CN116229676A - Fall detection method and device - Google Patents

Fall detection method and device Download PDF

Info

Publication number
CN116229676A
CN116229676A CN202310440017.8A CN202310440017A CN116229676A CN 116229676 A CN116229676 A CN 116229676A CN 202310440017 A CN202310440017 A CN 202310440017A CN 116229676 A CN116229676 A CN 116229676A
Authority
CN
China
Prior art keywords
heart rate
module
queue
user
term
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202310440017.8A
Other languages
Chinese (zh)
Other versions
CN116229676B (en
Inventor
陈达权
肖晓
付洪兵
吴应平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Fenda Intelligent Technology Co ltd
Original Assignee
Shenzhen Fenda Intelligent Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Fenda Intelligent Technology Co ltd filed Critical Shenzhen Fenda Intelligent Technology Co ltd
Priority to CN202310440017.8A priority Critical patent/CN116229676B/en
Publication of CN116229676A publication Critical patent/CN116229676A/en
Application granted granted Critical
Publication of CN116229676B publication Critical patent/CN116229676B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1116—Determining posture transitions
    • A61B5/1117—Fall detection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
    • G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
    • G08B21/043—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting an emergency event, e.g. a fall
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
    • G08B21/0438—Sensor means for detecting
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
    • G08B21/0438—Sensor means for detecting
    • G08B21/0446—Sensor means for detecting worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Emergency Management (AREA)
  • Business, Economics & Management (AREA)
  • Gerontology & Geriatric Medicine (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Engineering & Computer Science (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Cardiology (AREA)
  • Biophysics (AREA)
  • Physiology (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Psychiatry (AREA)
  • Psychology (AREA)
  • Social Psychology (AREA)
  • Alarm Systems (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

The invention belongs to the technical field of intelligent wearing, and provides a fall detection method which comprises a heart rate tracking step and a fall event detection step which are operated concurrently, wherein the heart rate tracking step activates a PPG heart rate monitoring module to monitor the heart rate when a first series of parameters meet a first formula, and the fall event detection step calculates a short-term heart rate queue through the fall event detection module
Figure ZY_1
Mean heart rate of all nodes in (1)
Figure ZY_2
And long term heart rate queue
Figure ZY_3
Mean heart rate of all nodes in (1)
Figure ZY_4
Thereby obtaining the falling event
Figure ZY_5
Transmitting to a main control center module, wherein the main control center module receives a falling event
Figure ZY_6
And then the user enters an emergency rescue program to provide rescue, so that falling detection and rescue are realized, the privacy of the user is ensured, the detection cost is reduced, the detection range is widened, and the detection accuracy is improved.

Description

Fall detection method and device
Technical Field
The invention relates to the technical field of intelligent wearing, in particular to a method and a device for detecting falling.
Background
Fall events are often not found in time, and are even life-threatening for the elderly to be at risk of fractures, hemiplegia, chronic complications, etc., so it is important to find and rescue the fall of the elderly in time. Currently, fall detection techniques are mainly implemented using fall detection algorithms, whereas existing fall detection algorithms detect fall events mainly by related algorithms based on video devices, audio devices, infrared/radar devices and wearable devices. The fall detection system based on the video equipment is high in recognition rate, but cannot effectively guarantee user privacy in the process of image data acquisition, is high in cost and small in detection range, and has certain limitation; the fall detection system based on the audio equipment is easy to be interfered by noise, and the identification accuracy is low; the fall detection system based on infrared rays/radar is high in cost and weak in anti-interference capability, and cannot meet the portable requirement; the fall detection system based on wearable equipment can meet the requirements of portability, user privacy protection and the like, has the advantages of low manufacturing cost, wide coverage range, strong expandability and the like, and still has the problems of low accuracy, poor wearing comfort of the equipment, more number of sensors required to be worn, node energy consumption and the like.
In summary, the existing fall detection technology has the technical problems of small detection range, low detection precision, high detection cost, unsatisfactory comfort level, and the like.
Disclosure of Invention
In order to solve the technical problems, the invention provides the following scheme.
In one aspect, the invention provides a fall detection method comprising a heart rate tracking step and a fall event detection step, which are operated concurrently, the heart rate tracking step comprising the steps of:
s1, judging whether a first series of parameters meet a first formula or not; the first series of parameters includes a heart rate long-term monitoring time interval
Figure SMS_1
Short-term heart rate monitoring time interval->
Figure SMS_2
Short term heart rate queue->
Figure SMS_3
The maximum queue length is +.>
Figure SMS_4
Long-term heart rate queue->
Figure SMS_5
The maximum queue length is +.>
Figure SMS_6
And the timestamp of the current moment of the system +.>
Figure SMS_7
The method comprises the steps of carrying out a first treatment on the surface of the The first formula is->
Figure SMS_8
Or->
Figure SMS_9
The method comprises the steps of carrying out a first treatment on the surface of the When the first series of parameters meet the first formula, jumping to a step S2;
s2, activating a PPG heart rate monitoring module to acquire a current heart rate value of a user
Figure SMS_11
If (if)
Figure SMS_13
The user's current heart rate value +.>
Figure SMS_18
Joining the short-term heart rate queue
Figure SMS_19
Is in the tail of the team; if->
Figure SMS_20
The user's current heart rate value +.>
Figure SMS_21
Joining the long term heart rate queue->
Figure SMS_22
Is in the tail of the team; if the short-term heart rate queue->
Figure SMS_10
The number of nodes reaches its maximum queue length
Figure SMS_12
Deleting the short-term heart rate queue +.>
Figure SMS_14
Is a team head node; if the long-term heart rate queue->
Figure SMS_15
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_16
Deleting the long-term heart rate queue +.>
Figure SMS_17
Is a team head node; jumping to the step S1;
the fall event detection step comprises the steps of:
s3, according to the triaxial acceleration signal
Figure SMS_24
、/>
Figure SMS_30
、/>
Figure SMS_31
And a triaxial angular velocity signal>
Figure SMS_32
、/>
Figure SMS_33
、/>
Figure SMS_34
Calculating a weighted Euler variation angle +.>
Figure SMS_35
Combined acceleration window variation->
Figure SMS_23
Angular velocity window change->
Figure SMS_25
To be in line with the window change threshold
Figure SMS_26
Comparing if->
Figure SMS_27
Or->
Figure SMS_28
Or->
Figure SMS_29
Step S4, jumping to the step;
s4, obtaining the current heart rate value of the user
Figure SMS_37
Calculating the short term heart rate queue +.>
Figure SMS_39
All of (3)Mean heart rate>
Figure SMS_40
And said long-term heart rate queue->
Figure SMS_41
Mean heart rate of all nodes in->
Figure SMS_42
And calculate
Figure SMS_43
，/>
Figure SMS_44
Setting a heart rate mutation threshold value
Figure SMS_36
In->
Figure SMS_38
If yes, jumping to step S5;
s5, sending a falling event to the master control center module through the falling event detection module
Figure SMS_45
The central control module receives the fall event +.>
Figure SMS_46
And then enter an emergency rescue program to provide assistance.
In one aspect, the invention provides a fall detection system comprising: a heart rate tracking module and a fall event detection module; the heart rate tracking module and the fall event detection module execute concurrently in the fall detection system such that the heart rate tracking module and the fall event detection module operate any of the methods described above.
In one aspect, the invention provides a fall detection apparatus comprising: the system comprises a triaxial accelerometer module, a triaxial gyroscope module, a PPG heart rate monitoring module, a sleep monitoring module, a calculation module, a data storage module, a power supply module and a control terminal module; the saidThe triaxial accelerometer module comprises a triaxial accelerometer; when the falling detection device is worn on the wrist of a user, the positive Z-axis direction of the triaxial accelerometer is the direction that the palm of the user points to the back of the hand; the tri-axis gyroscope module includes: a three-axis gyroscope; the positive X-axis direction of the three-axis gyroscope is the same as the positive X-axis direction of the three-axis accelerometer, the positive Y-axis direction of the three-axis gyroscope is the same as the positive Y-axis direction of the three-axis accelerometer, and the positive Z-axis direction of the three-axis gyroscope is the same as the positive Z-axis direction of the three-axis accelerometer; the control terminal module includes: the device comprises a communication module, an input module, a display module and a positioning module; the PPG heart rate monitoring module comprises: returning the current heart rate value of the user
Figure SMS_47
The method comprises the steps of carrying out a first treatment on the surface of the The sleep monitoring module comprises: returning to the user's current sleep state->
Figure SMS_48
If->
Figure SMS_49
0, indicating that the user is currently awake; if->
Figure SMS_50
1, indicating that the user is currently in a sleep state.
In one aspect, the invention provides a fall detection apparatus comprising:
a memory storing a computer program;
a processor running the computer program to implement any of the methods described above.
In one aspect, the invention provides a readable storage medium storing a computer program that is run on a processor to implement any one of the methods described above.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a fall detection method, which comprises a heart rate tracking step and a fall event detection step which are operated concurrently, wherein the heart rate tracking step judges whether a first series of parameters are full or notA first formula is given; the first series of parameters includes a heart rate long-term monitoring time interval
Figure SMS_62
Short-term heart rate monitoring time interval->
Figure SMS_63
Short term heart rate queue->
Figure SMS_64
The maximum queue length is +.>
Figure SMS_65
Long-term heart rate queue->
Figure SMS_66
The maximum queue length is +.>
Figure SMS_67
And the timestamp of the current moment of the system +.>
Figure SMS_68
The method comprises the steps of carrying out a first treatment on the surface of the The first formula is->
Figure SMS_69
Or->
Figure SMS_70
The method comprises the steps of carrying out a first treatment on the surface of the When the first series of parameters meet the first formula, activating a PPG heart rate monitoring module to acquire the current heart rate value of the user +.>
Figure SMS_71
If (if)
Figure SMS_73
The user's current heart rate value +.>
Figure SMS_74
Joining the short term heart rate queue->
Figure SMS_75
Is in the tail of the team; if->
Figure SMS_76
The user's current heart rate value +.>
Figure SMS_77
Joining the long term heart rate queue->
Figure SMS_79
Is in the tail of the team; if the short-term heart rate queue->
Figure SMS_83
The number of nodes reaches its maximum queue length
Figure SMS_85
Deleting the short-term heart rate queue +.>
Figure SMS_86
Is a team head node; if the long-term heart rate queue->
Figure SMS_87
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_88
Deleting the long-term heart rate queue +.>
Figure SMS_89
Is a team head node. The fall event detection step is performed by detecting +_based on the three-axis acceleration signal>
Figure SMS_90
、/>
Figure SMS_91
、/>
Figure SMS_92
And a triaxial angular velocity signal>
Figure SMS_93
、/>
Figure SMS_94
、/>
Figure SMS_95
Calculating a weighted Euler variation angle +.>
Figure SMS_96
Combined acceleration window variation->
Figure SMS_97
Angular velocity window change->
Figure SMS_98
To be equal to the window change threshold->
Figure SMS_51
、
Figure SMS_52
and />
Figure SMS_53
Comparing if->
Figure SMS_54
Or->
Figure SMS_55
Or->
Figure SMS_56
Acquiring the current heart rate value of the user>
Figure SMS_57
Calculating the short term heart rate queue +.>
Figure SMS_58
Mean heart rate of all nodes in->
Figure SMS_59
And said long-term heart rate queue->
Figure SMS_60
Mean heart rate of all nodes in->
Figure SMS_61
And calculate +.>
Figure SMS_72
，
Figure SMS_78
Setting a heart rate mutation threshold +.>
Figure SMS_80
In the following
Figure SMS_81
When in use, the falling event detection module sends a falling event to the master control center module>
Figure SMS_82
The central control module receives the fall event +.>
Figure SMS_84
And then the user enters an emergency rescue program to provide rescue, so that falling detection and rescue are realized, the privacy of the user is ensured, the detection cost is reduced, the detection range is widened, and the detection accuracy is improved.
Drawings
Fig. 1 is a schematic flow chart of a fall detection method according to an embodiment of the invention;
fig. 2 is a schematic diagram of an architecture of a fall detection device according to an embodiment of the invention;
fig. 3 is a schematic diagram of an architecture of a fall detection system according to an embodiment of the invention;
fig. 4 is a schematic diagram of an architecture of a fall detection device according to an embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. It should be understood that, in various embodiments of the present invention, the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention. It should be understood that in the present invention, "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus. It should be understood that in the present invention, "plurality" means two or more. "and/or" is merely an association relationship describing an association object, and means that three relationships may exist, for example, and/or B may mean: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. "comprising A, B and C", "comprising A, B, C" means that all three of A, B, C comprise, "comprising A, B or C" means that one of the three comprises A, B, C, and "comprising A, B and/or C" means that any 1 or any 2 or 3 of the three comprises A, B, C. It should be understood that in the present invention, "B corresponding to a", "a corresponding to B", or "B corresponding to a" means that B is associated with a, from which B can be determined. Determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information. The matching of A and B is that the similarity of A and B is larger than or equal to a preset threshold value. As used herein, "if" may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to detection" depending on the context. The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
Example 1
Referring to fig. 1, the embodiment provides a fall detection method, which includes a heart rate tracking step and a fall event detection step that operate concurrently, where the heart rate tracking step includes the following steps:
s1, judging whether a first series of parameters meet a first formula or not; the first series of parameters includes a heart rate long-term monitoring time interval
Figure SMS_100
Short-term heart rate monitoring time interval->
Figure SMS_101
Short term heart rate queue->
Figure SMS_102
The maximum queue length is +.>
Figure SMS_103
Long-term heart rate queue->
Figure SMS_105
The maximum queue length is +.>
Figure SMS_106
And the timestamp of the current moment of the system +.>
Figure SMS_107
The method comprises the steps of carrying out a first treatment on the surface of the The first formula is->
Figure SMS_99
Or->
Figure SMS_104
The method comprises the steps of carrying out a first treatment on the surface of the When the first series of parameters meet the first formula, jumping to a step S2;
s2, activating a PPG heart rate monitoring module to acquire a current heart rate value of a user
Figure SMS_109
If (if)
Figure SMS_111
The user's current heart rate value +.>
Figure SMS_113
Joining the short-term heart rate queue
Figure SMS_114
Is in the tail of the team; if->
Figure SMS_116
The user's current heart rate value +.>
Figure SMS_118
Joining the long term heart rate queue->
Figure SMS_119
Is in the tail of the team; if the short-term heart rate queue->
Figure SMS_108
The number of nodes reaches its maximum queue length
Figure SMS_110
Deleting the short-term heart rate queue +.>
Figure SMS_112
Is a team head node; if the long-term heart rate queue->
Figure SMS_115
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_117
Deleting the long-term heart rate queue +.>
Figure SMS_120
Is a team head node; jumping to the step S1;
the fall event detection step comprises the steps of:
s3, according to the triaxial acceleration signal
Figure SMS_122
、/>
Figure SMS_123
、/>
Figure SMS_126
And a triaxial angular velocity signal>
Figure SMS_128
、/>
Figure SMS_130
、/>
Figure SMS_132
Calculating a weighted Euler variation angle +.>
Figure SMS_133
Combined acceleration window variation->
Figure SMS_121
Angular velocity window change->
Figure SMS_124
To be in line with the window change threshold
Figure SMS_125
Comparing if->
Figure SMS_127
Or->
Figure SMS_129
Or->
Figure SMS_131
Step S4, jumping to the step;
s4, obtaining the current heart rate value of the user
Figure SMS_134
Calculating the short term heart rate queue +.>
Figure SMS_136
Mean heart rate of all nodes in->
Figure SMS_138
And said long-term heart rate queue->
Figure SMS_139
Mean heart rate of all nodes in->
Figure SMS_140
And calculate
Figure SMS_141
，/>
Figure SMS_142
Setting a heart rate mutation threshold value
Figure SMS_135
In->
Figure SMS_137
If yes, jumping to step S5; />
S5, sending a falling event to the master control center module through the falling event detection module
Figure SMS_143
The central control module receives the fall event +.>
Figure SMS_144
And then enter an emergency rescue program to provide assistance.
It should be noted that, the fall detection method provided in this embodiment may be executed by a fall detection device, where the fall detection device serves as an intelligent wearable device, and may be an execution subject of all or part of the steps in the fall detection method, and fall detection is performed by the fall detection deviceThe apparatus may perform some or all of the steps of the method referred to hereinafter, in addition to step S1, step S2, step S3, step S4, and step S5 in this embodiment. In this embodiment, the fall detection method includes a heart rate tracking step and a fall event detection step that are performed concurrently, where the heart rate tracking step determines whether a first series of parameters satisfy a first formula; the first series of parameters includes a heart rate long-term monitoring time interval
Figure SMS_171
Short-term heart rate monitoring time interval->
Figure SMS_173
Short term heart rate queue->
Figure SMS_174
The maximum queue length is +.>
Figure SMS_175
Long-term heart rate queue->
Figure SMS_176
The maximum queue length is +.>
Figure SMS_177
And the timestamp of the current moment of the system +.>
Figure SMS_178
The method comprises the steps of carrying out a first treatment on the surface of the The first formula is->
Figure SMS_181
Or (b)
Figure SMS_182
The method comprises the steps of carrying out a first treatment on the surface of the When the first series of parameters meet the first formula, activating a PPG heart rate monitoring module to acquire the current heart rate value of the user +.>
Figure SMS_185
If->
Figure SMS_186
The user's current heart rate value +.>
Figure SMS_187
Joining the short term heart rate queue->
Figure SMS_188
Is in the tail of the team; if->
Figure SMS_189
The user's current heart rate value +.>
Figure SMS_190
Joining the long term heart rate queue->
Figure SMS_146
Is in the tail of the team; if the short-term heart rate queue->
Figure SMS_148
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_150
Deleting the short-term heart rate queue +.>
Figure SMS_151
Is a team head node; if the long-term heart rate queue->
Figure SMS_153
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_155
Deleting the long-term heart rate queue
Figure SMS_159
Is a team head node. The fall event detection step is performed by detecting +_based on the three-axis acceleration signal>
Figure SMS_160
、/>
Figure SMS_162
、/>
Figure SMS_168
And a triaxial angular velocity signal>
Figure SMS_170
、/>
Figure SMS_172
、/>
Figure SMS_179
Calculating a weighted Euler variation angle +.>
Figure SMS_180
Combined acceleration window variation->
Figure SMS_183
Angular velocity window change
Figure SMS_184
To be equal to the window change threshold->
Figure SMS_145
Comparing if->
Figure SMS_147
Or (b)
Figure SMS_149
Or->
Figure SMS_152
Acquiring the current heart rate value of the user>
Figure SMS_154
Calculating the short-term heart rate queue
Figure SMS_156
Mean heart rate of all nodes in->
Figure SMS_157
And said long-term heart rate queue->
Figure SMS_158
Mean heart rate of all nodes in (1)
Figure SMS_161
And calculate +.>
Figure SMS_163
，/>
Figure SMS_164
Setting a heart rate mutation threshold +.>
Figure SMS_165
In->
Figure SMS_166
When in use, the falling event detection module sends a falling event to the master control center module>
Figure SMS_167
The central control module receives the fall event +.>
Figure SMS_169
And then the user enters an emergency rescue program to provide rescue, so that falling detection and rescue are realized, the privacy of the user is ensured, the detection cost is reduced, the detection range is widened, and the detection accuracy is improved.
In step S1, the fall detection device runs a heart rate tracking step comprising: judging whether the first series of parameters meet a first formula or not; the first series of parameters includes a heart rate long-term monitoring time interval
Figure SMS_199
Short-term heart rate monitoring time interval
Figure SMS_201
Short term heart rate queue->
Figure SMS_202
The maximum queue length is +.>
Figure SMS_203
Long-term heart rate teamColumn->
Figure SMS_204
Maximum queue length of (a) is
Figure SMS_206
And the timestamp of the current moment of the system +.>
Figure SMS_207
The method comprises the steps of carrying out a first treatment on the surface of the The first formula is->
Figure SMS_191
Or (b)
Figure SMS_194
The method comprises the steps of carrying out a first treatment on the surface of the And when the first series of parameters meet the first formula, jumping to the step S2. In some embodiments, step S1 comprises: step one, setting a heart rate long-term monitoring time interval +.>
Figure SMS_195
Short heart rate monitoring time interval->
Figure SMS_196
Create and initialize a short term heart rate queue +.>
Figure SMS_197
And long-term heart rate queue->
Figure SMS_198
The method comprises the steps of carrying out a first treatment on the surface of the Wherein short term heart rate queue
Figure SMS_200
The maximum queue length is +.>
Figure SMS_205
Long-term heart rate queue->
Figure SMS_192
The maximum queue length is +.>
Figure SMS_193
；
Step two, acquiring a time stamp of the current moment of the system
Figure SMS_208
；
Step three, if
Figure SMS_209
Or->
Figure SMS_210
Activating a sleep monitoring module to acquire the current sleep state of the user +.>
Figure SMS_211
If->
Figure SMS_212
If the value is 0, jumping to the step S2, otherwise jumping to the step II; wherein (1)>
Figure SMS_213
0, indicating that the user is currently awake; />
Figure SMS_214
1, indicating that the user is currently in a sleep state.
In step S2, the fall detection device runs a heart rate tracking step comprising: activating a PPG heart rate monitoring module to acquire the current heart rate value of the user
Figure SMS_225
If->
Figure SMS_227
The user's current heart rate value +.>
Figure SMS_228
Joining the short term heart rate queue->
Figure SMS_230
Is in the tail of the team; if->
Figure SMS_232
The user is currently heartRate->
Figure SMS_233
Joining the long term heart rate queue->
Figure SMS_234
Is in the tail of the team; if the short-term heart rate queue->
Figure SMS_215
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_217
Deleting the short-term heart rate queue +.>
Figure SMS_219
Is a team head node; if the long-term heart rate queue->
Figure SMS_222
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_223
Deleting the long-term heart rate queue +.>
Figure SMS_226
Is a team head node; jump to step S1. In some embodiments, step S2 comprises: step four, activating a PPG heart rate monitoring module to acquire the current heart rate value +.>
Figure SMS_229
If->
Figure SMS_231
The user's current heart rate value +.>
Figure SMS_216
Joining the short term heart rate queue->
Figure SMS_218
Is in the tail of the team; if->
Figure SMS_220
The user's current heart rate value +.>
Figure SMS_221
Joining the long term heart rate queue->
Figure SMS_224
Is in the tail of the team;
step five, if the short-term heart rate queue
Figure SMS_235
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_236
Deleting the short-term heart rate queue +.>
Figure SMS_237
Is a team head node; if the long-term heart rate queue->
Figure SMS_238
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_239
Deleting the long-term heart rate queue +.>
Figure SMS_240
Is a team head node; jump to step one.
In step S3, the fall detection device runs a fall event detection step comprising: from triaxial acceleration signals
Figure SMS_241
、/>
Figure SMS_245
、/>
Figure SMS_249
And a triaxial angular velocity signal>
Figure SMS_250
、/>
Figure SMS_251
、/>
Figure SMS_252
Calculating a weighted Euler variation angle +.>
Figure SMS_253
Window change of combined acceleration
Figure SMS_242
Angular velocity window change->
Figure SMS_243
To be equal to the window change threshold->
Figure SMS_244
Comparing if
Figure SMS_246
Or->
Figure SMS_247
Or->
Figure SMS_248
Then the process goes to step S4. In some embodiments, step S3 comprises:
step S31, at sampling rate
Figure SMS_257
Acquiring a time period of a triaxial accelerometer module and a triaxial gyroscope module +.>
Figure SMS_259
Inner triaxial acceleration signal->
Figure SMS_261
、/>
Figure SMS_263
、/>
Figure SMS_264
And a triaxial angular velocity signal>
Figure SMS_266
、/>
Figure SMS_268
、/>
Figure SMS_254
And respectively performing mean filtering processing to obtain signals +.>
Figure SMS_256
、/>
Figure SMS_258
、/>
Figure SMS_260
、/>
Figure SMS_262
、/>
Figure SMS_265
and />
Figure SMS_267
The method comprises the steps of carrying out a first treatment on the surface of the Calculate the total acceleration +.>
Figure SMS_269
The method comprises the steps of carrying out a first treatment on the surface of the Calculating the resultant angular velocity +.>
Figure SMS_255
；
Step S32, setting frame length
Figure SMS_278
Frame shift->
Figure SMS_280
For the signals +.>
Figure SMS_282
、/>
Figure SMS_283
、/>
Figure SMS_285
、/>
Figure SMS_288
、/>
Figure SMS_290
、
Figure SMS_292
、/>
Figure SMS_294
and />
Figure SMS_296
Performing framing processing to obtain signal->
Figure SMS_297
、/>
Figure SMS_298
、/>
Figure SMS_300
、/>
Figure SMS_302
、/>
Figure SMS_304
、/>
Figure SMS_270
、/>
Figure SMS_272
and />
Figure SMS_275
And respectively for the signals->
Figure SMS_277
、/>
Figure SMS_279
、/>
Figure SMS_281
、/>
Figure SMS_284
、/>
Figure SMS_286
、/>
Figure SMS_287
、/>
Figure SMS_289
and />
Figure SMS_291
Windowing to obtain signal +.>
Figure SMS_293
、/>
Figure SMS_295
、/>
Figure SMS_299
、/>
Figure SMS_301
、/>
Figure SMS_303
、/>
Figure SMS_271
、/>
Figure SMS_273
and />
Figure SMS_274
； wherein ,/>
Figure SMS_276
；
Figure SMS_305
，/>
Figure SMS_306
；
Figure SMS_307
，/>
Figure SMS_308
；
Figure SMS_309
，/>
Figure SMS_310
；
Figure SMS_311
；
Figure SMS_312
；
Figure SMS_313
；
Step S33, calculating Euler angles
Figure SMS_314
，/>
Figure SMS_315
； wherein ,
Figure SMS_316
，/>
Figure SMS_317
；
step S34, for the signal
Figure SMS_318
、/>
Figure SMS_320
、/>
Figure SMS_322
、/>
Figure SMS_325
、/>
Figure SMS_326
、/>
Figure SMS_328
and />
Figure SMS_331
Synchronous selection of a single Window->
Figure SMS_319
、/>
Figure SMS_321
、/>
Figure SMS_323
、/>
Figure SMS_324
、/>
Figure SMS_327
、/>
Figure SMS_329
and />
Figure SMS_330
；
wherein ,
Figure SMS_332
；
Figure SMS_333
；
Figure SMS_334
；
Figure SMS_335
；
Figure SMS_336
；
step S35, calculating the absolute change of the Euler angle window:
Figure SMS_337
；
Figure SMS_338
；
Figure SMS_339
；
Figure SMS_340
；
Figure SMS_341
；
Figure SMS_342
；
Figure SMS_343
； wherein ,/>
Figure SMS_344
and />
Figure SMS_345
Can be obtained according to experimental data analysis; />
Step S36, calculating a weighted Euler variation angle
Figure SMS_346
； wherein ,
Figure SMS_347
、/>
Figure SMS_348
and />
Figure SMS_349
Can be obtained according to experimental data analysis;
step S37, obtaining
Figure SMS_351
Maximum value->
Figure SMS_352
And minimum->
Figure SMS_353
Obtain->
Figure SMS_354
Maximum value->
Figure SMS_355
And minimum->
Figure SMS_356
Calculate the combined acceleration window change->
Figure SMS_357
Angular velocity window change
Figure SMS_350
；
Step S38, setting a window change threshold
Figure SMS_359
If->
Figure SMS_361
Or (b)
Figure SMS_363
Or->
Figure SMS_364
Step S4, jumping to the step; otherwise, signal->
Figure SMS_366
、/>
Figure SMS_367
、/>
Figure SMS_368
、/>
Figure SMS_358
、
Figure SMS_360
、/>
Figure SMS_362
and />
Figure SMS_365
Synchronously selecting a single window of the next time sequence, and jumping to the step S35; if the next timing single window does not exist, the process goes to step S31.
In step S4, the fall detection device runs a fall event detection step comprising: obtaining a current heart rate value of a user
Figure SMS_370
Calculating the short term heart rate queue +.>
Figure SMS_372
Mean heart rate of all nodes in->
Figure SMS_373
And the long-term heart rate queue
Figure SMS_376
Mean heart rate of all nodes in->
Figure SMS_377
And calculate +.>
Figure SMS_378
，
Figure SMS_381
Setting a heart rate mutation threshold +.>
Figure SMS_369
In the following
Figure SMS_371
If so, the process goes to step S5. In some embodiments, step S4 comprises: step S49, activating a PPG heart rate monitoring module to acquire the current heart rate value of the user +.>
Figure SMS_374
Calculating the short term heart rate queue +.>
Figure SMS_375
Mean heart rate of all nodes in->
Figure SMS_379
Calculating the long-term heart rate queue +.>
Figure SMS_380
Mean heart rate of all nodes in->
Figure SMS_382
；
Step S410, setting a heart rate mutation threshold
Figure SMS_384
Calculate->
Figure SMS_385
，
Figure SMS_387
If->
Figure SMS_388
Step S5, jumping to the step; otherwise, signal->
Figure SMS_391
、/>
Figure SMS_392
、/>
Figure SMS_393
、/>
Figure SMS_383
、/>
Figure SMS_386
、/>
Figure SMS_389
and />
Figure SMS_390
Synchronously selecting a single window of the next time sequence, and jumping to the step S35; if the next timing single window does not exist, the process goes to step S31.
In step S5, the fall detection device runs a fall event detection step comprising: transmitting the falling event to the master control center module through the falling event detection module
Figure SMS_394
The central control module receives the fall event +.>
Figure SMS_395
And then enter an emergency rescue program to provide assistance. In some embodiments, step S5 comprises: step S511, the fall event detection module sends the fall event +.>
Figure SMS_396
The method comprises the steps of carrying out a first treatment on the surface of the Step S512, receiving the fall event +.>
Figure SMS_397
And then entering a preset emergency contact program to provide rescue. Further, step S512 includes the steps of: receiving the fall event +.>
Figure SMS_398
The master control center module acquires the current position information of the user through the positioning module; will beThe help seeking information with the current position information of the user is sent to all emergency contacts reserved by the user through the communication module, and voice calls are sequentially and circularly dialed according to the sequence of the emergency contacts until the voice calls are connected; after the call is ended, the process goes to step S31.
It should also be noted that, referring to fig. 2, the fall detection method may be implemented in a fall detection apparatus, which includes: the system comprises a triaxial accelerometer module, a triaxial gyroscope module, a PPG heart rate monitoring module, a sleep monitoring module, a computing module, a data storage module, a power supply module and a control terminal module. The tri-axial accelerometer module, comprising: a three-axis accelerometer; when the falling detection device is worn on the wrist of a user, the positive Z-axis direction of the triaxial accelerometer is the direction of pointing the palm of the user to the back of the hand. The tri-axial gyroscope module includes: a three-axis gyroscope; the X-axis positive direction of the three-axis gyroscope is the same as the X-axis positive direction of the three-axis accelerometer, the Y-axis positive direction of the three-axis gyroscope is the same as the Y-axis positive direction of the three-axis accelerometer, and the Z-axis positive direction of the three-axis gyroscope is the same as the Z-axis positive direction of the three-axis accelerometer. The control terminal module comprises: the device comprises a communication module, an input module, a display module and a positioning module. The PPG heart rate monitoring module comprises: returning the current heart rate value of the user
Figure SMS_399
. The sleep monitoring module comprises: returning to the user's current sleep state->
Figure SMS_400
If->
Figure SMS_401
0, indicating that the user is currently awake; if->
Figure SMS_402
1, indicating that the user is currently in a sleep state. An accelerometer and a gyroscope which are arranged in the fall detection device acquire triaxial acceleration and triaxial angular velocity signals, and the triaxial acceleration and the triaxial angular velocity signals are respectively calculated independentlyAnd then, according to the comparison result of the tracked long/short-term heart rate and the current heart rate of the user, making final confirmation of the falling event detection, and finally, returning the falling event to help the user to realize effective emergency help so as to obtain timely rescue. The fall detection method runs in the equipment, and the equipment does not need too many sensors, so the equipment has the characteristics of portability, privacy, comfort in wearing and the like, can be suitable for and fully covers all formal and informal daily scenes of the old, and reduces various risks caused by falling of the old. The method for detecting the falling event is based on a falling event pre-detection algorithm of a threshold value judging method, the used model features are simple time domain features, the robustness of the algorithm is high, the reliability is high, and meanwhile, the calculation and storage resources required to be occupied by the algorithm are low; and the tracked long/short-term heart rate of the user is combined with the current heart rate to carry out simple comparison to realize final confirmation of the fall event detection, so that the anti-noise and anti-interference capability is better, the false detection rate and the omission rate of the fall event detection are greatly reduced, the algorithm robustness is high, the reliability is high, the user is ensured to realize effective and tight fall emergency help seeking to obtain timely rescue, and the high-quality life and the navigation are protected for the old.
Example two
Referring to fig. 3, the present embodiment provides a fall detection system, comprising: a heart rate tracking module and a fall event detection module; the heart rate tracking module and the fall event detection module are executed concurrently in the fall detection system, so that the heart rate tracking module and the fall event detection module operate the method in any one of the embodiments, and the heart rate tracking step is performed concurrently by determining whether a first series of parameters satisfy a first formula; the first series of parameters includes a heart rate long-term monitoring time interval
Figure SMS_434
Short-term heart rate monitoring time interval
Figure SMS_435
Short term heart rate queue->
Figure SMS_436
The maximum queue length is +.>
Figure SMS_437
Long-term heart rate queue->
Figure SMS_438
Maximum queue length of (a) is
Figure SMS_439
And the timestamp of the current moment of the system +.>
Figure SMS_440
The method comprises the steps of carrying out a first treatment on the surface of the The first formula is->
Figure SMS_441
Or (b)
Figure SMS_442
The method comprises the steps of carrying out a first treatment on the surface of the When the first series of parameters meet the first formula, activating a PPG heart rate monitoring module to acquire the current heart rate value of the user +.>
Figure SMS_443
If->
Figure SMS_444
The user's current heart rate value +.>
Figure SMS_445
Joining the short term heart rate queue->
Figure SMS_446
Is in the tail of the team; if->
Figure SMS_447
The user's current heart rate value +.>
Figure SMS_448
Joining the long term heart rate queue->
Figure SMS_403
Is in the tail of the team; if the short-term heart rate queue->
Figure SMS_406
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_408
Deleting the short-term heart rate queue +.>
Figure SMS_410
Is a team head node; if the long-term heart rate queue->
Figure SMS_413
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_416
Deleting the long-term heart rate queue
Figure SMS_419
Is a team head node. The fall event detection step is performed by detecting +_based on the three-axis acceleration signal>
Figure SMS_421
、/>
Figure SMS_423
、/>
Figure SMS_425
And a triaxial angular velocity signal>
Figure SMS_426
、/>
Figure SMS_427
、/>
Figure SMS_428
Calculating a weighted Euler variation angle +.>
Figure SMS_429
Combined acceleration window variation->
Figure SMS_430
Angular velocity window change->
Figure SMS_432
To be equal to the window change threshold->
Figure SMS_404
Comparing if->
Figure SMS_405
Or (b)
Figure SMS_407
Or->
Figure SMS_409
Acquiring the current heart rate value of the user>
Figure SMS_411
Calculating the short-term heart rate queue
Figure SMS_412
Mean heart rate of all nodes in->
Figure SMS_414
And said long-term heart rate queue->
Figure SMS_415
Mean heart rate of all nodes in (1)
Figure SMS_417
And calculate +.>
Figure SMS_418
，/>
Figure SMS_420
Setting a heart rate mutation threshold +.>
Figure SMS_422
In->
Figure SMS_424
When in use, the falling event detection module sends a falling event to the master control center module>
Figure SMS_431
The central control module receives the fall event +.>
Figure SMS_433
And then the user enters an emergency rescue program to provide rescue, so that falling detection and rescue are realized, the privacy of the user is ensured, the detection cost is reduced, the detection range is widened, and the detection accuracy is improved.
Example III
Referring to fig. 4, the present embodiment provides a fall detection apparatus comprising:
a memory storing a computer program;
a processor running the computer program to implement the method of any of the above embodiments, through a heart rate tracking step and a fall event detection step running concurrently, the heart rate tracking step by determining whether the first series of parameters satisfy a first formula; the first series of parameters includes a heart rate long-term monitoring time interval
Figure SMS_480
Short-term heart rate monitoring time interval
Figure SMS_481
Short term heart rate queue->
Figure SMS_482
The maximum queue length is +.>
Figure SMS_483
Long-term heart rate queue->
Figure SMS_484
Maximum queue length of (a) is
Figure SMS_485
And the timestamp of the current moment of the system +.>
Figure SMS_486
The method comprises the steps of carrying out a first treatment on the surface of the The first formula is->
Figure SMS_487
Or (b)
Figure SMS_488
The method comprises the steps of carrying out a first treatment on the surface of the When the first series of parameters meet the first formula, activating a PPG heart rate monitoring module to acquire the current heart rate value of the user +.>
Figure SMS_489
If->
Figure SMS_490
The user's current heart rate value +.>
Figure SMS_491
Joining the short term heart rate queue->
Figure SMS_492
Is in the tail of the team; if->
Figure SMS_493
The user's current heart rate value +.>
Figure SMS_494
Joining the long term heart rate queue->
Figure SMS_449
Is in the tail of the team; if the short-term heart rate queue->
Figure SMS_451
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_453
Deleting the short-term heart rate queue +.>
Figure SMS_456
Is a team head node; if the long-term heart rate queue->
Figure SMS_457
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_458
Deleting the long-term heart rate queue
Figure SMS_460
Is a team head node. The fall event detection step is performed by detecting +_based on the three-axis acceleration signal>
Figure SMS_462
、/>
Figure SMS_463
、/>
Figure SMS_467
And a triaxial angular velocity signal>
Figure SMS_469
、/>
Figure SMS_470
、/>
Figure SMS_472
Calculating a weighted Euler variation angle +.>
Figure SMS_474
Combined acceleration window variation->
Figure SMS_476
Angular velocity window change
Figure SMS_477
To be equal to the window change threshold->
Figure SMS_450
Comparing if->
Figure SMS_452
Or (b)
Figure SMS_454
Or->
Figure SMS_455
Step S4 is skipped to obtain the current heart rate value +.>
Figure SMS_459
Calculating the short term heart rate queue +.>
Figure SMS_461
Mean heart rate of all nodes in->
Figure SMS_464
And said long-term heart rate queue->
Figure SMS_465
Mean heart rate of all nodes in->
Figure SMS_466
And calculate +.>
Figure SMS_468
，
Figure SMS_471
Setting a heart rate mutation threshold +.>
Figure SMS_473
In the following
Figure SMS_475
When in use, the falling event detection module sends a falling event to the master control center module>
Figure SMS_478
The central control module receives the fall event +.>
Figure SMS_479
Then enter the emergency rescue program to provide rescue, thereby realizing falling detection and rescue, guaranteeing user privacy, reducing detection cost and wideningAnd the detection range is increased, and the detection accuracy is improved.
The memory may be a flash memory (flash), and the computer program may be an application program, a functional module, or the like for implementing the above method. In the alternative, the memory may be separate or integrated with the processor. When the memory is a device separate from the processor, the apparatus may further include: and the bus is used for connecting the memory and the processor.
Example IV
The present embodiment provides a readable storage medium, in which a computer program is stored, where the computer program is configured to implement the methods provided in the foregoing various embodiments when executed by a processor, by a heart rate tracking step and a fall event detection step that are executed concurrently, where the heart rate tracking step determines whether a first series of parameters satisfy a first formula; the first series of parameters includes a heart rate long-term monitoring time interval
Figure SMS_525
Short-term heart rate monitoring time interval->
Figure SMS_527
Short term heart rate queue->
Figure SMS_528
The maximum queue length is +.>
Figure SMS_529
Long-term heart rate queue->
Figure SMS_530
The maximum queue length is +.>
Figure SMS_531
And the timestamp of the current moment of the system +.>
Figure SMS_532
The method comprises the steps of carrying out a first treatment on the surface of the The first formula is->
Figure SMS_533
Or (b)
Figure SMS_534
The method comprises the steps of carrying out a first treatment on the surface of the When the first series of parameters meet the first formula, activating a PPG heart rate monitoring module to acquire the current heart rate value of the user +.>
Figure SMS_535
If->
Figure SMS_536
The user's current heart rate value +.>
Figure SMS_537
Joining the short term heart rate queue->
Figure SMS_538
Is in the tail of the team; if->
Figure SMS_539
The user's current heart rate value +.>
Figure SMS_540
Joining the long term heart rate queue->
Figure SMS_495
Is in the tail of the team; if the short-term heart rate queue->
Figure SMS_499
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_502
Deleting the short-term heart rate queue +.>
Figure SMS_504
Is a team head node; if the long-term heart rate queue->
Figure SMS_507
The number of nodes of (a) reaches its maximum queue length +.>
Figure SMS_508
Deleting the long-term heart rate queue
Figure SMS_510
Is a team head node. The fall event detection step is performed by detecting +_based on the three-axis acceleration signal>
Figure SMS_511
、/>
Figure SMS_512
、/>
Figure SMS_514
And a triaxial angular velocity signal>
Figure SMS_515
、/>
Figure SMS_516
、/>
Figure SMS_518
Calculating a weighted Euler variation angle +.>
Figure SMS_523
Combined acceleration window variation->
Figure SMS_524
Angular velocity window change
Figure SMS_526
To be equal to the window change threshold->
Figure SMS_496
Comparing if->
Figure SMS_497
Or->
Figure SMS_498
Or->
Figure SMS_500
Acquiring the current heart rate value of the user>
Figure SMS_501
Calculating the short term heart rate queue +.>
Figure SMS_503
Mean heart rate of all nodes in->
Figure SMS_505
And said long-term heart rate queue->
Figure SMS_506
Mean heart rate of all nodes in->
Figure SMS_509
And calculate
Figure SMS_513
，/>
Figure SMS_517
Setting a heart rate mutation threshold value
Figure SMS_519
In->
Figure SMS_520
When in use, the falling event detection module sends a falling event to the master control center module>
Figure SMS_521
The central control module receives the fall event +.>
Figure SMS_522
And then the user enters an emergency rescue program to provide rescue, so that falling detection and rescue are realized, the privacy of the user is ensured, the detection cost is reduced, the detection range is widened, and the detection accuracy is improved.
The readable storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media can be any available media that can be accessed by a general purpose or special purpose computer. For example, a readable storage medium is coupled to the processor such that the processor can read information from, and write information to, the readable storage medium. In the alternative, the readable storage medium may be integral to the processor. The processor and the readable storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). In addition, the ASIC may reside in a user device. The processor and the readable storage medium may reside as discrete components in a communication device. The readable storage medium may be read-only memory (ROM), random-access memory (RAM), CD-ROMs, magnetic tape, floppy disk, optical data storage device, etc. In the above embodiment of the apparatus, it should be understood that the processor may be a central processing unit (english: central Processing Unit, abbreviated as CPU), or may be other general purpose processors, digital signal processors (english: digital Signal Processor, abbreviated as DSP), application specific integrated circuits (english: application Specific Integrated Circuit, abbreviated as ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.

Claims (10)

1. A fall detection method comprising a heart rate tracking step and a fall event detection step, operating concurrently, the heart rate tracking step comprising the steps of:
s1, judging whether a first series of parameters meet a first formula or not; the first series of parameters includes a heart rate long-term monitoring time interval
Figure QLYQS_3
Short-term heart rate monitoring time interval->
Figure QLYQS_4
Short term heart rate queue->
Figure QLYQS_5
The maximum queue length is +.>
Figure QLYQS_6
Long-term heart rate queue->
Figure QLYQS_7
The maximum queue length is +.>
Figure QLYQS_8
And the timestamp of the current moment of the system +.>
Figure QLYQS_9
The method comprises the steps of carrying out a first treatment on the surface of the The first formula is
Figure QLYQS_1
Or->
Figure QLYQS_2
The method comprises the steps of carrying out a first treatment on the surface of the When the first series of parameters meet the first formula, jumping to a step S2;
s2, activating a PPG heart rate monitoring module to acquire a current heart rate value of a user
Figure QLYQS_11
If->
Figure QLYQS_12
The user's current heart rate value +.>
Figure QLYQS_15
Joining the short term heart rate queue->
Figure QLYQS_18
Is in the tail of the team; if it is
Figure QLYQS_20
The user's current heart rate value +.>
Figure QLYQS_21
Joining the long term heart rate queue->
Figure QLYQS_22
Is in the tail of the team; if the short-term heart rate queue->
Figure QLYQS_10
The number of nodes of (a) reaches its maximum queue length +.>
Figure QLYQS_13
Deleting the short-term heart rate queue +.>
Figure QLYQS_14
Is a team head node; if the long-term heart rate queue->
Figure QLYQS_16
The number of nodes of (a) reaches its maximum queue length +.>
Figure QLYQS_17
Deleting the long-term heart rate queue +.>
Figure QLYQS_19
Is a team head node; jumping to the step S1;
the fall event detection step comprises the steps of:
s3, according to the triaxial acceleration signal
Figure QLYQS_24
、/>
Figure QLYQS_27
、/>
Figure QLYQS_29
And a triaxial angular velocity signal>
Figure QLYQS_31
、/>
Figure QLYQS_33
、/>
Figure QLYQS_34
Calculating a weighted Euler variation angle +.>
Figure QLYQS_35
Combined acceleration window variation->
Figure QLYQS_23
Angular velocity window change->
Figure QLYQS_25
To be in line with the window change threshold
Figure QLYQS_26
Comparing if->
Figure QLYQS_28
Or->
Figure QLYQS_30
Or->
Figure QLYQS_32
Step S4, jumping to the step;
s4, obtaining the current heart rate value of the user
Figure QLYQS_37
Calculating the short term heart rate queue +.>
Figure QLYQS_38
Mean heart rate of all nodes in (1)
Figure QLYQS_40
And said long-term heart rate queue->
Figure QLYQS_41
Mean heart rate of all nodes in->
Figure QLYQS_42
And calculate
Figure QLYQS_43
，/>
Figure QLYQS_44
Setting a heart rate mutation threshold value
Figure QLYQS_36
In->
Figure QLYQS_39
If yes, jumping to step S5;
s5, sending a falling event to the master control center module through the falling event detection module
Figure QLYQS_45
The central control module receives the fall event +.>
Figure QLYQS_46
And then enter an emergency rescue program to provide assistance.
2. A fall detection method as claimed in claim 1, wherein step S1 comprises:
step one, setting a heart rate long-term monitoring time interval
Figure QLYQS_48
Short heart rate monitoring time interval->
Figure QLYQS_49
Create and initialize a short term heart rate queue +.>
Figure QLYQS_50
And long-term heart rate queue->
Figure QLYQS_51
The method comprises the steps of carrying out a first treatment on the surface of the Wherein, short term heart rate queue->
Figure QLYQS_52
Maximum queue length of (a) is
Figure QLYQS_53
Long-term heart rate queue->
Figure QLYQS_54
The maximum queue length is +.>
Figure QLYQS_47
；
Step two, acquiring a time stamp of the current moment of the system
Figure QLYQS_55
；
Step three, if
Figure QLYQS_56
Or->
Figure QLYQS_57
Activating a sleep monitoring module to acquire the current sleep state of the user +.>
Figure QLYQS_58
If->
Figure QLYQS_59
If the value is 0, jumping to the step S2, otherwise jumping to the step II; wherein (1)>
Figure QLYQS_60
0, indicating that the user is currently awake; />
Figure QLYQS_61
1, indicating that the user is currently in a sleep state. />
3. A fall detection method as claimed in claim 2, wherein step S2 comprises:
step four, activating a PPG heart rate monitoring module to acquire the current heart rate value of the user
Figure QLYQS_62
If (if)
Figure QLYQS_63
The user's current heart rate value +.>
Figure QLYQS_64
Joining the short term heart rate queue->
Figure QLYQS_65
Is in the tail of the team; if->
Figure QLYQS_66
The user's current heart rate value +.>
Figure QLYQS_67
Joining the long term heart rate queue->
Figure QLYQS_68
Is in the tail of the team;
step five, if the short-term heart rate queue
Figure QLYQS_69
The number of nodes of (a) reaches its maximum queue length +.>
Figure QLYQS_70
Deleting the short-term heart rate queue +.>
Figure QLYQS_71
Is a team head node; if the long-term heart rate queue->
Figure QLYQS_72
The number of nodes of (a) reaches its maximum queue length +.>
Figure QLYQS_73
Deleting the long-term heart rate queue +.>
Figure QLYQS_74
Is a team head node; jump to step one.
4. A fall detection method as claimed in claim 3, wherein step S3 comprises:
step S31, at sampling rate
Figure QLYQS_78
Acquiring a time period of a triaxial accelerometer module and a triaxial gyroscope module +.>
Figure QLYQS_80
Inner triaxial acceleration signal->
Figure QLYQS_83
、/>
Figure QLYQS_84
、/>
Figure QLYQS_87
And a triaxial angular velocity signal>
Figure QLYQS_89
、/>
Figure QLYQS_90
、/>
Figure QLYQS_75
And respectively performing mean filtering processing to obtain signals +.>
Figure QLYQS_77
、/>
Figure QLYQS_79
、/>
Figure QLYQS_81
、/>
Figure QLYQS_82
、/>
Figure QLYQS_85
and />
Figure QLYQS_86
The method comprises the steps of carrying out a first treatment on the surface of the Calculate the total acceleration +.>
Figure QLYQS_88
The method comprises the steps of carrying out a first treatment on the surface of the Calculating the resultant angular velocity +.>
Figure QLYQS_76
；
Step S32, setting frame length
Figure QLYQS_101
Frame shift->
Figure QLYQS_103
For the signals +.>
Figure QLYQS_106
、/>
Figure QLYQS_109
、/>
Figure QLYQS_111
、/>
Figure QLYQS_114
、/>
Figure QLYQS_117
、/>
Figure QLYQS_118
、
Figure QLYQS_119
and />
Figure QLYQS_120
Performing framing processing to obtain signal->
Figure QLYQS_121
、/>
Figure QLYQS_122
、/>
Figure QLYQS_123
、/>
Figure QLYQS_124
、/>
Figure QLYQS_125
、/>
Figure QLYQS_91
、/>
Figure QLYQS_94
and />
Figure QLYQS_95
And respectively for the signals->
Figure QLYQS_97
、/>
Figure QLYQS_98
、/>
Figure QLYQS_100
、/>
Figure QLYQS_102
、/>
Figure QLYQS_104
、/>
Figure QLYQS_105
、/>
Figure QLYQS_107
and />
Figure QLYQS_108
Windowing to obtain signal +.>
Figure QLYQS_110
、/>
Figure QLYQS_112
、/>
Figure QLYQS_113
、/>
Figure QLYQS_115
、/>
Figure QLYQS_116
、/>
Figure QLYQS_92
、/>
Figure QLYQS_93
and />
Figure QLYQS_96
； wherein ,/>
Figure QLYQS_99
；
Figure QLYQS_126
，/>
Figure QLYQS_127
；
Figure QLYQS_128
，/>
Figure QLYQS_129
；
Figure QLYQS_130
，/>
Figure QLYQS_131
；
Figure QLYQS_132
；
Figure QLYQS_133
；
Figure QLYQS_134
；
Step S33, calculating Euler angles
Figure QLYQS_135
，/>
Figure QLYQS_136
； wherein ,
Figure QLYQS_137
，/>
Figure QLYQS_138
；
step S34, for the signal
Figure QLYQS_146
、/>
Figure QLYQS_147
、/>
Figure QLYQS_148
、/>
Figure QLYQS_149
、/>
Figure QLYQS_150
、/>
Figure QLYQS_151
and />
Figure QLYQS_152
Synchronous selection of a single Window->
Figure QLYQS_139
、/>
Figure QLYQS_140
、/>
Figure QLYQS_141
、/>
Figure QLYQS_142
、/>
Figure QLYQS_143
、/>
Figure QLYQS_144
and />
Figure QLYQS_145
；
wherein ,
Figure QLYQS_153
；/>
Figure QLYQS_154
；
Figure QLYQS_155
；
Figure QLYQS_156
；
Figure QLYQS_157
；
step S35, calculating the absolute change of the Euler angle window:
Figure QLYQS_158
；
Figure QLYQS_159
；
Figure QLYQS_160
；
Figure QLYQS_161
；
Figure QLYQS_162
；
Figure QLYQS_163
；
Figure QLYQS_164
； wherein ,/>
Figure QLYQS_165
and />
Figure QLYQS_166
Can be obtained according to experimental data analysis;
step S36, calculating a weighted Euler variation angle
Figure QLYQS_167
； wherein ,/>
Figure QLYQS_168
、/>
Figure QLYQS_169
and />
Figure QLYQS_170
Can be obtained according to experimental data analysis;
step S37, obtaining
Figure QLYQS_172
Maximum value->
Figure QLYQS_173
And minimum->
Figure QLYQS_174
Obtain->
Figure QLYQS_175
Maximum value->
Figure QLYQS_176
And minimum->
Figure QLYQS_177
Calculate the combined acceleration window change->
Figure QLYQS_178
Angular velocity window change
Figure QLYQS_171
；
Step S38, setting a window change threshold
Figure QLYQS_180
If->
Figure QLYQS_181
Or->
Figure QLYQS_183
Or (b)
Figure QLYQS_184
Step S4, jumping to the step; otherwise, signal->
Figure QLYQS_187
、/>
Figure QLYQS_188
、/>
Figure QLYQS_189
、/>
Figure QLYQS_179
、/>
Figure QLYQS_182
、/>
Figure QLYQS_185
and />
Figure QLYQS_186
Synchronously selecting a single window of the next time sequence, and jumping to the step S35; if the next timing single window does not exist, the process goes to step S31.
5. A fall detection method as claimed in claim 4, wherein step S4 comprises:
step S49, activating a PPG heart rate monitoring module to acquire the current heart rate value of the user
Figure QLYQS_190
Calculating the short-term heart rate queue
Figure QLYQS_191
Mean heart rate of all nodes in->
Figure QLYQS_192
Calculating the long-term heart rate queue +.>
Figure QLYQS_193
Mean heart rate of all nodes in (1)
Figure QLYQS_194
；
Step S410, setting a heart rate mutation threshold
Figure QLYQS_196
Calculate->
Figure QLYQS_198
，
Figure QLYQS_201
If->
Figure QLYQS_202
Step S5, jumping to the step; otherwise, signal->
Figure QLYQS_203
、/>
Figure QLYQS_204
、/>
Figure QLYQS_205
、/>
Figure QLYQS_195
、/>
Figure QLYQS_197
、/>
Figure QLYQS_199
and />
Figure QLYQS_200
Synchronously selecting a single window of the next time sequence, and jumping to the step S35; if the next timing single window does not exist, the process goes to step S31./>
6. A fall detection method as claimed in claim 5, wherein step S5 comprises:
step S511, a fall event is sent to the central control module through the fall event detection module
Figure QLYQS_206
；
Step S512, receiving a fall event at the Master control center Module
Figure QLYQS_207
And then entering a preset emergency contact program to provide rescue.
7. A fall detection method as claimed in claim 6, wherein step S512 comprises the steps of:
receiving the fall event at the central control module
Figure QLYQS_208
The master control center module acquires the current position information of the user through the positioning module;
the help seeking information with the current position information of the user is sent to all emergency contacts reserved by the user through a communication module, and voice calls are sequentially and circularly dialed according to the sequence of the emergency contacts until the voice calls are connected;
after the call is ended, the process goes to step S31.
8. A fall detection system, comprising: a heart rate tracking module and a fall event detection module;
the heart rate tracking module and the fall event detection module being executed concurrently in the fall detection system such that the heart rate tracking module and the fall event detection module operate the method of claim 1.
9. A fall detection device, comprising: the system comprises a triaxial accelerometer module, a triaxial gyroscope module, a PPG heart rate monitoring module, a sleep monitoring module, a calculation module, a data storage module, a power supply module and a control terminal module; the triaxial accelerometer module comprises a triaxial accelerometer; when the falling detection device is worn on the wrist of a user, the positive Z-axis direction of the triaxial accelerometer is the direction that the palm of the user points to the back of the hand; the three-axis gyroscope module comprises a three-axis gyroscope; the positive X-axis direction of the three-axis gyroscope is the same as the positive X-axis direction of the three-axis accelerometer, the positive Y-axis direction of the three-axis gyroscope is the same as the positive Y-axis direction of the three-axis accelerometer, and the positive Z-axis direction of the three-axis gyroscope is the same as the positive Z-axis direction of the three-axis accelerometer; the control terminal module packageThe device comprises a communication module, an input module, a display module and a positioning module; the PPG heart rate monitoring module comprises a step of returning the current heart rate value of the user
Figure QLYQS_209
The method comprises the steps of carrying out a first treatment on the surface of the The sleep monitoring module comprises a step of returning the current sleep state of the user>
Figure QLYQS_210
If->
Figure QLYQS_211
0, indicating that the user is currently awake; if->
Figure QLYQS_212
1, indicating that the user is currently in a sleep state.
10. A readable storage medium storing a computer program, wherein the computer program is operative on a processor to implement the method of any one of claims 1-7.
CN202310440017.8A 2023-04-23 2023-04-23 Fall detection method and device Active CN116229676B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310440017.8A CN116229676B (en) 2023-04-23 2023-04-23 Fall detection method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310440017.8A CN116229676B (en) 2023-04-23 2023-04-23 Fall detection method and device

Publications (2)

Publication Number Publication Date
CN116229676A true CN116229676A (en) 2023-06-06
CN116229676B CN116229676B (en) 2023-10-03

Family

ID=86580810

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310440017.8A Active CN116229676B (en) 2023-04-23 2023-04-23 Fall detection method and device

Country Status (1)

Country Link
CN (1) CN116229676B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104055518A (en) * 2014-07-08 2014-09-24 广州柏颐信息科技有限公司 Fall detection wrist watch and fall detection method
CN204542088U (en) * 2015-02-12 2015-08-12 田文壮 Old man uses intelligent health wrist strap
CN110675596A (en) * 2019-10-09 2020-01-10 台州颐健科技有限公司 Fall detection method applied to wearable terminal
CN113288096A (en) * 2021-05-24 2021-08-24 南京优博一创智能科技有限公司 Sleep health management method and system based on short-term and medium-term sleep data analysis
US20220175310A1 (en) * 2020-12-09 2022-06-09 Medtronic, Inc. Detection and monitoring of sleep apnea conditions
US20220223274A1 (en) * 2021-01-10 2022-07-14 Bardy Diagnostics, Inc. System and method for long-term patient monitoring of continuous ecg and physiological data

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104055518A (en) * 2014-07-08 2014-09-24 广州柏颐信息科技有限公司 Fall detection wrist watch and fall detection method
CN204542088U (en) * 2015-02-12 2015-08-12 田文壮 Old man uses intelligent health wrist strap
CN110675596A (en) * 2019-10-09 2020-01-10 台州颐健科技有限公司 Fall detection method applied to wearable terminal
US20220175310A1 (en) * 2020-12-09 2022-06-09 Medtronic, Inc. Detection and monitoring of sleep apnea conditions
US20220223274A1 (en) * 2021-01-10 2022-07-14 Bardy Diagnostics, Inc. System and method for long-term patient monitoring of continuous ecg and physiological data
CN113288096A (en) * 2021-05-24 2021-08-24 南京优博一创智能科技有限公司 Sleep health management method and system based on short-term and medium-term sleep data analysis

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陶文元: "基于可穿戴传感的人体跌倒行为检测研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 7, pages 140 - 207 *

Also Published As

Publication number Publication date
CN116229676B (en) 2023-10-03

Similar Documents

Publication Publication Date Title
EP3014476B1 (en) Using movement patterns to anticipate user expectations
US10416740B2 (en) Upsampling sensors to auto-detect a fitness activity
US9726498B2 (en) Combining monitoring sensor measurements and system signals to determine device context
US9568977B2 (en) Context sensing for computing devices
US20180329713A1 (en) Fitness sensor with low power attributes in sensor hub
US9885734B2 (en) Method of motion processing and related mobile device and microcontroller unit
TWI631451B (en) Method and mobile device with sensor time calibration
US20190076063A1 (en) Systems and methods of ski activity detection
WO2017054298A1 (en) Positioning method and apparatus for mobile terminal, and mobile terminal
CN109758154B (en) Motion state determination method, device, equipment and storage medium
CN116229676B (en) Fall detection method and device
CN111123326B (en) Positioning method, positioning device, storage medium and terminal
Yebda et al. Multi-sensing of fragile persons for risk situation detection: devices, methods, challenges
US20180143217A1 (en) Methods of motion processing and related electronic devices and motion modules
US10551195B2 (en) Portable device with improved sensor position change detection
WO2018014432A1 (en) Voice application triggering control method, device and terminal
WO2022057476A1 (en) Method for generating calibration signal, electronic device, and computer storage medium
CN116943130A (en) Counting method, counting device, counting equipment and storage medium
WO2020097875A1 (en) Falling-down detection method and apparatus, and device and storage medium
CN115644857B (en) Fall detection waistband buckle and detection method thereof
CN114579421A (en) Method and device for testing stuck-in state
WO2020161673A1 (en) A foot mounted wearable device and a method to operate the same
CN116026493B (en) Core body temperature detection method and electronic equipment
WO2023160158A9 (en) Heart rate detection method and apparatus, and computer-readable storage medium and electronic device
CN116784838B (en) Steering identification system, method, equipment and medium based on wearable inertial sensor

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant