Intelligent fall prevention system based on biological characteristics of old people

Abstract

The invention discloses an intelligent fall prevention system based on the biological characteristics of the elderly, the system comprises a wearable photoplethysmography sensor, a human body induction sensor, a gait sensor and an evaluation module, the waking state of a user can be judged after the user prepares to get up, when the user is judged to be in the waking state, the user is allowed to walk, and the user is prevented from falling down. When it is judged that the user is in a non-waking state, the user is prompted to postpone getting up, if the user does not take care of the prompt and starts walking, early warning is further given out in an acousto-optic mode to wake up the user, and the situation that the user falls down is avoided.

Description

Technical Field

[0001] The present invention relates to an anti-fall warning technology for the elderly, and in particular to an intelligent fall prevention system based on biological characteristics of the elderly. Background Art

[0002] Fall prevention for the elderly is an important health issue. Medical practice shows that falls in the elderly can cause soft tissue injuries, fractures, internal bleeding, and in severe cases, death. At the same time, falls often cause the elderly to suffer tremendous mental stress, such as fear of falling again, anxiety, and depression. The restricted movement after the injury often leads to social isolation, which greatly affects the quality of life of the elderly.

[0003] At present, fall prevention achieved with the help of technical means often includes: environmental adaptation for the elderly, such as adding handrails, increasing floor friction, and personal wearing of protective equipment such as fall airbags, etc. Although these technical means can reduce the risk of falls to a certain extent, they cannot accurately provide real-time behavioral guidance, danger warnings, and automatic help requests based on individual conditions.

[0004] In addition, studies have found that getting up at night is a high-risk scenario for accidental falls in the elderly. The main reason is that they have just woken up, are not fully alert, and lack control over their bodies. Therefore, it is necessary to provide a reliable fall prevention program for this special scenario.

[0005] Based on the above problems, the inventors simultaneously utilized wearable sensors and intelligent environmental transformation to coordinate human biological indicators with external anti-fall facilities through the Internet of Things, thereby realizing human-machine integrated fall risk warning and fall assistance services. Summary of the invention

[0006] In order to overcome the above problems, the inventors have conducted intensive research and designed an intelligent fall prevention system based on the biological characteristics of the elderly, which includes a wearable photoplethysmography sensor, a human body sensing sensor, a gait sensor and an evaluation module. The system can judge the user's awake state after the user is about to get up. When the user is judged to be in an awake state, the user is allowed to walk. When the user is judged to be in an unconscious state, the user is prompted to postpone getting up. If the user ignores the reminder and starts walking, an early warning is further issued in the form of sound and light to wake up the user and prevent the user from falling, thereby completing the present invention.

[0007] Specifically, the purpose of the present invention is to provide an intelligent fall prevention system based on the biological characteristics of the elderly, the system comprising:

[0008] A wearable photoplethysmography sensor 1, which is mounted on a wearable device that the user wears for a long time, and is used to obtain the user's pulse interval sequence in real time;

[0009] A human body sensing sensor 2 is installed at the foot of the user's bed to monitor whether the user is ready to get up and send an evaluation instruction when the user is ready to get up;

[0010] The evaluation module 3 is used to retrieve the pulse interval sequence of the most recent time unit after receiving the evaluation instruction, and judge the user's autonomic nervous arousal level based on it. When the autonomic nervous arousal level is lower than the set walking-suitable value, it enters the alarm state.

[0011] The most recent 5 time units are counted from the time when the user is found to be ready to get up, and go back 5 time units;

[0012] The time unit is preferably 1 minute.

[0013] Among them, based on the pulse interval sequence data of each time unit, the corresponding autonomic nervous system arousal level of a user is obtained by the following formula (1):

[0014]

[0015] Among them, AL represents the level of autonomic arousal;

[0016] represents the average value of the sai sequence,

[0017] represents the average value of the pai sequence,

[0018] A represents a constant.

[0019] Among them, in the evaluation module 3, after obtaining 5 autonomic nervous arousal levels, they are compared with the walking suitability value one by one. When 3 or more autonomic nervous arousal levels are greater than the walking suitability value, it is considered that the user is in a wakeful state at this time and no additional operation is required. When 3 or more autonomic nervous arousal levels are lower than the set walking suitability value, an alarm state is entered.

[0020] The walkability value is pre-stored in the evaluation module 3.

[0021] Preferably, the walkability value is variable, and an average value of a group of users of the same type is collected as an initial value.

[0022] The updating method of the walkability value is as follows:

[0023] The wearable photoplethysmography sensor 1 collects the pulse interval sequence of the user in the daily awake state in real time.

[0024] The data is divided into multiple groups according to the time unit, and the corresponding autonomic nervous system arousal level is obtained based on each group of data.

[0025] The obtained autonomic arousal levels were sorted from high to low, and the value ranked at the 95th percentile was selected as the walking suitability value.

[0026] When the evaluation module 3 determines that the autonomic nervous system arousal level is greater than or equal to the set walking-suitable value, the indicator presents a "can get up" signal;

[0027] The "you can get up" signal includes a green light, a sound effect or voice indicating that you can walk.

[0028] Wherein, in the alarm state, a "postpone getting up" signal is presented by an indicator.

[0029] In the alarm state, when it is detected that the user starts walking, the indicator presents a "stop walking" signal;

[0030] The "stop walking" signal includes vibration, red light, sound effect or voice expressing stop walking.

[0031] The system further comprises a gait sensor 4, which is mounted on two shoes of the user;

[0032] The gait sensor 4 is used to detect and record the user's foot movement information, including the foot space movement trajectory and the foot rotation angle.

[0033] The beneficial effects of the present invention include:

[0034] (1) According to the intelligent fall prevention system based on the biological characteristics of the elderly provided by the present invention, the system can evaluate whether the user's mental state meets the safe walking standards when getting up, and has a fall warning function, and ultimately provides key prevention for high-risk fall scenarios such as getting up at night and getting up;

[0035] (2) According to the intelligent fall prevention system based on the biometrics of the elderly provided by the present invention, the system detects the user's standing up, real-time detection of the user's sobriety level, and provides guidance before standing and walking. The system allows the user to complete the mental state preparation before walking through a set of guidance processes, thereby basically eliminating the risk of falls in high-risk scenarios such as getting up at night or getting out of bed. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The overall logic diagram of the intelligent fall prevention system based on the biometrics of the elderly of the present application is shown.

[0037] Description of Reference Numerals

[0038] 1- Wearable Photoplethysmography Sensor

[0039] 2-Human body induction sensor

[0040] 3-Evaluation Module

[0041] 4-Gait sensor DETAILED DESCRIPTION

[0042] The present invention will be further described in detail below through the accompanying drawings and embodiments. Through these descriptions, the characteristics and advantages of the present invention will become more clear and distinct.

[0043] The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise noted.

[0044] The present invention provides an intelligent fall prevention system based on biological characteristics of the elderly, which comprises a wearable photoplethysmography sensor 1, a human body induction sensor 2, an evaluation module 3 and a gait sensor 4.

[0045] The wearable photoplethysmography sensor 1 is mounted on a wearable device that is worn by a user for a long time, and is used to obtain the user's pulse interval sequence in real time; the wearable device is a smart bracelet or a watch; the signal generated by the wearable photoplethysmography sensor is filtered and peak-extracted by the bracelet or the watch to obtain the pulse interval sequence.

[0046] The human body sensing sensor 2 is installed at the foot of the user's bed to monitor whether the user is ready to get up, and sends an evaluation instruction when the user is ready to get up; the human body sensing sensor 2 can be a gravity sensor, which determines whether the user's feet are on the ground by sensing the weight change at the foot of the bed. When the user's feet are on the ground, it can be considered that the user is ready to get up. The human body sensing sensor 2 can also be a laser radar sensor or an infrared sensor, etc., which can sense and detect in real time whether the user's legs / feet fall into the detection height area. The detection height area can be set according to actual conditions, such as an area below 30 cm from the ground. When the user's legs / feet fall into the detection height area, it can be considered that the user is ready to get up. In this application, due to the different working principles of the human body sensing sensor 2, the recognition standards for the user's preparation to get up are not completely consistent, but it can be determined that the user is ready to switch from the sleep state to the walking activity state at this time, and targeted analysis and early warning are required.

[0047] The evaluation module 3 is used to retrieve the pulse interval sequence of the latest 5 time units after receiving the evaluation instruction, and judge the user's autonomic nervous awakening level based on it. When the autonomic nervous awakening level is lower than the set walking-suitable value, it enters the alarm state.

[0048] Preferably, the most recent 5 time units are counted from when the user is found to be ready to get up, and go back 5 time units;

[0049] The time unit is preferably 1 minute, and based on the pulse interval sequence data of each time unit, the autonomic nervous system arousal level of a user is correspondingly obtained.

[0050] Preferably, the user's autonomic arousal level is obtained by the following formula (1):

[0051]

[0052] Wherein, AL represents the autonomic arousal level; in the present application, the autonomic arousal level may also be referred to as the degree of wakefulness;

[0053] Said sai sequence represents the average value, said pulse interval sequence includes said sai sequence, that is, said sai sequence is part of the data in the pulse interval sequence, and said sai sequence specifically means the sympathetic nerve index sequence obtained by inputting the heartbeat cycle sequence in the time window into the Laguerre regression model, which is used to characterize the strength of sympathetic nerve activity;

[0054] represents the average value of the pai sequence, the pulse interval sequence includes the pai sequence, that is, the pai sequence is part of the data in the pulse interval sequence, and the specific meaning of the pai sequence is the parasympathetic nerve index sequence obtained by inputting the heartbeat cycle sequence in the time window into the Laguerre regression model, which is used to characterize the strength of the parasympathetic nerve activity; the Laguerre regression model uses the model in Gaetano V, Luca C, Philip SJ, et al. Measures of Sympathetic and Parasympathetic Autonomic Outflow from Heartbeat Dynamics. [J]. Journal of Applied Physiology, 2018, 125 (1): 19-39.

[0055] A represents a constant, and its preferred value is 10000.

[0056] In the evaluation module 3, after obtaining 5 autonomic arousal levels, they are compared with the walking suitability value one by one. When 3 or more autonomic arousal levels are greater than the walking suitability value, it is considered that the user is in a wakeful state and no additional operation is required. When 3 or more autonomic arousal levels are lower than the set walking suitability value, an alarm state is entered.

[0057] Preferably, the walkability value is pre-stored in the evaluation module 3.

[0058] Preferably, the walkability value is variable, and the average value of the user's peer group is collected as the initial value. The user's peer group refers to people of the same age and gender as the user and whose weight level differs by less than 2 kg.

[0059] Preferably, the updating method of the walkability value is:

[0060] The wearable photoplethysmography sensor 1 is used to collect the pulse interval sequence of the user in the daily awake state in real time, and the awake state is comprehensively judged by the gait sensor and the current time;

[0061] The data is divided into multiple groups according to the time unit, and the corresponding autonomic nervous system arousal level is obtained based on each group of data, that is, one group of data corresponds to each minute. After the user wears the intelligent fall prevention system, a large amount of data can be generated within a period of time, and the walking suitability value can be updated once an hour;

[0062] Collect at least 1000 sets of data from individuals and sort them from small to large (daytime activity data, non-sleep data), sort the obtained autonomic nervous arousal levels from high to low, and perform normalization, that is, standardize the maximum and minimum values, select the 20% percentile value for the maximum value, and select the 80% percentile value for the minimum value. Select the 75% value as the suitable walking value. The suitable walking value selected by this method is basically at the bottom line for the user to stay awake, which can ensure that the user is awake and not prone to falling, and can also minimize the user's waiting time. In most cases, when the user is ready to get out of bed, he can reach this awake state and can perform subsequent operations such as getting out of bed and walking.

[0063] Preferably, when the evaluation module 3 determines that the autonomic nervous system arousal level is greater than or equal to the set walking-suitable value, the indicator presents a "can get up" signal;

[0064] The "you can get up" signal includes a green light, a sound effect or voice indicating that you can walk.

[0065] Preferably, in the alarm state, a "hold off getting up" signal is presented by an indicator.

[0066] In the alarm state, when it is detected that the user starts walking, the indicator presents a "stop walking" signal;

[0067] The "stop walking" signal includes vibration, red light, sound effect or voice expressing stop walking.

[0068] The gait sensor 4 is installed on the two shoes of the user; the gait sensor 4 is used to detect and record the user's foot movement information, including the foot space movement trajectory and the foot rotation angle. The detected data can be converted into a series of indicators in real time, such as step frequency, stride, landing posture, ground contact time, foot eversion angle, swing angle, impact load, vertical stride ratio, etc. It can be judged whether the user is walking based on the detected data, so as to be used in conjunction with the evaluation module to provide an alarm prompt to the user who is walking in an unconscious state. It can also judge the user's fall risk based on the detected data.

[0069] Furthermore, a service node can also be set up in the system, which is used to receive and store the data information detected by the gait sensor 4 in real time. The service node accumulates the index data of the user's walking. When the amount of data exceeds a certain amount, such as indoor walking data for 2 natural days, the service node establishes distribution information for each index of personal walking. The service node can use the distribution information of personal indicators to establish a fall risk alarm standard. Specifically, in the subsequent monitoring process, a moderate risk alarm is triggered when a certain indicator of the user exceeds a certain limit of his or her own data distribution. The certain limit can be 1.5 standard deviations centered on the mean; the user's own indicators can also be used to compare with the pre-stored population standardized prone to fall mode status data. When the data matches, the service node will trigger a high fall risk alarm.

[0070] Furthermore, the system can also be provided with an information repeater, which is used to assume the communication function between each sensor, indicator and service node, so as to replace the direct communication between each sensor, indicator and service node, thereby improving the networking flexibility, reducing costs and improving the environmental adaptability of the system. The repeater obtains sensor data by wireless protocol and obtains data through wired connection. For example, the information repeater is connected to the sensor and indicator by a short-range wireless information transmission protocol, such as via the intranet of wifi, Bluetooth connection, star flash connection, etc., and the repeater communicates with the service node through a wide area network. In the case of wireless connection, due to the spatial limitations of wireless transmission such as distance and signal blocking by walls, when the transmission range needs to exceed the effective range of a single repeater signal, multiple repeaters can be used to bridge to achieve transmission space expansion. For example, when there are multiple rooms, repeaters can be deployed in each room and corridor and bridged.

[0071] Example

[0072] 68 elderly residents with normal cognition and able to get out of bed and walk on their own were selected from a nursing home. Among the 68 elderly residents, 32 were males and 36 were females, all of whom were over 65 years old.

[0073] Each elderly person is provided with a set of the intelligent fall prevention system based on the biometric characteristics of the elderly in this application. After being taught the specific usage methods, each elderly person wears the intelligent fall prevention system based on the biometric characteristics of the elderly for a long time.

[0074] The intelligent fall prevention system Figure 1 As shown in , it includes a wearable photoplethysmography sensor 1, a human body sensing sensor 2, an evaluation module 3 and a gait sensor 4;

[0075] The wearable photoplethysmography sensor is used to obtain the user's pulse interval sequence in real time;

[0076] Monitor whether the user is ready to get up through a human body sensing sensor, and send an evaluation instruction when the user is ready to get up;

[0077] After receiving the evaluation instruction, the evaluation module retrieves the pulse interval sequence of the last five time units, and judges the user's autonomic nerve arousal level based on the sequence. When the autonomic nerve arousal level is lower than the set walking-suitable value, the user enters the alarm state.

[0078] In the alarm state, a "hold off" signal is presented by the indicator.

[0079] In the alarm state, when the gait sensor 4 detects that the user starts walking, the indicator presents a "stop walking" signal; the "stop walking" signal includes vibration, red light, sound effect or voice expressing stop walking.

[0080] The most recent five time units are counted from when the user is found to be ready to get up, and go back five time units; the time unit is 1 minute, and based on the pulse interval sequence data of each time unit, the corresponding autonomic nervous arousal level of a user is obtained.

[0081] The user's autonomic arousal level is obtained by the following formula (1):

[0082]

[0083] Among them, AL represents the level of autonomic arousal;

[0084] Represents the average value of the sai sequence;

[0085] represents the average value of the pai sequence;

[0086] A represents a constant, and its value is 10000.

[0087] After obtaining 5 autonomic arousal levels, they are compared with the walking suitability value one by one. When 3 or more autonomic arousal levels are greater than the walking suitability value, it is considered that the user is in a wakeful state and no additional operation is required. When 3 or more autonomic arousal levels are lower than the set walking suitability value, an alarm state is entered.

[0088] The updating method of the walkability value is:

[0089] The wearable photoplethysmography sensor 1 is used to collect the pulse interval sequence of the user in the daily awake state in real time, and the awake state is comprehensively judged by the gait sensor and the current time;

[0090] The data is divided into multiple groups according to the time unit, and the corresponding autonomic nervous arousal level is obtained based on each group of data, that is, one group of data corresponds to each minute;

[0091] The obtained autonomic arousal levels were sorted from high to low, and the value ranked at 75% was selected as the walking suitability value.

[0092] The intelligent fall prevention system and the living conditions of the elderly were continuously monitored within 3 months.

[0093] During the test period, a total of 122 people entered the alarm state, and a total of 18 people issued a stop walking signal. After the stop walking signal was issued, the elderly stopped walking and sat back on the bed. During the entire test period, no elderly people wearing the intelligent fall prevention system based on the elderly's biometrics fell at night.

[0094] According to the records of the nursing home, before the introduction of the intelligent fall prevention system based on the biometrics of the elderly of the present application, there were at least two accidents of elderly people falling at night every month on average.

[0095] Based on this, it can be seen that the intelligent fall prevention system based on the biological characteristics of the elderly provided in this application can effectively prevent the occurrence of fall accidents among the elderly at night and has extremely high practical value.

[0096] The present invention has been described above in conjunction with preferred embodiments, but these embodiments are only exemplary and serve only as an illustration. On this basis, the present invention may be subjected to a variety of substitutions and improvements, all of which fall within the scope of protection of the present invention.

Claims

1. An intelligent fall prevention system based on the biological characteristics of the elderly, characterized in that: The system includes: A wearable photoplethysmography sensor (1) is mounted on a wearable device that is worn by a user for a long time and is used to obtain the user's pulse interval sequence in real time; A human body sensing sensor (2) is installed at the foot of the user's bed and is used to monitor whether the user is ready to get up and send an evaluation instruction when the user is ready to get up; The evaluation module (3) is used to retrieve the pulse interval sequence of the latest five time units after receiving the evaluation instruction, and judge the user's autonomic nervous system arousal level based on the sequence, and enter an alarm state when the autonomic nervous system arousal level is lower than a set walking-suitable value.

2. The intelligent fall prevention system based on biometrics of the elderly according to claim 1 is characterized in that: The most recent 5 time units are counted from the time when the user is found to be ready to get up, and go back 5 time units; The time unit is preferably 1 minute.

3. The intelligent fall prevention system based on biometrics of the elderly according to claim 1 is characterized in that: Based on the pulse interval sequence data of each time unit, the corresponding autonomic nervous system arousal level of a user is obtained by the following formula (1): Among them, AL represents the level of autonomic arousal; represents the average value of the sai sequence, represents the average value of the pai sequence, A represents a constant.

4. The intelligent fall prevention system based on biometrics of the elderly according to claim 3 is characterized in that: In the evaluation module (3), after obtaining 5 autonomic arousal levels, they are compared with the walking suitability value one by one. When 3 or more autonomic arousal levels are greater than the walking suitability value, it is considered that the user is in a wakeful state and no additional operation is required. When 3 or more autonomic arousal levels are lower than the set walking suitability value, an alarm state is entered.

5. The intelligent fall prevention system based on biometrics of the elderly according to claim 1 is characterized in that: The walkability value is pre-stored in the evaluation module (3), The walkability value is variable, and is obtained by collecting an average value of a group of users of the same type as the initial value.

6. The intelligent fall prevention system based on biometrics of the elderly according to claim 5 is characterized in that: The updating method of the walkability value is: The wearable photoplethysmography sensor (1) collects the pulse interval sequence of the user in the daily awake state in real time. The data is divided into multiple groups according to the time unit, and the corresponding autonomic nervous system arousal level is obtained based on each group of data. The obtained autonomic arousal levels were sorted from high to low, and the value ranked at the 95th percentile was selected as the walking suitability value.

7. The intelligent fall prevention system based on biometrics of the elderly according to claim 1 is characterized in that: When the evaluation module (3) determines that the autonomic nervous system arousal level is greater than or equal to the set walking-suitable value, the indicator presents a "can get up" signal; The "you can get up" signal includes a green light, a sound effect or voice indicating that you can walk.

8. The intelligent fall prevention system based on biometrics of the elderly according to claim 1 is characterized in that: In the alarm state, a "hold off on getting up" signal is presented by the indicator. In the alarm state, when it is detected that the user starts walking, the indicator presents a "stop walking" signal; The "stop walking" signal includes vibration, red light, sound effect or voice expressing stop walking.

9. The intelligent fall prevention system based on biometrics of the elderly according to claim 8, characterized in that: The system also includes gait sensors (4) mounted on two shoes of the user; The gait sensor (4) is used to detect and record the user's foot movement information, including the foot space movement trajectory and the foot rotation angle.

Images