

Description

Behavior monitoring method and device based on wearable devices

technical field

The embodiments of the present invention relate to the field of communication technologies, and in particular to a wearable device-based behavior monitoring method and device.

Background technique

The wearable health monitoring system is based on wearable devices, collects information such as the physiology, activity, location and environment of the human body through various types of sensors, and processes these information locally or remotely through communication technology to monitor the user's current or future health. to make a diagnosis or prediction of a physical condition. Wearable health monitoring systems can provide patients with low-load, non-contact, long-term continuous physiological monitoring, and are considered to be the most effective and practical means of monitoring in the new generation of medical monitoring mode.

In the existing technology, the wearable device monitors the user's heart rate data continuously around the clock, and automatically transmits it to the smartphone for analysis and processing through Bluetooth short-distance communication technology; The instrument is used to collect signal data and position data reflecting the main movement posture changes of the human body.

However, the accelerometer and gyroscope built into the smartphone cannot accurately monitor the user's daily behavior.

Contents of the invention

Embodiments of the present invention provide a wearable device-based behavior monitoring method and device, so as to improve the accuracy of monitoring user behavior information.

An aspect of the embodiments of the present invention is to provide a wearable device-based behavior monitoring method, including:

Obtain the user's acceleration information monitored by the wearable device in real time;

According to the user's acceleration information monitored by the wearable device in real time, determine the first moment when the magnitude of the user's acceleration is greater than a preset magnitude and the peak value of the acceleration corresponding to the first moment;

calculating the difference in magnitude of the user's acceleration corresponding to adjacent moments within a preset time period after the first moment;

Determine the historical moment and the second moment according to the acceleration vector of the user corresponding to the historical moment before the first moment and the acceleration vector of the user corresponding to the second moment after the first moment between changes in the user's azimuth;

According to the difference in magnitude of the acceleration of the user corresponding to adjacent moments within a preset time period after the first moment, and the azimuth angle of the user between the historical moment and the second moment change, and determine the behavior information of the user.

Another aspect of the embodiments of the present invention is to provide a wearable device-based behavior monitoring device, including:

An acquisition module, configured to acquire the user's acceleration information monitored by the wearable device in real time;

A determining module, configured to determine, according to the user's acceleration information monitored by the wearable device in real time, the first moment when the magnitude of the user's acceleration is greater than a preset magnitude and the peak value of the acceleration corresponding to the first moment;

A calculation module, configured to calculate the difference in magnitude of the user's acceleration corresponding to adjacent moments within a preset time period after the first moment;

The determining module is further configured to: determine the user's acceleration vector corresponding to a historical moment before the first moment and the user's acceleration vector corresponding to a second moment after the first moment. The change of the azimuth angle of the user between the historical moment and the second moment; the difference in the magnitude of the acceleration of the user corresponding to the adjacent moment in the preset time period after the first moment, and The change of the azimuth angle of the user between the historical moment and the second moment determines behavior information of the user.

The wearable device-based behavior monitoring method and device provided by the embodiments of the present invention determine the first moment and the first moment when the amplitude of the user's acceleration is greater than the preset amplitude according to the user's acceleration information monitored by the wearable device in real time. The peak value of the acceleration corresponding to the time, calculate the difference value of the acceleration amplitude value of the user corresponding to the adjacent time in the preset time period after the first time, according to the acceleration vector of the user corresponding to the historical time before the first time, and the first time The acceleration vector of the user corresponding to the second moment after the first moment determines the change of the azimuth angle of the user between the historical moment and the second moment, and according to the acceleration vector of the user corresponding to the adjacent moment in the preset time period after the first moment The difference of the amplitude value and the change of the azimuth angle of the user between the historical moment and the second moment determine the behavior information of the user and improve the accuracy of monitoring the behavior information of the user.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description serve to explain the principles of the disclosure.

FIG. 1 is a schematic diagram of a communication system provided by an embodiment of the present invention;

FIG. 2 is a schematic structural diagram of a wearable device provided by an embodiment of the present invention;

FIG. 3 is a flowchart of a behavior monitoring method based on a wearable device provided by an embodiment of the present invention;

FIG. 4 is a schematic diagram of acceleration over time provided by an embodiment of the present invention;

FIG. 5 is a flowchart of a wearable device-based behavior monitoring method provided by another embodiment of the present invention;

FIG. 6 is a flowchart of a wearable device-based behavior monitoring method provided by another embodiment of the present invention;

FIG. 7 is a structural diagram of a behavior monitoring device based on a wearable device provided by an embodiment of the present invention;

Fig. 8 is a structural diagram of a behavior monitoring device based on a wearable device according to another embodiment of the present invention.

By means of the above-mentioned drawings, certain embodiments of the present disclosure have been shown and will be described in more detail hereinafter. These drawings and written description are not intended to limit the scope of the disclosed concept in any way, but to illustrate the disclosed concept for those skilled in the art by referring to specific embodiments.

Detailed ways

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

The behavior monitoring method based on wearable devices provided by the present invention can be applied to the communication system shown in FIG. 1 . As shown in FIG. 1 , the communication system includes: a wearable device 11 , a mobile terminal 12 , a base station 13 , and a server 14 , wherein the wearable device 11 is specifically a vest. The wearable device 11 may include various sensors, such as a three-axis acceleration sensor for detecting the user's motion state, a heart rate sensor and a body temperature sensor for detecting the user's physiological parameters. This is only a schematic illustration, and does not limit the specific wearing form of the wearable device 11 , nor does it limit the types of sensors that the wearable device 11 may include. In addition, the wearable device 11 also includes a communication module, which is specifically a wireless communication module such as a Bluetooth module, and an acceleration sensor, a heart rate sensor, and a body temperature sensor are respectively electrically connected to the communication module, and the user's acceleration detected by the acceleration sensor in real time can pass This communication module such as bluetooth module sends to mobile terminal 12, and the user's heart rate that heart rate sensor detects in real time can send to mobile terminal 12 through this communication module such as bluetooth module, the user's body temperature that body temperature sensor detects in real time can pass this communication module such as The bluetooth module sends to the mobile terminal 12.

FIG. 2 is a schematic structural diagram of the wearable device 11 . As shown in FIG. 2 , the wearable device 11 includes: an acceleration sensor, a heart rate sensor, a body temperature sensor, a Bluetooth module, an external expansion interface, and a rechargeable lithium battery. The acceleration sensor, the heart rate sensor, and the body temperature sensor are respectively electrically connected to the Bluetooth module, for example, the acceleration sensor, the heart rate sensor, and the body temperature sensor are respectively wired to the Bluetooth module. The rechargeable lithium battery is the power supply module of the wearable device 11, which can supply power to the acceleration sensor, heart rate sensor, body temperature sensor, and Bluetooth module. Wherein, the sensors included in the wearable device 11 are not limited to acceleration sensors, heart rate sensors, and body temperature sensors. The Bluetooth module can connect other types of sensors through the external expansion interface.

Optionally, the wearable device 11 is specifically a vest, the acceleration sensor is set at the front abdomen inside the vest, the body temperature sensor is set at the armpit inside the vest, the heart rate sensor is set in the pocket inside the vest, and the Bluetooth module is set in the vest Lining at the left/right side pockets. In addition, the wearable device 11 may also include a switch button, through which the user can control the wearable device 11 to be turned on or off according to his own needs.

After the mobile terminal 12 receives the user's acceleration detected in real time by the acceleration sensor sent by the Bluetooth module of the wearable device 11, the user's heart rate detected by the heart rate sensor, and the user's body temperature detected by the body temperature sensor, the user's acceleration and heart rate can be calculated. , Body temperature display and storage. The mobile terminal 12 can also monitor the user's behavior information according to the user's acceleration detected by the acceleration sensor in real time, and send the detected user's behavior information to the server 14 through the base station 13 . In addition, when the mobile terminal 12 determines that the user's behavior information is abnormal according to the user's acceleration detected by the acceleration sensor in real time, it may also issue an alarm prompt. In addition, the mobile terminal 12 can also judge whether the user's physiological parameters are normal according to the user's heart rate detected by the heart rate sensor and/or the user's body temperature detected by the body temperature sensor. If the user's physiological parameters are abnormal, the mobile terminal 12 can also Issue an alarm prompt. This embodiment does not limit the manner in which the mobile terminal 12 issues an alarm prompt. For example, the mobile terminal 12 can call an emergency number, call a mobile terminal of a family member of the user, or issue a voice prompt to prompt the user to pay attention. In addition, the mobile terminal 12 also includes a positioning module such as GPS. When the user's behavior information and/or physiological parameters are abnormal, the positioning module can also provide the user's positioning information.

Or, after the mobile terminal 12 receives the user's acceleration detected in real time by the acceleration sensor sent by the Bluetooth module of the wearable device 11, the user's heart rate detected by the heart rate sensor, and the user's body temperature detected by the body temperature sensor, the acceleration sensor detects in real time The acceleration of the user is sent to the server 14 through the base station 13, the heart rate of the user detected by the heart rate sensor is sent to the server 14 through the base station 13, and the body temperature of the user detected by the body temperature sensor is sent to the server 14 through the base station 13. The server 14 monitors the user's behavior information according to the user's acceleration detected by the acceleration sensor in real time. When the server 14 determines that the user's behavior information is abnormal according to the user's acceleration detected by the acceleration sensor in real time, an alarm prompt is issued. In addition, the server 14 can also judge whether the user's physiological parameters are normal according to the user's heart rate detected by the heart rate sensor and/or the user's body temperature detected by the body temperature sensor. If the user's physiological parameters are abnormal, the server 14 can also send an alarm. hint. This embodiment does not limit the way in which the server 14 issues an alarm prompt. For example, the server 14 can call an emergency number, call a mobile terminal of a family member of the user, or send a voice prompt to the mobile terminal 12 through the base station 13 to remind the user of precautions, etc.

It should be noted that the communication system shown in FIG. 1 can be applied to different network standards, for example, it can be applied to Global System of Mobile communication (GSM for short), Code Division Multiple Access (CDMA for short). ), Wideband Code Division Multiple Access (WCDMA for short), Time Division-Synchronous Code Division Multiple Access (TD-SCDMA for short), Long Term Evolution (LTE for short) systems and Future network standards such as 5G. Optionally, the foregoing communication system may be a system in a scenario of Ultra-Reliable and Low Latency Communications (URLLC for short) transmission in a 5G communication system.

The base station 13 may be a base station (Base Transceiver Station, referred to as BTS) and/or a base station controller in GSM or CDMA, and may also be a base station (NodeB, referred to as NB) and/or a radio network controller (RadioNetwork Controller, referred to as NB) in WCDMA. RNC), may also be an evolved base station (Evolutional Node B, eNB or eNodeB for short) in LTE, or a relay station or an access point, or a base station (gNB) in a future 5G network, etc., and the present invention is not limited here.

The aforementioned mobile terminal 12 may be a wireless terminal or a wired terminal. A wireless terminal may be a device that provides voice and/or other business data connectivity to a user, a handheld device with a wireless connection function, or other processing device connected to a wireless modem. The wireless terminal can communicate with one or more core network devices via the radio access network (Radio Access Network, referred to as RAN), and the wireless terminal can be a mobile terminal, such as a mobile phone (or called a "cellular" phone) and a The computers, which may be, for example, portable, pocket, handheld, built-in or vehicle-mounted mobile devices, exchange speech and/or data with the radio access network. For another example, the wireless terminal may also be a Personal Communication Service (PCS for short) phone, a cordless phone, a Session Initiation Protocol (SIP for short) phone, a Wireless Local Loop (WLL for short) station, Personal digital assistant (Personal Digital Assistant, referred to as PDA) and other devices. Wireless terminal can also be called system, subscriber unit (Subscriber Unit), subscriber station (Subscriber Station), mobile station (Mobile Station), mobile station (Mobile), remote station (Remote Station), remote terminal (RemoteTerminal), access A terminal (Access Terminal), a user terminal (User Terminal), a user agent (UserAgent), and a user device (User Device or User Equipment) are not limited herein. Optionally, the aforementioned mobile terminal 12 may also be a device such as a smart watch or a tablet computer.

The technical solution of the present invention and how the technical solution of the present application solves the above technical problems will be described in detail below with specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.

Fig. 3 is a flowchart of a behavior monitoring method based on a wearable device provided by an embodiment of the present invention. Aiming at the above technical problems of the prior art, the embodiment of the present invention provides a behavior monitoring method based on a wearable device. The specific steps of the method are as follows:

Step 301. Obtain the user's acceleration information monitored by the wearable device in real time.

The execution body of the method described in the embodiment of the present invention may be the mobile terminal 12 as shown in FIG. 1 , or the server 14 as shown in FIG. 1 . The following uses the server 14 as an example to introduce a behavior monitoring method based on wearable devices.

Specifically, an acceleration sensor such as a three-axis acceleration sensor in the wearable device 11 detects the user's acceleration in real time. It can be understood that acceleration is a vector, which has both direction and magnitude. The three-axis acceleration sensor sends the acceleration detected by it to the bluetooth module, and the acceleration detected by the three-axis acceleration sensor in real time is sent to the mobile terminal 12 by the bluetooth module, and the mobile terminal 12 detects the three-axis acceleration sensor in real time through the base station 13 and the Internet The acceleration of is sent to the server 14. The amplitude of the acceleration detected by the acceleration sensor in real time changes with time, as shown in Figure 4, the horizontal axis represents the time t, the vertical axis represents the amplitude S(t) of the acceleration, and the amplitude S(t) of the acceleration changes with time t And change. The point with a larger acceleration amplitude S(t) comes from the force generated by the interaction process between the human and the outside world. For example, when a person is walking, the point with a larger acceleration amplitude S(t) comes from the human contact At the moment of reaching the ground, it can be known from the theorem of action force and reaction force that when the ground immediately exerts an upward force, the amplitude S(t) of the acceleration of the human body increases instantly. In addition, when the human body is exercising violently, the amplitude S(t) of its acceleration is also relatively large, and the human body is in an overweight state at this time.

In addition, before the whole body touches the ground, people will protectively and instinctively stretch out a certain part of the body (hands, arms, etc.) to touch the ground to slow down the damage caused by the impact, so the acceleration amplitude will appear Two consecutive peaks correspond to the acceleration amplitudes of the knee and upper body at the moment of ground contact respectively. If it is an unprotected fall process, in this case, the human body does not extend the hand, arm and other parts to slow down the impact at the moment of touching the ground, so there is only a large peak value of the acceleration amplitude, which corresponds to the acceleration amplitude of the moment the body touches the ground value. During the falling process before touching the ground, the acceleration of the human body in the vertical direction is less than 1g, and there is acceleration in the horizontal direction, but the whole body is still in a state of weightlessness, that is, the acceleration amplitude ranges from 0g to 1g.

Step 302, according to the user's acceleration information monitored by the wearable device in real time, determine the first moment when the magnitude of the user's acceleration is greater than a preset magnitude and the peak value of the acceleration corresponding to the first moment.

As shown in Figure 4, the server 14 can receive the user's acceleration collected by the acceleration sensor in real time, and the server 14 can monitor the user's acceleration in real time. Assuming that the server 14 starts to monitor the user's acceleration at time t0, whenever the server 14 receives the acceleration of the mobile terminal 12 When the acceleration of the user is sent, it is judged whether the magnitude of the acceleration is greater than the preset magnitude, which can be 2g specifically, as shown in Figure 4, assuming that at time t1, the server 14 detects that S(t1) is greater than If the amplitude is preset, record the time t1 and the peak value S(t1) of the acceleration corresponding to the time t1.

Step 303. Calculate the difference between the magnitudes of the user's acceleration corresponding to adjacent moments within a preset time period after the first moment.

After the server 14 records the peak value S(t1) of the acceleration corresponding to the time t1 and the time t1, further, detect the magnitude of the acceleration of the user corresponding to the adjacent time in T2 for a preset time period after the time t1 Difference, as shown in Figure 4, assuming that the time length between the t1 moment and the t2 moment is the preset time period T2, in the time length T2 between the t1 moment and the t2 moment, the server 14 calculates the corresponding value of the adjacent time The difference in the magnitude of the user's acceleration. For example, tk is a time between time t1 and time t2, and within the time period [t1, tk], the server 14 detects whether the difference between the acceleration magnitudes of the user corresponding to adjacent times is less than a preset difference For example, 0.3g, if within the time period [t1, tk], the difference between the magnitudes of the user’s acceleration corresponding to adjacent moments is less than 0.3g, then it is determined that the static point starts, and the time period of [t1, tk] is calculated. , the mean value M(t) of the amplitude of the acceleration of the user, the calculation formula of M(t) is specifically shown in the following formula (1):

Wherein, Th represents a preset difference such as 0.3g.

After calculating M(t), use M(t) as the standard output of the acceleration amplitude in the static state, and calculate the difference between S(t) and M(t) within the time period (tk,t2], if In the time period (tk, t2], the difference between S(t) and M(t) is still smaller than th(M), indicating that the static state continues. That is to say, in the time period (tk, t2], if If the formula (2) holds true, it means that the static state continues.

Wherein, th(M) may be Th.

Step 304, according to the acceleration vector of the user corresponding to the historical moment before the first moment and the acceleration vector of the user corresponding to the second moment after the first moment, determine the historical moment and the A change in the azimuth angle of the user between second moments.

In the output of the three coordinate axes of the acceleration sensor, the axis with the maximum/minimum output value often changes, that is, the initial horizontal axis becomes a vertical axis, because the orientation of the human body often changes before and after the fall, that is, the vertical to lie flat. Therefore, it is also necessary to calculate the change of the azimuth angle before and after the human body falls.

Specifically, select an acceleration vector such as A(t1-T1) at a historical moment before the t1 moment such as (t1-T1) moment, and select an acceleration vector such as A( t1+T2), calculate the angle θ between A(t1-T1) and A(t1+T2), the angle θ between A(t1-T1) and A(t1+T2) can indicate that the user is in ( The change of azimuth angle at time t1-T1) and time (t1+T2), the calculation formula of θ is as follows formula (3):

Step 305, according to the difference in magnitude of the user's acceleration corresponding to adjacent moments in the preset time period after the first moment, and the user's acceleration amplitude between the historical moment and the second moment The change of the azimuth angle determines the behavior information of the user.

In this embodiment, the server 14 may base on the result determined in step 302, that is, the first moment and the peak value of the acceleration corresponding to the first moment, and the result determined in step 303, that is, within a preset time period after the first moment The difference between the acceleration amplitudes of the user corresponding to adjacent moments, and the result determined in step 304, that is, the change of the azimuth angle of the user at (t1-T1) time and (t1+T2) time, determine the user's behavioral information.

Specifically, according to the difference in magnitude of the user's acceleration corresponding to adjacent moments in the preset time period after the first moment, and the Changes in the azimuth angle of the user, determining the behavior information of the user, including: if the difference in the magnitude of the acceleration of the user corresponding to adjacent moments in the preset time period after the first moment is smaller than the preset difference value, and the change of the azimuth angle of the user between the historical moment and the second moment is greater than a preset angle, then it is determined that the user has fallen.

In this embodiment, the server 14 determines that the user is exercising violently at the time t1 and may fall according to the time when the acceleration amplitude S(t) is greater than the preset amplitude S(t1) for the first time and the time t1. Further, if the difference between the acceleration amplitudes of the user corresponding to adjacent moments in T2 within a preset period of time after time t1 is smaller than the preset difference, it means that the user is still after strenuous activity, which may be dangerous. Further, if the change of the azimuth angle of the user between the time (t1-T1) and the time (t1+T2) is greater than the preset angle, it means that the user falls and stops and is in danger.

According to the user's acceleration information monitored by the wearable device in real time, the embodiment of the present invention determines the first moment when the amplitude of the user's acceleration is greater than the preset amplitude and the peak value of the acceleration corresponding to the first moment, and calculates the acceleration after the first moment. The difference in magnitude of the user's acceleration corresponding to adjacent moments within the preset time period is based on the user's acceleration vector corresponding to the historical moment before the first moment, and the user's acceleration vector corresponding to the second moment after the first moment , to determine the change of the user's azimuth angle between the historical moment and the second moment, according to the difference in the amplitude of the user's acceleration corresponding to the adjacent moment in the preset time period after the first moment, and the historical moment and the second moment Changes in the azimuth angles of the users between them determine the behavior information of the users and improve the accuracy of monitoring the behavior information of the users.

Fig. 5 is a flowchart of a behavior monitoring method based on a wearable device according to another embodiment of the present invention. On the basis of the above embodiments, the wearable device-based behavior monitoring method provided in this embodiment specifically includes the following steps:

Step 501. Obtain the user's acceleration information monitored by the wearable device in real time.

The implementation manners and specific principles of step 501 and step 301 are the same, and will not be repeated here.

Step 502: According to the user's acceleration information monitored by the wearable device in real time, determine the first moment when the magnitude of the user's acceleration is greater than a preset magnitude and the peak value of the acceleration corresponding to the first moment.

The implementation manners and specific principles of step 502 and step 302 are the same, and will not be repeated here.

Step 503: Calculate the difference between the magnitudes of the user's acceleration corresponding to adjacent moments within a preset time period after the first moment.

The implementation manners and specific principles of step 503 and step 303 are the same, and will not be repeated here.

Step 504, according to the acceleration vector of the user corresponding to the historical moment before the first moment and the acceleration vector of the user corresponding to the second moment after the first moment, determine the historical moment and the A change in the azimuth angle of the user between second moments.

The implementation manners and specific principles of step 504 and step 304 are the same, and will not be repeated here.

Step 505: Count the time interval between the peak value of acceleration corresponding to the first moment and the peak value of acceleration after the first moment.

In this embodiment, the server 14 can further count the time interval between the peak value S(t1) of the acceleration corresponding to the moment t1 and the peak value of the acceleration after the moment t1, as shown in FIG. 4 , at t3 after the moment t1 The peak value S(t3) of the acceleration occurs again at a time, and the server 14 can count the time interval between S(t1) and S(t3), that is, the server 14 can count the time interval between the time t1 and the time t3.

Step 506, according to the difference of the magnitude of the acceleration of the user corresponding to adjacent moments in the preset time period after the first moment, the orientation of the user between the historical moment and the second moment The change of the angle and the time interval between the peak value of the acceleration corresponding to the first moment and the peak value of the acceleration after the first moment determine the behavior information of the user.

In this embodiment, the server 14 may base on the result determined in step 502, that is, the first moment and the peak value of the acceleration corresponding to the first moment, and the result determined in step 503, that is, within a preset time period after the first moment The difference between the acceleration magnitudes of the user corresponding to adjacent moments, and the result determined in step 504, that is, the change of the azimuth angle of the user at (t1-T1) moment and (t1+T2) moment, and the result determined in step 505 Result: the time interval between S(t1) and S(t3), determine the user's behavior information.

In this embodiment, the process of determining user behavior information by the server 14 is specifically shown in FIG. 6 . FIG. 6 uses a decision tree algorithm as a recognition algorithm, and the decision tree algorithm only needs simple comparison, and the classification is faster. Decision tree classification algorithms are more efficient than methods that rely on comparing the distance between input samples and training samples. Specifically, as shown in FIG. 6 , the acceleration is obtained first, and the process of obtaining the acceleration is specifically as in step 301 above. It is further judged whether the magnitude of the acceleration is greater than the preset magnitude, if yes, it means that the user is exercising violently and may fall, otherwise, it means that the user is performing daily moderate activities. In order to determine whether the user has fallen, it is further judged whether the difference between the acceleration magnitudes corresponding to adjacent moments in the preset time period after the acceleration magnitude is greater than the preset magnitude is less than the preset difference, and if it is, it means that the user is active It may be dangerous, otherwise, it means that after the action is over, other activities will be carried out, and there is no danger for the time being. Wherein, the calculation method of the difference between the acceleration amplitudes corresponding to adjacent moments in the preset time period after the acceleration amplitude is greater than the preset amplitude is specifically as the above-mentioned step 303 . After determining that the user is stationary after strenuous activity and may be dangerous, it is further judged whether the change of the user's azimuth angle is greater than the preset angle. In extremely fast squatting, the calculation method of the change of the azimuth angle of the user is specifically as in step 304 above. In order to determine whether the user jumps up, it is further judged whether the time interval between adjacent acceleration peaks is greater than the preset time interval. The method of the time interval between the acceleration peaks is specifically as in step 505 above.

Specifically, according to the difference in magnitude of the user's acceleration corresponding to adjacent moments within a preset time period after the first moment, the user's acceleration between the historical moment and the second moment The change of the azimuth angle, and the time interval between the peak value of the acceleration corresponding to the first moment and the peak value of the acceleration after the first moment, determine the behavior information of the user, including: if the first moment The difference between the acceleration magnitudes of the user corresponding to adjacent moments in the subsequent preset time period is less than the preset difference, and the change of the user's azimuth angle between the historical moment and the second moment is less than If the angle is preset and the time interval between the peak value of the acceleration corresponding to the first moment and the peak value of the acceleration after the first moment is greater than the preset time interval, then it is determined that the user jumps.

Corresponding to the user's jumping action, there will be two continuous peaks in the acceleration amplitude, corresponding to the acceleration generated when the leg kicks the ground and the foot hits the ground respectively. When the user is jumping, the balance of the human body is normal. Standing at the angle of the jumper, the whole body is still in a controllable state. Therefore, although there are two peaks in the acceleration amplitude, it takes a long time compared to the fall action. When jumping in the air, the human body is in a state of weightlessness, and the continuous weightlessness time between two peaks is greater than 0.2 seconds.

When an unprotected fall occurs, although the human body instinctively slows down the time to touch the ground, due to the poor balance of the human body at this time, it is still an uncontrollable action, so the time interval between two touchdowns is very close, and two consecutive acceleration amplitudes There is basically no point of loss between the peak values, that is, when the first peak value does not drop to 1g, the body touches the ground for the second time, and the acceleration amplitude reaches the peak value again. Therefore, when the user falls, the two consecutive acceleration amplitude values The time interval between peaks is short.

In this embodiment, the server 14 determines that the user is exercising violently at the time t1 and may fall according to the time when the acceleration amplitude S(t) is greater than the preset amplitude S(t1) for the first time and the time t1. Further, if the difference between the acceleration amplitudes of the user corresponding to adjacent moments in T2 within a preset period of time after time t1 is smaller than the preset difference, it means that the user is still after strenuous activity, which may be dangerous. Furthermore, if the change of the azimuth angle of the user at the time (t1-T1) and time (t1+T2) is smaller than the preset angle, it means that the user did not fall, and may have performed other actions, such as jumping up, sitting on the sofa, extremely fast Squat down and wait. Further, if the time interval between adjacent acceleration peaks is greater than the preset time interval, it means that the user jumped.

According to the user's acceleration information monitored by the wearable device in real time, the embodiment of the present invention determines the first moment when the amplitude of the user's acceleration is greater than the preset amplitude and the peak value of the acceleration corresponding to the first moment, and according to the acceleration after the first moment The difference in the magnitude of the user's acceleration corresponding to adjacent moments within the preset time period, the change of the user's azimuth angle between the historical moment and the second moment, and the peak value of the acceleration corresponding to the first moment and after the first moment The time interval between the peak values of the acceleration is used to determine the user's behavior information, which further improves the accuracy of monitoring the user's behavior information.

Fig. 7 is a structural diagram of a behavior monitoring device based on a wearable device provided by an embodiment of the present invention. The behavior monitoring device based on the wearable device provided in the embodiment of the present invention can execute the processing flow provided in the embodiment of the behavior monitoring method based on the wearable device. As shown in FIG. 7 , the behavior monitoring device 70 based on the wearable device includes: an acquisition module 71. Determination module 72, calculation module 73; wherein, the acquisition module 71 is used to obtain the user's acceleration information monitored by the wearable device in real time; the determination module 72 is used to obtain the user's acceleration information monitored by the wearable device in real time, It is determined that the magnitude of the user's acceleration is greater than the first moment of the preset magnitude and the peak value of the acceleration corresponding to the first moment; the calculation module 73 is used to calculate the adjacent acceleration within the preset time period after the first moment The difference of the magnitude of the acceleration of the user corresponding to the moment; the determination module 72 is also used to: according to the acceleration vector of the user corresponding to the historical moment before the first moment, and the first moment after the first moment According to the acceleration vector of the user corresponding to the second moment, the change of the azimuth angle of the user between the historical moment and the second moment is determined; The difference between the magnitude of the acceleration of the user and the change of the azimuth angle of the user between the historical moment and the second moment determine the behavior information of the user.

The wearable device-based behavior monitoring device provided in the embodiment of the present invention can be specifically used to execute the method embodiment provided in FIG. 3 above, and the specific functions will not be repeated here.

According to the user's acceleration information monitored by the wearable device in real time, the embodiment of the present invention determines the first moment when the amplitude of the user's acceleration is greater than the preset amplitude and the peak value of the acceleration corresponding to the first moment, and calculates the acceleration after the first moment. The difference in magnitude of the user's acceleration corresponding to adjacent moments within the preset time period is based on the user's acceleration vector corresponding to the historical moment before the first moment, and the user's acceleration vector corresponding to the second moment after the first moment , to determine the change of the user's azimuth angle between the historical moment and the second moment, according to the difference in the amplitude of the user's acceleration corresponding to the adjacent moment in the preset time period after the first moment, and the historical moment and the second moment Changes in the azimuth angles of the users between them determine the behavior information of the users and improve the accuracy of monitoring the behavior information of the users.

Fig. 8 is a structural diagram of a behavior monitoring device based on a wearable device according to another embodiment of the present invention. On the basis of the above-mentioned embodiments, the determining module 72 is based on the difference between the acceleration magnitudes of the user corresponding to adjacent moments in the preset time period after the first moment, and the historical moment and the first moment. The change of the azimuth angle of the user between two moments, when determining the behavior information of the user, is specifically used for: if the acceleration of the user corresponding to the adjacent moment in the preset time period after the first moment If the amplitude difference is smaller than a preset difference, and the change of the azimuth angle of the user between the historical moment and the second moment is greater than a preset angle, then it is determined that the user has fallen.

Optionally, the wearable device-based behavior monitoring device 70 also includes: a statistical module 74, which is used to count the difference between the peak value of the acceleration corresponding to the first moment and the peak value of the acceleration after the first moment. time interval; correspondingly, the determining module 72 is based on the difference between the magnitude of the acceleration of the user corresponding to adjacent moments in the preset time period after the first moment, and the historical moment and the second moment When determining the behavior information of the user, it is specifically used for: according to the magnitude of the acceleration of the user corresponding to the adjacent moment in the preset time period after the first moment , the change of the azimuth angle of the user between the historical moment and the second moment, and the peak value of the acceleration corresponding to the first moment and the peak value of the acceleration after the first moment The time interval is used to determine the behavior information of the user.

Optionally, the determining module 72 is based on the difference between the magnitude of the user's acceleration corresponding to adjacent moments within a preset time period after the first moment, and the time difference between the historical moment and the second moment. The change of the azimuth angle of the user, and the time interval between the peak value of the acceleration corresponding to the first moment and the peak value of the acceleration after the first moment, when determining the behavior information of the user, is specifically used for: if The difference between the acceleration magnitudes of the user corresponding to adjacent moments within the preset time period after the first moment is smaller than the preset difference, the user's acceleration between the historical moment and the second moment If the change of the azimuth angle is smaller than the preset angle, and the time interval between the peak value of the acceleration corresponding to the first moment and the peak value of the acceleration after the first moment is greater than the preset time interval, then it is determined that the user jumps.

Optionally, the wearable device includes at least one of the following: an acceleration sensor, a heart rate sensor, a body temperature sensor, a communication module, and a power supply module.

The wearable device-based behavior monitoring device provided in the embodiment of the present invention can be specifically used to execute the method embodiment provided in FIG. 5 above, and the specific functions will not be repeated here.

According to the user's acceleration information monitored by the wearable device in real time, the embodiment of the present invention determines the first moment when the amplitude of the user's acceleration is greater than the preset amplitude and the peak value of the acceleration corresponding to the first moment, and according to the acceleration after the first moment The difference in the magnitude of the user's acceleration corresponding to adjacent moments within the preset time period, the change of the user's azimuth angle between the historical moment and the second moment, and the peak value of the acceleration corresponding to the first moment and after the first moment The time interval between the peak values of the acceleration is used to determine the user's behavior information, which further improves the accuracy of monitoring the user's behavior information.

To sum up, the embodiment of the present invention determines the first moment when the magnitude of the user's acceleration is greater than the preset magnitude and the peak value of the acceleration corresponding to the first moment according to the user's acceleration information monitored by the wearable device in real time, and calculates The difference in magnitude of the user's acceleration corresponding to adjacent moments in the preset time period after the first moment is based on the user's acceleration vector corresponding to the historical moment before the first moment, and the second moment after the first moment. The user's acceleration vector, determine the change of the user's azimuth angle between the historical moment and the second moment, according to the difference in the magnitude of the user's acceleration corresponding to the adjacent moment in the preset time period after the first moment, and the history The change of the user's azimuth angle between the second moment and the second moment determines the user's behavior information, which improves the accuracy of monitoring the user's behavior information; through the real-time monitoring of the user's acceleration information by the wearable device, the user's acceleration is determined The amplitude is greater than the first moment of the preset amplitude and the peak value of the acceleration corresponding to the first moment, and according to the difference and historical The change of the user's azimuth angle between the moment and the second moment, and the time interval between the peak value of the acceleration corresponding to the first moment and the peak value of the acceleration after the first moment, determine the user's behavior information, and further improve the user behavior The accuracy with which the information is monitored.

In the several embodiments provided by the present 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 only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described 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 may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

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

The above-mentioned integrated units implemented in the form of software functional units may be stored in a computer-readable storage medium. The above-mentioned software functional units are stored in a storage medium, and include several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) or a processor (processor) execute the methods described in various embodiments of the present invention. partial steps. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other various media that can store program codes. .

Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional modules is used as an example for illustration. The internal structure of the system is divided into different functional modules to complete all or part of the functions described above. For the specific working process of the device described above, reference may be made to the corresponding process in the foregoing method embodiments, and details are not repeated here.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the various embodiments of the present invention. scope.

Claims (10)

1. A kind of 1. behavior monitoring method based on wearable device, which is characterized in that including：

   Obtain the acceleration information of user that wearable device real-time monitors；

   According to the acceleration information for the user that the wearable device real-time monitors, the amplitude of the acceleration of the user is determined More than the first moment of default amplitude and the peak value of first moment corresponding acceleration；

   Calculate the amplitude of the acceleration of the corresponding user of adjacent moment in the preset time period after first moment Difference；

   According to the acceleration of the historical juncture corresponding user before first moment and first moment The acceleration of the second moment corresponding user later, determines institute between the historical juncture and second moment State azimuthal variation of user；

   According to the amplitude of the acceleration of the corresponding user of adjacent moment in the preset time period after first moment Azimuthal variation of the user, determines the user's between difference and the historical juncture and second moment Behavioural information.
2. 2. the according to the method described in claim 1, it is characterized in that, preset time period according to after first moment The difference of the amplitude of the acceleration of the corresponding user of interior adjacent moment and the historical juncture and second moment it Between the user azimuthal variation, determine the behavioural information of the user, including：

   If the amplitude of the acceleration of the corresponding user of adjacent moment in the preset time period after first moment Difference is less than preset difference value, and azimuthal variation of the user is more than in advance between the historical juncture and second moment If angle, it is determined that the user falls.
3. 3. it according to the method described in claim 1, it is characterized in that, further includes：

   It counts between the peak value of first moment corresponding acceleration and the peak value of the acceleration after first moment Time interval；

   Correspondingly, in the preset time period according to after first moment corresponding user of adjacent moment acceleration Azimuthal variation of the user between the difference of the amplitude of degree and the historical juncture and second moment determines The behavioural information of the user, including：

   According to the amplitude of the acceleration of the corresponding user of adjacent moment in the preset time period after first moment Azimuthal variation of the user and first moment pair between difference, the historical juncture and second moment Time interval between the peak value of the peak value for the acceleration answered and the acceleration after first moment, determines the user's Behavioural information.
4. 4. the according to the method described in claim 3, it is characterized in that, preset time period according to after first moment Institute between the difference of the amplitude of the acceleration of the corresponding user of interior adjacent moment, the historical juncture and second moment State azimuthal variation of user and the peak value of first moment corresponding acceleration and adding after first moment Time interval between the peak value of speed determines the behavioural information of the user, including：

   If the amplitude of the acceleration of the corresponding user of adjacent moment in the preset time period after first moment Azimuthal variation of the difference less than the user between preset difference value, the historical juncture and second moment is less than default Between the peak value of the peak value and the acceleration after first moment of angle and first moment corresponding acceleration when Between interval be more than prefixed time interval, it is determined that the user takeoffs.
5. 5. according to claim 1-4 any one of them methods, which is characterized in that the wearable device includes following at least one Kind：

   Acceleration transducer, heart rate sensor, body temperature transducer, communication module, power supply module.
6. 6. a kind of behavior monitoring device based on wearable device, which is characterized in that including：

   Acquisition module, for obtaining the acceleration information for the user that wearable device real-time monitors；

   Determining module for the acceleration information of the user real-time monitored according to the wearable device, determines the user The amplitude of acceleration be more than the first moment of default amplitude and the peak value of first moment corresponding acceleration；

   Computing module, for calculate in the preset time period after first moment corresponding user's of adjacent moment plus The difference of the amplitude of speed；

   The determining module is additionally operable to：It is sweared according to the acceleration of the historical juncture corresponding user before first moment The acceleration of the second moment corresponding user after amount and first moment, determines the historical juncture Azimuthal variation of the user between second moment；According to phase in the preset time period after first moment The difference of the amplitude of the acceleration of adjacent moment corresponding user and institute between the historical juncture and second moment Azimuthal variation of user is stated, determines the behavioural information of the user.
7. 7. the behavior monitoring device according to claim 6 based on wearable device, which is characterized in that the determining module According to the difference of the amplitude of the acceleration of the corresponding user of adjacent moment in the preset time period after first moment, And between the historical juncture and second moment user azimuthal variation, determine the user behavior letter During breath, it is specifically used for：

   If the amplitude of the acceleration of the corresponding user of adjacent moment in the preset time period after first moment Difference is less than preset difference value, and azimuthal variation of the user is more than in advance between the historical juncture and second moment If angle, it is determined that the user falls.
8. 8. the behavior monitoring device according to claim 7 based on wearable device, which is characterized in that further include：

   Statistical module, for counting the peak value of first moment corresponding acceleration and the acceleration after first moment Peak value between time interval；

   Correspondingly, the determining module is according to the corresponding use of adjacent moment in the preset time period after first moment Azimuthal change of the user between the difference of the amplitude of the acceleration at family and the historical juncture and second moment Change, when determining the behavioural information of the user, be specifically used for：

   According to the amplitude of the acceleration of the corresponding user of adjacent moment in the preset time period after first moment Azimuthal variation of the user and first moment pair between difference, the historical juncture and second moment Time interval between the peak value of the peak value for the acceleration answered and the acceleration after first moment, determines the user's Behavioural information.
9. 9. the behavior monitoring device according to claim 8 based on wearable device, which is characterized in that the determining module According to the difference of the amplitude of the acceleration of the corresponding user of adjacent moment in the preset time period after first moment, Between the historical juncture and second moment azimuthal variation of the user and first moment it is corresponding plus Time interval between the peak value of the peak value of speed and the acceleration after first moment determines the behavior letter of the user During breath, it is specifically used for：

   If the amplitude of the acceleration of the corresponding user of adjacent moment in the preset time period after first moment Azimuthal variation of the difference less than the user between preset difference value, the historical juncture and second moment is less than default Between the peak value of the peak value and the acceleration after first moment of angle and first moment corresponding acceleration when Between interval be more than prefixed time interval, it is determined that the user takeoffs.
10. 10. according to behavior monitoring device of the claim 6-9 any one of them based on wearable device, which is characterized in that institute It states wearable device and includes following at least one：

    Acceleration transducer, heart rate sensor, body temperature transducer, communication module, power supply module.