CN117158955A - User safety intelligent monitoring method based on wearable monitoring equipment - Google Patents
User safety intelligent monitoring method based on wearable monitoring equipment Download PDFInfo
- Publication number
- CN117158955A CN117158955A CN202311337662.3A CN202311337662A CN117158955A CN 117158955 A CN117158955 A CN 117158955A CN 202311337662 A CN202311337662 A CN 202311337662A CN 117158955 A CN117158955 A CN 117158955A
- Authority
- CN
- China
- Prior art keywords
- positioning
- sequence
- information
- positioning information
- generate
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 84
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000033001 locomotion Effects 0.000 claims abstract description 121
- 210000000707 wrist Anatomy 0.000 claims abstract description 88
- 238000004458 analytical method Methods 0.000 claims abstract description 83
- 238000004891 communication Methods 0.000 claims abstract description 45
- 210000003423 ankle Anatomy 0.000 claims abstract description 28
- 238000012806 monitoring device Methods 0.000 claims abstract description 21
- 230000009471 action Effects 0.000 claims description 84
- 230000001133 acceleration Effects 0.000 claims description 53
- 230000005856 abnormality Effects 0.000 claims description 37
- 230000002159 abnormal effect Effects 0.000 claims description 33
- 238000004088 simulation Methods 0.000 claims description 31
- 230000008859 change Effects 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 20
- 238000013507 mapping Methods 0.000 claims description 18
- 239000013598 vector Substances 0.000 claims description 14
- 230000003213 activating effect Effects 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 230000036541 health Effects 0.000 abstract description 17
- 230000000694 effects Effects 0.000 abstract description 5
- 230000036544 posture Effects 0.000 description 36
- 230000006870 function Effects 0.000 description 16
- 210000001624 hip Anatomy 0.000 description 11
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- GFWBKUDRXMQSFD-FJXQXJEOSA-M 3-aminopropanoyl-[(1s)-1-carboxy-2-(1h-imidazol-5-yl)ethyl]azanide;zinc Chemical compound [Zn].NCCC(=O)[N-][C@H](C(O)=O)CC1=CN=CN1 GFWBKUDRXMQSFD-FJXQXJEOSA-M 0.000 description 1
- 208000012661 Dyskinesia Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000000554 physical therapy Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 229940056457 promace Drugs 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of user safety early warning, and provides a user safety intelligent monitoring method based on wearable monitoring equipment, which comprises the following steps: receiving user positioning information and extracting environment characteristic information; the positioning anomaly analysis generates a positioning anomaly coefficient, if the positioning anomaly coefficient is greater than or equal to a positioning anomaly coefficient threshold value, the communication wrist wearing device, the patch type wearing device and the ankle wearing device carry out positioning information backtracking, a first positioning sequence, a second positioning sequence and a third positioning sequence are generated and are analyzed, falling motion probability is generated, if the positioning anomaly coefficient is greater than or equal to a falling motion probability threshold value, falling safety early warning signals are generated, the problem that the monitoring range of the fixed safety monitoring device is limited, the whole environment cannot be comprehensively monitored, real-time and omnibearing health monitoring service technical problems cannot be provided for a user is solved, the purpose that the wearable device is utilized to realize omnibearing and all-weather monitoring of the user is achieved, the monitoring range is enlarged, monitoring is carried out at any time and any place, and the timeliness and accuracy technical effect of monitoring are improved.
Description
Technical Field
The invention relates to the technical field related to user safety precaution, in particular to a user safety intelligent monitoring method based on wearable monitoring equipment.
Background
In recent years, wearable devices are becoming popular, and the portability and the real-time monitoring capability of the wearable devices enable the wearable devices to be widely applied to the fields of health, sports and the like, such as remote handrings with health monitoring functions of sleeping, heart rate, blood oxygen and the like.
Along with the aging of population and the improvement of social health consciousness, the demands for health care and safety monitoring are increasing day by day, and it is common that in a health care institution park, by installing devices such as monitoring equipment and sensors at important positions, the devices are responsible for real-time monitoring by management staff to prevent accidents, but the traditional safety monitoring depends on fixed safety monitoring equipment such as cameras and sensors, and the monitoring range is limited, all areas cannot be covered comprehensively, a certain monitoring blind area exists, and manual inspection and monitoring are often required, so that real-time and omnibearing monitoring is difficult to realize.
In summary, the monitoring range of the fixed security monitoring device in the prior art is limited, and only a specific area can be covered, so that the whole environment may not be monitored comprehensively, and the technical problem that real-time and omnibearing health monitoring service cannot be provided for users may not be solved.
Disclosure of Invention
The application provides a user safety intelligent monitoring method based on wearable monitoring equipment, which aims to solve the technical problems that the monitoring range of fixed safety monitoring equipment in the prior art is limited, only a specific area can be covered, the whole environment can not be comprehensively monitored, and real-time and omnibearing health monitoring service can not be provided for users.
In view of the above problems, the present application provides a user safety intelligent monitoring method based on wearable monitoring equipment.
The application discloses a first aspect, provides a user safety intelligent monitoring method based on wearable monitoring equipment, wherein the method is applied to a user safety intelligent monitoring system, the system comprises a service end and a mobile terminal, the system is in communication connection with the wearable monitoring equipment, the wearable monitoring equipment comprises wrist wearing equipment and patch wearing equipment, and the service end execution steps comprise: carrying out digital modeling on the first park to generate a digital twin park, wearing wrist wearing equipment on the wrist of a user, and wearing patch wearing equipment on the waist of the user; the communication wearable monitoring equipment is used for receiving fitting of user positioning information in the digital twin park and extracting environment characteristic information, wherein the environment characteristic information comprises wrist type wearable equipment positioning information, patch type wearable equipment positioning information and ground positioning information; performing positioning abnormality analysis according to the wrist type wearable equipment positioning information, the patch type wearable equipment positioning information and the ground positioning information to generate a positioning abnormality coefficient; when the positioning anomaly coefficient is greater than or equal to a positioning anomaly coefficient threshold, the communication wrist wearing equipment performs positioning information backtracking to generate a first positioning sequence, the communication patch wearing equipment performs positioning information backtracking to generate a second positioning sequence, and the communication ankle wearing equipment performs positioning information backtracking to generate a third positioning sequence; performing motion anomaly analysis according to the first positioning sequence, the second positioning sequence and the third positioning sequence to generate falling motion probability; and when the falling motion probability is greater than or equal to a falling motion probability threshold value, generating a falling safety early warning signal based on the user positioning information and sending the falling safety early warning signal to a neighboring mobile terminal, wherein the neighboring mobile terminal is worn by a park manager.
In another aspect of the disclosure, a user safety intelligent monitoring system based on a wearable monitoring device is provided, wherein the system is in communication connection with the wearable monitoring device, the wearable monitoring device comprises a wrist wearable device and a patch wearable device, and the system comprises: the digital modeling module is used for carrying out digital modeling on the first park to generate a digital twin park, wearing the wrist type wearing equipment on the wrist of the user, and wearing the patch type wearing equipment on the waist of the user; the characteristic information extraction module is used for communicating the wearable monitoring equipment, receiving fitting of user positioning information in the digital twin park, and extracting environment characteristic information, wherein the environment characteristic information comprises wrist type wearable equipment positioning information, patch type wearable equipment positioning information and ground positioning information; the positioning abnormality analysis module is used for performing positioning abnormality analysis according to the wrist type wearable equipment positioning information, the patch type wearable equipment positioning information and the ground positioning information to generate a positioning abnormality coefficient; the positioning information backtracking module is used for carrying out positioning information backtracking on the communication wrist wearing equipment to generate a first positioning sequence, carrying out positioning information backtracking on the communication patch wearing equipment to generate a second positioning sequence, carrying out positioning information backtracking on the communication ankle wearing equipment to generate a third positioning sequence when the positioning abnormal coefficient is larger than or equal to the positioning abnormal coefficient threshold; the motion anomaly analysis module is used for performing motion anomaly analysis according to the first positioning sequence, the second positioning sequence and the third positioning sequence to generate falling motion probability; and the signal sending module is used for generating a falling safety early warning signal based on the user positioning information and sending the falling safety early warning signal to the adjacent mobile terminal when the falling motion probability is larger than or equal to the falling motion probability threshold value, wherein the adjacent mobile terminal is worn by park manager.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
because the digital modeling is adopted, a digital twin park is generated; communicating and receiving user positioning information, and extracting environment characteristic information; the positioning anomaly analysis generates a positioning anomaly coefficient, if the positioning anomaly coefficient is greater than or equal to a positioning anomaly coefficient threshold, the communication wrist wearing device, the patch type wearing device and the ankle wearing device carry out positioning information backtracking, a first positioning sequence, a second positioning sequence and a third positioning sequence are generated, movement anomaly analysis is carried out, falling movement probability is generated, if the positioning anomaly coefficient is greater than or equal to a falling movement probability threshold, falling safety early warning signals are generated and sent to a nearby mobile terminal, the purpose of realizing omnibearing and all-weather monitoring of a user by using the wearable device is achieved, the monitoring range is enlarged, monitoring is carried out at any time and any place, timeliness and accuracy of monitoring are improved, meanwhile, the real-time transmission to the cloud side is carried out for processing and analysis, and the technical effect of data processing and analysis efficiency is greatly improved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic diagram of a possible flow chart of a user safety intelligent monitoring method based on wearable monitoring equipment according to an embodiment of the application;
FIG. 2 is a schematic flow chart of a possible positioning consistency generation method in a user safety intelligent monitoring method based on wearable monitoring equipment according to an embodiment of the present application;
fig. 3 is a schematic diagram of a possible structure of a user safety intelligent monitoring system based on a wearable monitoring device according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a digital modeling module 100, a characteristic information extraction module 200, a positioning abnormality analysis module 300, a positioning information backtracking module 400, a motion abnormality analysis module 500 and a signal transmission module 600.
Detailed Description
Exemplary embodiments of the present application will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present application are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Example 1
As shown in fig. 1, an embodiment of the present application provides a user security intelligent monitoring method based on a wearable monitoring device, where the method is applied to a user security intelligent monitoring system, the system includes a server and a mobile terminal, the system is in communication connection with the wearable monitoring device, the wearable monitoring device includes a wrist wearable device and a patch wearable device, and the server executes the steps including:
step-1: carrying out digital modeling on the first park to generate a digital twin park, wearing wrist wearing equipment on the wrist of a user, and wearing patch wearing equipment on the waist of the user;
step-2: the communication wearable monitoring equipment is used for receiving fitting of user positioning information in the digital twin park and extracting environment characteristic information, wherein the environment characteristic information comprises wrist type wearable equipment positioning information, patch type wearable equipment positioning information and ground positioning information;
step-3: performing positioning abnormality analysis according to the wrist type wearable equipment positioning information, the patch type wearable equipment positioning information and the ground positioning information to generate a positioning abnormality coefficient;
the wearable monitoring equipment comprises wrist wearing equipment and patch wearing equipment, the wrist wearing equipment comprises wrist wearing equipment and ankle wearing equipment, the first park is a health care organization park, and the digital modeling refers to a process of modeling an object in the real world by using a mathematical model and a computer algorithm. The digital twin park is to model an actual park by using a digital modeling technology, create a digital twin version corresponding to the actual park in a virtual environment, specifically, digitally model the building, facilities, environments and the like of the park by using Ansys Twin Builder (software names, which provide functions of modeling, simulating and deploying the digital twin model and can help users to digitally model and optimize the health facility), proMACE (software names, which can use a digital twin modeling tool set to construct the digital twin model of the health facility, describe multi-dimensional information such as the spatial position, rehabilitation physiotherapy, health care, leisure entertainment and the like of the health facility park), unity (software names, which can use the Unity engine to create the virtual environment of the digital twin park and realize interactive experience such as virtual reality and augmented reality) and the like.
The wearable monitoring device is a device which can be worn on a user and is used for monitoring physiological parameters, movement states and other information of the user, and in the embodiment of the application, the wearable monitoring device comprises a wrist type wearing device and a patch type wearing device, wherein the wrist type wearing device is usually a smart watch or a bracelet and the like, can be worn on a wrist and is used for monitoring the position, movement states and other information of the user, and the patch type wearing device is usually a small device which can be stuck on the user and is used for monitoring the physiological parameters, position and other information of the user.
The positioning information fitting refers to fitting and matching the position information of the user in the digital twin park to determine the accurate position of the user in the digital twin park; the environmental characteristic information refers to various information about the environment, such as topography, landform, building, road and the like, extracted from the positioning information, which can help the server to better know the environment where the user is located, and perform early warning and analysis on possible abnormal conditions.
The positioning abnormality analysis refers to judgment and analysis of positioning abnormality according to wrist type wearing equipment, patch type wearing equipment and ground positioning information: if there is a large difference or inconsistency between the positioning information, there may be a situation of positioning abnormality, and the server side may generate a positioning abnormality coefficient by comparing and analyzing the information, for evaluating the degree of positioning abnormality.
The safety of the user is improved, through monitoring the physiological parameters, the motion state and the position information of the user in real time, early warning can be sent out in time and corresponding measures can be taken when abnormal conditions occur, and meanwhile, the establishment of the digital twin park can help the server to better know and master the environment where the user is located, so that service is better provided for the user. In addition, the accuracy and reliability of positioning can be improved, and by fitting and matching using various positioning information, positioning errors can be reduced and positioning accuracy can be improved.
Step-4: when the positioning anomaly coefficient is greater than or equal to a positioning anomaly coefficient threshold, the communication wrist wearing equipment performs positioning information backtracking to generate a first positioning sequence, the communication patch wearing equipment performs positioning information backtracking to generate a second positioning sequence, and the communication ankle wearing equipment performs positioning information backtracking to generate a third positioning sequence;
step-5: performing motion anomaly analysis according to the first positioning sequence, the second positioning sequence and the third positioning sequence to generate falling motion probability;
step-6: and when the falling motion probability is greater than or equal to a falling motion probability threshold value, generating a falling safety early warning signal based on the user positioning information and sending the falling safety early warning signal to a neighboring mobile terminal, wherein the neighboring mobile terminal is worn by a park manager.
The positioning abnormality coefficient is a numerical value for evaluating the positioning abnormality degree obtained by comparing and analyzing the wrist type wearing equipment, the patch type wearing equipment and the ground positioning information; the abnormal positioning coefficient threshold is a preset abnormal positioning coefficient threshold, and when the abnormal positioning coefficient is greater than or equal to the threshold, the abnormal positioning coefficient is indicated; wrist wearing equipment, patch wearing equipment and ankle wearing equipment refer to different types in the wearable monitoring equipment, and are used for monitoring information of different positions such as wrist, waist and ankle respectively.
The positioning information backtracking refers to backtracking and analyzing positioning information recorded by wrist wearing equipment, patch type wearing equipment and ankle wearing equipment to generate a first positioning sequence, a second positioning sequence and a third positioning sequence; the first positioning sequence, the second positioning sequence and the third positioning sequence refer to sequences generated after backtracking positioning information of the wrist wearing device, the patch wearing device and the ankle wearing device, and can be used for representing a motion track and a motion state of a user in a certain time period.
The motion anomaly analysis refers to analyzing the motion state and track of a user by using a first positioning sequence, a second positioning sequence and a third positioning sequence to detect and identify whether motion anomalies such as falling exist or not and generate falling motion probability; the falling motion probability threshold is a preset threshold of falling motion probability, and when the falling motion probability is greater than or equal to the threshold, the falling motion probability means that the user falls.
The falling safety early warning signal is a safety early warning signal generated according to the positioning information of the user when the falling situation of the user is detected, and is used for sending an alarm to the adjacent mobile terminal so as to remind park managers in the park of the health care organization to take corresponding measures in time. Realize real-time monitoring and early warning function: when abnormal movement conditions such as abnormal positioning or falling occur, early warning signals can be timely generated and informed to park managers, so that the park managers take corresponding measures to ensure the safety of users, further the monitoring precision and reliability are improved, meanwhile, the conditions of missing report and false report are reduced, and therefore better safety guarantee is provided for the users.
Performing positioning abnormality analysis according to the wrist type wearable device positioning information, the patch type wearable device positioning information and the ground positioning information to generate positioning abnormality coefficients, wherein Step-3 comprises:
performing positioning height consistency verification on the wrist type wearable equipment positioning information and the patch type wearable equipment positioning information to generate positioning consistency;
when the positioning consistency is smaller than a positioning consistency threshold, setting the positioning anomaly coefficient to 0;
when the positioning consistency is greater than or equal to the positioning consistency threshold, calculating a first height difference of the wrist type wearable equipment positioning information and the ground positioning information, and calculating a second height difference of the patch type wearable equipment positioning information and the ground positioning information;
And obtaining the reciprocal of the mean value of the first height difference and the second height difference, and setting the reciprocal as the positioning anomaly coefficient.
Based on wrist wearing equipment, patch wearing equipment and ground positioning information, detecting and identifying abnormal conditions in the positioning process, wherein the wrist wearing equipment is intelligent equipment capable of being worn on a wrist, commonly known as a sports bracelet and has the functions of positioning and tracking the position of a user; the patch type wearable device is an intelligent device capable of being worn on the body, and generally has the functions of health monitoring, motion tracking, communication and payment, and is similar to a wrist type wearable device; ground positioning information generally refers to position information of the ground acquired by GPS or other positioning technology.
The positioning height consistency check is used for verifying whether the positioning information provided by the wrist type and patch type wearable equipment is consistent with the ground positioning information in height; the positioning consistency is a measurement value used for representing the consistency degree of the positioning information of the wrist type wearable equipment and the patch type wearable equipment and the ground positioning information.
The positioning consistency threshold is a set standard value, and when the positioning consistency is lower than the threshold, the positioning abnormality exists; conversely, when the positioning uniformity is greater than or equal to this threshold, it means that the positioning information may be uniform; the first and second height differences represent differences in height between the wrist and patch type wearable device and the ground positioning information. The positioning anomaly coefficient is a value obtained by the calculation process, and represents the reciprocal of the average value of the height difference between the positioning information of the wrist type and patch type wearable devices and the ground positioning information, and when the value is large, the existence of a large height difference, namely the existence of positioning anomaly, is indicated.
The height difference between the positioning information is calculated by comparing the consistency of the positioning information of the wrist type wearable device and the patch type wearable device with the ground positioning information, and the positioning information is applied to various scenes needing accurate position information, such as health monitoring, safety monitoring and the like, so that possible abnormal positioning conditions of user falling, user rolling and the like can be effectively detected.
As shown in fig. 2, performing location height consistency check on the wrist wearable device location information and the patch wearable device location information to generate location consistency, step-3 further includes:
the wrist wearing equipment positioning information comprises ankle wearing equipment positioning information and wrist wearing equipment positioning information;
the patch type wearable device positioning information comprises waist wearable device positioning information;
performing height difference analysis on the ankle wearing equipment positioning information and the waist wearing equipment positioning information to generate a fourth height difference;
performing height difference analysis on the wrist wearing equipment positioning information and the waist wearing equipment positioning information to generate a fifth height difference;
and setting the reciprocal of the fourth height difference or the fifth height difference as the positioning consistency.
The wrist wearing device comprises a wrist wearing device and an ankle wearing device, wherein the wrist wearing device positioning information refers to positioning information from the wrist wearing device, the ankle wearing device positioning information refers to positioning information from the ankle wearing device, and the height difference analysis is a method for measuring the distance difference between two or more positioning information in the vertical direction. Setting the reciprocal of the fourth height difference or the fifth height difference as the positioning consistency degree, wherein the positioning consistency degree is a measurement value used for measuring the consistency degree of the positioning information of the wrist type and patch type wearable equipment and the ground positioning information.
Reflecting whether the positioning information of the wrist-type and patch-type wearable devices is consistent with the ground positioning information, setting the reciprocal of the fourth and fifth height differences to be the positioning consistency degree means that when the height differences are smaller (i.e., the difference is smaller), the positioning consistency degree is higher, the positioning information of the wrist-type and patch-type wearable devices is consistent with the ground positioning information, effective data support and calibration can be provided for scenes requiring accurate position information, such as health monitoring, safety monitoring and the like, and meanwhile, an alarm or prompt can be timely sent out when the height differences are found to be too large (i.e., the positioning is inconsistent) so as to perform necessary adjustment or repair, thereby improving the accuracy and reliability of the overall positioning data.
When the positioning anomaly coefficient is greater than or equal to the positioning anomaly coefficient threshold, the communication wrist wearing device performs positioning information backtracking to generate a first positioning sequence, the communication patch wearing device performs positioning information backtracking to generate a second positioning sequence, the communication ankle wearing device performs positioning information backtracking to generate a third positioning sequence, and Step-4 further comprises:
when the positioning abnormal coefficient is greater than or equal to the positioning abnormal coefficient threshold value, acquiring the duration of the positioning abnormal state;
when the duration of the abnormal positioning state is greater than or equal to a duration threshold, generating a falling safety early warning signal based on user positioning information and sending the falling safety early warning signal to the adjacent mobile terminal;
when the duration of the abnormal positioning state is smaller than the duration threshold, constructing a positioning neighborhood range based on the user positioning information;
based on the positioning neighborhood range, the communication wrist wearable device performs positioning information backtracking to generate a first positioning sequence, the communication patch wearable device performs positioning information backtracking to generate a second positioning sequence, and the communication ankle wearable device performs positioning information backtracking to generate a third positioning sequence.
When the positioning anomaly coefficient exceeds or equals to a preset threshold value, and the duration of the anomaly state is long, the early warning is directly carried out, wherein the positioning anomaly coefficient represents the reciprocal of the average value of the height difference between the positioning information of the wrist type wearable equipment and the patch type wearable equipment and the ground positioning information, and when the numerical value of the positioning anomaly coefficient is too large, the existence of the large height difference is indicated, namely the positioning anomaly exists.
The locating abnormal state duration is the duration of the locating abnormal state duration; the duration threshold is a preset time length value, and when the duration of the abnormal positioning state exceeds or is equal to the threshold, the early warning operation is triggered; the falling safety early warning signal is an emergency signal which is automatically sent to an adjacent mobile terminal when the falling and the rolling of the user are detected, and the adjacent mobile terminal can be a telephone area number+emergency telephone where an area is or a contact mode close to an emergency center;
when the positioning abnormality coefficient exceeds or equals to the threshold value, it can be judged that positioning abnormality exists, and the duration of the positioning abnormality state can be obtained: if the duration exceeds the preset duration threshold, a fall safety early warning signal is generated based on the positioning information of the user and sent to the adjacent mobile terminal so as to remind relevant personnel to pay attention and take necessary measures.
If the duration of the abnormal locating state does not exceed the duration threshold, the user is indicated to be free from the falling state in a short time, a locating neighborhood range is constructed based on the locating information of the user, and the locating neighborhood range can be used for judging an activity path or a behavior mode of the user in a specific time period.
Positioning information can be obtained from the wrist, patch and ankle wearable devices respectively, and first, second and third positioning sequences are generated, so that more detailed and comprehensive user position information can be provided to support higher-level analysis and application, for example, the motion trail and behavior pattern of a user can be analyzed through the sequences, or the falling situation of the user can be further judged, including stair falling situation and step falling situation. The system can effectively monitor and early warn the falling situation of the user, simultaneously provide detailed positioning information to support higher-level analysis and application, and can be applied to various scenes needing accurate position information and personal safety early warning, such as elderly care, employee safety monitoring and the like.
According to the first positioning sequence, the second positioning sequence and the third positioning sequence, motion anomaly analysis is performed to generate falling motion probability, and Step-5 further comprises:
fitting human motion states based on the first positioning sequence, the second positioning sequence and the third positioning sequence to generate a human body simulation gesture sequence;
determining an action change acceleration based on the first positioning sequence, the second positioning sequence, and the third positioning sequence;
And activating a motion abnormality analysis module embedded in the server to analyze the human body simulation gesture sequence and the motion change acceleration to generate the falling motion probability.
The actions which can simultaneously accord with the first positioning sequence, the second positioning sequence and the third positioning sequence are limited, the action sequences which accord with the three positioning sequences can be extracted and the action sequence which accords with the positioning sequence is selected from the action sequences by carrying out positioning adjustment on joints of a human body, wherein the first positioning sequence, the second positioning sequence and the third positioning sequence are positioning information sequences obtained from wrist type, patch type and ankle wearing equipment;
the human motion state fitting refers to simulating and predicting the state of human motion by using a first positioning sequence, a second positioning sequence and a third positioning sequence, the human simulation gesture sequence refers to a sequence which is generated according to the first positioning sequence, the second positioning sequence and the third positioning sequence and represents the human motion gesture through a fitting algorithm, specifically, a model suitable for human motion gesture recognition, such as a circulatory neural network (RNN), is selected, training is performed respectively based on positioning sequences corresponding to common human motion gestures in a jogging state, a standing state, a walking state and the like, and the human motion gesture can be accurately recognized by adjusting model parameters, so that a human motion gesture recognition model is finally obtained.
Extracting action sequences conforming to the three positioning sequences, inputting the action sequences conforming to the three positioning sequences into the human body motion gesture recognition model, and recognizing the action sequences conforming to the positioning sequences most in the human body motion gesture recognition model, wherein the action change acceleration refers to the change speed and intensity of the human body gesture or action in the motion process; the motion anomaly analysis module embedded in the server side of the human motion gesture recognition model is a module which runs in the server and is specially used for analyzing the motion state of the human body; the probability of fall motion represents a value of the likelihood of a human falling.
By analyzing the human body simulation gesture sequence and the action change acceleration, the falling motion probability can be obtained. The analysis process can detect and identify abnormal motion states of the human body, such as falling or tumbling, and provide corresponding early warning or notification. Through real-time monitoring and analysis, the method is applied to various scenes needing to monitor the motion state and safety of the human body, such as the care of the elderly, the training of athletes, the safety monitoring of factories and the like, and can timely discover and process potential safety risks, thereby improving the overall safety and life quality.
Activating a motion anomaly analysis module embedded in a server to analyze the human body simulation gesture sequence and the motion change acceleration to generate the falling motion probability, wherein Step-5 further comprises:
The motion abnormality analysis module comprises an iteration template matching channel and a falling analysis channel;
extracting an iterative action sequence table based on the iterative template matching channel, and performing similarity evaluation with the human body simulation gesture sequence to generate an action similarity coefficient;
based on the falling analysis channel, extracting falling acceleration vectors of iterative action sequences with the action similarity coefficient larger than or equal to the action similarity coefficient threshold value, and performing deviation analysis on the falling acceleration vectors and the action change acceleration to generate acceleration deviation;
and setting the falling motion probability to 1 when the acceleration deviation is smaller than or equal to an acceleration deviation threshold value, otherwise setting the falling motion probability to 0.
The motion abnormality analysis module is a module specially used for analyzing the motion state of a human body and comprises an iteration template matching channel and a falling analysis channel; the iterative template matching channel is one channel in the motion anomaly analysis module and is used for carrying out template matching on the action sequence in an iterative mode, extracting an iterative action sequence and carrying out similarity evaluation; the fall analysis channel refers to another channel in the motion abnormality analysis module, which is used for analyzing an action sequence which may cause a fall.
The iterative action sequence table refers to an iterative action sequence extracted from an iterative template matching channel and can be used for carrying out similarity evaluation with a human body simulation gesture sequence; the action similarity coefficient is a numerical value which is generated through iterative template matching channel similarity evaluation and represents the similarity degree of the action sequence; the fall acceleration vector is an acceleration vector of an action sequence extracted from a fall analysis channel and possibly causing a fall.
The acceleration deviation is a numerical value representing the degree of deviation between acceleration vectors, which is generated by performing deviation analysis with the motion change acceleration; the falling motion probability is a numerical value which is generated by analyzing a human body simulation gesture sequence and an action change acceleration and represents the falling possibility.
By activating a motion abnormality analysis module embedded in a server, analyzing a human body simulation gesture sequence and motion change acceleration to generate falling motion probability; the iterative template matching channel can extract iterative action sequences, evaluate the similarity, generate action similarity coefficients and evaluate the similarity degree of the human body simulation gesture sequences and the iterative action sequences; the falling analysis channel can extract acceleration vectors of the action sequences possibly causing falling, and performs deviation analysis on the acceleration vectors and the action change acceleration to generate acceleration deviation, and the deviation degree between the change acceleration of the human body simulation gesture sequences and the acceleration vectors causing falling is estimated; and when the acceleration deviation is smaller than or equal to the acceleration deviation threshold value, setting the falling motion probability to be 1, otherwise, setting the falling motion probability to be 0, and judging whether the human body possibly falls according to the magnitude of the acceleration deviation. In general, the human body simulation gesture sequence and the action change acceleration are effectively analyzed, the falling motion probability is generated, corresponding early warning or notification is provided, and the method is applied to various scenes in which the human body motion state and safety need to be monitored.
Based on the iterative template matching channel, extracting an iterative action sequence table, performing similarity evaluation with the human body simulation gesture sequence, generating action similarity coefficients, and Step-5 further comprises:
constructing first human body posture information and second human body posture information to carry out similarity coefficient identification, and generating a human body posture similarity coefficient identification result;
based on a convolutional neural network, performing similarity coefficient mapping on the first human body posture information and the second human body posture information, and evaluating mapping output accuracy by using the human body posture similarity coefficient identification result;
when the mapping output accuracy continuously preset times meet the preset output accuracy, generating a similarity coefficient evaluation function;
synchronizing the first iterative action sequence and the human body simulation gesture sequence of the iterative action sequence table to the similarity coefficient evaluation function for mapping to generate a plurality of gesture similarity coefficients;
and counting the gesture quantity proportion of the gesture similarity coefficients which are larger than or equal to the gesture similarity coefficient threshold value, and setting the gesture quantity proportion as the action similarity coefficient.
Meanwhile, the actions conforming to the first positioning sequence, the second positioning sequence and the third positioning sequence are limited, and the action sequences conforming to the three positioning sequences can be extracted by positioning and adjusting the joints of the human body, and specifically comprise the following steps: extracting an iterative action sequence table through an iterative template matching channel, performing similarity evaluation with a human body simulation gesture sequence, and generating an action similarity coefficient, wherein the iterative template matching channel refers to one channel in a motion anomaly analysis module and is used for performing template matching on the action sequence in an iterative mode to extract an iterative action sequence; the human body posture information refers to data representing the human body posture, including body posture, motion, and the like; the first human body posture information and the second human body posture information refer to two different human body posture information to be compared; the similarity coefficient identification means that the first human body posture information and the second human body posture information are compared, the similarity degree between the first human body posture information and the second human body posture information is evaluated, and an identification result is generated.
The convolutional neural network is a deep learning algorithm, and is commonly used for processing data such as images and the like, and learning and extracting features from the data; the similarity coefficient mapping means that the first human body posture information and the second human body posture information are mapped into the same feature space through a convolutional neural network so as to be compared and evaluated; the similarity coefficient evaluation function is a function which is generated based on the mapping output accuracy and is used for evaluating the human posture similarity coefficient; the iterative action sequence list refers to an iterative action sequence list extracted from the iterative template matching channel.
The gesture similarity coefficient is a numerical value which is calculated through a similarity coefficient evaluation function and represents the similarity degree between the human body simulation gesture sequence and the iterative action sequence; the action similarity coefficient is a numerical value which is obtained by counting the number of postures with a plurality of posture similarity coefficients being larger than or equal to a posture similarity coefficient threshold value and represents the overall similarity degree between the human body simulation posture sequence and the iterative action sequence.
The similarity degree between the first human body posture information and the second human body posture information can be quantitatively evaluated by constructing the first human body posture information and the second human body posture information to carry out similarity coefficient identification; the similarity coefficient mapping can be carried out on the first human body posture information and the second human body posture information based on the convolutional neural network, and the accuracy of similarity assessment is improved by assessing the mapping output accuracy; when the mapping output accuracy continuously preset times meet the preset output accuracy, a similarity coefficient evaluation function can be generated and used for evaluating the human body posture similarity coefficient; synchronizing a first iterative action sequence and a human body simulation gesture sequence of the iterative action sequence table to a similarity coefficient evaluation function for mapping, so that a plurality of gesture similarity coefficients can be generated; by counting the gesture number proportion that the gesture similarity coefficients are greater than or equal to the gesture similarity coefficient threshold, the action similarity coefficients can be obtained and used for representing the overall similarity degree between the human body simulation gesture sequence and the iterative action sequence.
In general, the method can effectively extract the iterative action sequence, evaluate the similarity with the human body simulation gesture sequence, generate action similarity coefficients, provide corresponding motion state evaluation and early warning functions, and be applied to various scenes needing to monitor the motion state and safety of the human body.
In summary, the user safety intelligent monitoring method based on the wearable monitoring device provided by the embodiment of the application has the following technical effects:
1. through the real-time monitoring of the wearable equipment, the safety risk of the user can be discovered at the first time, and corresponding measures are taken for intervention and prevention.
2. The wearable equipment is utilized for data acquisition, so that the time and labor cost of data processing and analysis can be greatly reduced, and the working efficiency is improved.
3. The customized equipment configuration and data processing analysis are carried out according to different scenes and requirements, and the method has high flexibility and expansibility.
4. The motion abnormality analysis module comprises an iteration template matching channel and a falling analysis channel; based on the iterative template matching channel, extracting an iterative action sequence table, and carrying out similarity evaluation with the human body simulation gesture sequence to generate an action similarity coefficient; based on the falling analysis channel, extracting falling acceleration vectors of iterative action sequences with action similarity coefficients greater than or equal to action similarity coefficient threshold values, performing deviation analysis on the falling acceleration vectors and action change acceleration, and generating acceleration deviation; and setting the falling motion probability to 1 when the acceleration deviation is smaller than or equal to the acceleration deviation threshold value, otherwise setting the falling motion probability to 0. The human body simulation gesture sequence and the action change acceleration are effectively analyzed, the falling motion probability is generated, corresponding early warning or notification is provided, and the human body simulation gesture sequence and the action change acceleration are applied to various scenes needing to monitor the human body motion state and safety.
Example two
Based on the same inventive concept as the user safety intelligent monitoring method based on the wearable monitoring device in the foregoing embodiment, as shown in fig. 3, an embodiment of the present application provides a user safety intelligent monitoring system based on the wearable monitoring device, where the system includes a server and a mobile terminal, the system is in communication connection with the wearable monitoring device, the wearable monitoring device includes a wrist wearable device and a patch wearable device, and the system includes:
the digital modeling module 100 is configured to digitally model the first campus to generate a digital twin park, wear the wrist type wearable device on the wrist of the user, and wear the patch type wearable device on the waist of the user;
the feature information extraction module 200 is configured to communicate with a wearable monitoring device, receive fitting of user positioning information in the digital twin park, and extract environmental feature information, where the environmental feature information includes wrist type wearable device positioning information, patch type wearable device positioning information, and ground positioning information;
the positioning anomaly analysis module 300 is configured to perform positioning anomaly analysis according to the wrist wearable device positioning information, the patch wearable device positioning information and the ground positioning information, and generate a positioning anomaly coefficient;
The positioning information backtracking module 400 is configured to perform positioning information backtracking on the communication wrist wearable device to generate a first positioning sequence, perform positioning information backtracking on the communication patch wearable device to generate a second positioning sequence, and perform positioning information backtracking on the communication ankle wearable device to generate a third positioning sequence when the positioning anomaly coefficient is greater than or equal to a positioning anomaly coefficient threshold;
the motion anomaly analysis module 500 is configured to perform motion anomaly analysis according to the first positioning sequence, the second positioning sequence, and the third positioning sequence, and generate a falling motion probability;
the signal sending module 600 is configured to generate a fall safety early warning signal based on the user positioning information and send the fall safety early warning signal to a neighboring mobile terminal when the fall motion probability is greater than or equal to a fall motion probability threshold, where the neighboring mobile terminal is worn by a campus manager.
Further, the positioning anomaly analysis module 300 is configured to perform the following steps:
performing positioning height consistency verification on the wrist type wearable equipment positioning information and the patch type wearable equipment positioning information to generate positioning consistency;
when the positioning consistency is smaller than a positioning consistency threshold, setting the positioning anomaly coefficient to 0;
When the positioning consistency is greater than or equal to the positioning consistency threshold, calculating a first height difference of the wrist type wearable equipment positioning information and the ground positioning information, and calculating a second height difference of the patch type wearable equipment positioning information and the ground positioning information;
and obtaining the reciprocal of the mean value of the first height difference and the second height difference, and setting the reciprocal as the positioning anomaly coefficient.
Further, the positioning anomaly analysis module 300 is further configured to perform the following steps:
the wrist wearing equipment positioning information comprises ankle wearing equipment positioning information and wrist wearing equipment positioning information;
the patch type wearable device positioning information comprises waist wearable device positioning information;
performing height difference analysis on the ankle wearing equipment positioning information and the waist wearing equipment positioning information to generate a fourth height difference;
performing height difference analysis on the wrist wearing equipment positioning information and the waist wearing equipment positioning information to generate a fifth height difference;
and setting the reciprocal of the fourth height difference or the fifth height difference as the positioning consistency.
Further, the location information backtracking module 400 is configured to perform the following steps:
When the positioning abnormal coefficient is greater than or equal to the positioning abnormal coefficient threshold value, acquiring the duration of the positioning abnormal state;
when the duration of the abnormal positioning state is greater than or equal to a duration threshold, generating a falling safety early warning signal based on user positioning information and sending the falling safety early warning signal to the adjacent mobile terminal;
when the duration of the abnormal positioning state is smaller than the duration threshold, constructing a positioning neighborhood range based on the user positioning information;
based on the positioning neighborhood range, the communication wrist wearable device performs positioning information backtracking to generate a first positioning sequence, the communication patch wearable device performs positioning information backtracking to generate a second positioning sequence, and the communication ankle wearable device performs positioning information backtracking to generate a third positioning sequence.
Further, the motion anomaly analysis module 500 is configured to perform the following steps:
fitting human motion states based on the first positioning sequence, the second positioning sequence and the third positioning sequence to generate a human body simulation gesture sequence;
determining an action change acceleration based on the first positioning sequence, the second positioning sequence, and the third positioning sequence;
and activating a motion abnormality analysis module embedded in the server to analyze the human body simulation gesture sequence and the motion change acceleration to generate the falling motion probability.
Further, the motion anomaly analysis module 500 is further configured to perform the following steps:
the motion abnormality analysis module comprises an iteration template matching channel and a falling analysis channel;
extracting an iterative action sequence table based on the iterative template matching channel, and performing similarity evaluation with the human body simulation gesture sequence to generate an action similarity coefficient;
based on the falling analysis channel, extracting falling acceleration vectors of iterative action sequences with the action similarity coefficient larger than or equal to the action similarity coefficient threshold value, and performing deviation analysis on the falling acceleration vectors and the action change acceleration to generate acceleration deviation;
and setting the falling motion probability to 1 when the acceleration deviation is smaller than or equal to an acceleration deviation threshold value, otherwise setting the falling motion probability to 0.
Further, the motion anomaly analysis module 500 is further configured to perform the following steps:
constructing first human body posture information and second human body posture information to carry out similarity coefficient identification, and generating a human body posture similarity coefficient identification result;
based on a convolutional neural network, performing similarity coefficient mapping on the first human body posture information and the second human body posture information, and evaluating mapping output accuracy by using the human body posture similarity coefficient identification result;
When the mapping output accuracy continuously preset times meet the preset output accuracy, generating a similarity coefficient evaluation function;
synchronizing the first iterative action sequence and the human body simulation gesture sequence of the iterative action sequence table to the similarity coefficient evaluation function for mapping to generate a plurality of gesture similarity coefficients;
and counting the gesture quantity proportion of the gesture similarity coefficients which are larger than or equal to the gesture similarity coefficient threshold value, and setting the gesture quantity proportion as the action similarity coefficient.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any method for implementing an embodiment of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. The user safety intelligent monitoring method based on the wearable monitoring equipment is characterized by being applied to a user safety intelligent monitoring system, wherein the system comprises a service end and a mobile terminal, the system is in communication connection with the wearable monitoring equipment, the wearable monitoring equipment comprises wrist wearing equipment and patch wearing equipment, and the service end executing steps comprise:
carrying out digital modeling on the first park to generate a digital twin park, wearing wrist wearing equipment on the wrist of a user, and wearing patch wearing equipment on the waist of the user;
the communication wearable monitoring equipment is used for receiving fitting of user positioning information in the digital twin park and extracting environment characteristic information, wherein the environment characteristic information comprises wrist type wearable equipment positioning information, patch type wearable equipment positioning information and ground positioning information;
performing positioning abnormality analysis according to the wrist type wearable equipment positioning information, the patch type wearable equipment positioning information and the ground positioning information to generate a positioning abnormality coefficient;
when the positioning anomaly coefficient is greater than or equal to a positioning anomaly coefficient threshold value, the communication wrist wearing equipment performs positioning information backtracking to generate a first positioning sequence, the communication patch wearing equipment performs positioning information backtracking to generate a second positioning sequence, and the communication ankle wearing equipment performs positioning information backtracking to generate a third positioning sequence;
Performing motion anomaly analysis according to the first positioning sequence, the second positioning sequence and the third positioning sequence to generate falling motion probability;
and when the falling motion probability is greater than or equal to a falling motion probability threshold value, generating a falling safety early warning signal based on the user positioning information and sending the falling safety early warning signal to a neighboring mobile terminal, wherein the neighboring mobile terminal is worn by a park manager.
2. The method of claim 1, wherein performing a positioning anomaly analysis based on the wrist-worn device positioning information, the patch-worn device positioning information, and the ground positioning information, generating a positioning anomaly coefficient comprises:
performing positioning height consistency verification on the wrist type wearable equipment positioning information and the patch type wearable equipment positioning information to generate positioning consistency;
when the positioning consistency is smaller than a positioning consistency threshold, setting the positioning anomaly coefficient to 0;
when the positioning consistency is greater than or equal to the positioning consistency threshold, calculating a first height difference of the wrist type wearable equipment positioning information and the ground positioning information, and calculating a second height difference of the patch type wearable equipment positioning information and the ground positioning information;
And obtaining the reciprocal of the mean value of the first height difference and the second height difference, and setting the reciprocal as the positioning anomaly coefficient.
3. The method of claim 2, wherein performing location height consistency verification on the wrist-worn device location information and the patch-worn device location information to generate a location consistency comprises:
the wrist wearing equipment positioning information comprises ankle wearing equipment positioning information and wrist wearing equipment positioning information;
the patch type wearable device positioning information comprises waist wearable device positioning information;
performing height difference analysis on the ankle wearing equipment positioning information and the waist wearing equipment positioning information to generate a fourth height difference;
performing height difference analysis on the wrist wearing equipment positioning information and the waist wearing equipment positioning information to generate a fifth height difference;
and setting the reciprocal of the fourth height difference or the fifth height difference as the positioning consistency.
4. The method of claim 1, wherein when the positioning anomaly coefficient is greater than or equal to a positioning anomaly coefficient threshold, the communications wrist-worn device performs positioning information backtracking, generating a first positioning sequence, the communications patch-worn device performs positioning information backtracking, generating a second positioning sequence, the communications ankle-worn device performs positioning information backtracking, generating a third positioning sequence, comprising:
When the positioning abnormal coefficient is greater than or equal to the positioning abnormal coefficient threshold value, acquiring the duration of the positioning abnormal state;
when the duration of the abnormal positioning state is greater than or equal to a duration threshold, generating a falling safety early warning signal based on user positioning information and sending the falling safety early warning signal to the adjacent mobile terminal;
when the duration of the abnormal positioning state is smaller than the duration threshold, constructing a positioning neighborhood range based on the user positioning information;
based on the positioning neighborhood range, the communication wrist wearable device performs positioning information backtracking to generate a first positioning sequence, the communication patch wearable device performs positioning information backtracking to generate a second positioning sequence, and the communication ankle wearable device performs positioning information backtracking to generate a third positioning sequence.
5. The method of claim 1, wherein performing motion anomaly resolution from the first, second, and third positioning sequences, generating a fall motion probability, comprises:
fitting human motion states based on the first positioning sequence, the second positioning sequence and the third positioning sequence to generate a human body simulation gesture sequence;
Determining an action change acceleration based on the first positioning sequence, the second positioning sequence, and the third positioning sequence;
and activating a motion abnormality analysis module embedded in the server to analyze the human body simulation gesture sequence and the motion change acceleration to generate the falling motion probability.
6. The method of claim 5, wherein activating a motion anomaly analysis module embedded in a server side, analyzing the human body simulated gesture sequence and the motion change acceleration, generating the fall motion probability, comprises:
the motion abnormality analysis module comprises an iteration template matching channel and a falling analysis channel;
extracting an iterative action sequence table based on the iterative template matching channel, and performing similarity evaluation with the human body simulation gesture sequence to generate an action similarity coefficient;
based on the falling analysis channel, extracting falling acceleration vectors of iterative action sequences with the action similarity coefficient larger than or equal to the action similarity coefficient threshold value, and performing deviation analysis on the falling acceleration vectors and the action change acceleration to generate acceleration deviation;
and setting the falling motion probability to 1 when the acceleration deviation is smaller than or equal to an acceleration deviation threshold value, otherwise setting the falling motion probability to 0.
7. The method of claim 6, wherein extracting an iterative action sequence table based on the iterative template matching channel, performing similarity assessment with the human simulated pose sequence, generating action similarity coefficients, comprises:
constructing first human body posture information and second human body posture information to carry out similarity coefficient identification, and generating a human body posture similarity coefficient identification result;
based on a convolutional neural network, performing similarity coefficient mapping on the first human body posture information and the second human body posture information, and evaluating mapping output accuracy by using the human body posture similarity coefficient identification result;
when the mapping output accuracy continuously preset times meet the preset output accuracy, generating a similarity coefficient evaluation function;
synchronizing the first iterative action sequence and the human body simulation gesture sequence of the iterative action sequence table to the similarity coefficient evaluation function for mapping to generate a plurality of gesture similarity coefficients;
and counting the gesture quantity proportion of the gesture similarity coefficients which are larger than or equal to the gesture similarity coefficient threshold value, and setting the gesture quantity proportion as the action similarity coefficient.
8. A user safety intelligent monitoring system based on a wearable monitoring device, characterized by being used for implementing the user safety intelligent monitoring method based on the wearable monitoring device according to any one of claims 1-7, wherein the system is in communication connection with the wearable monitoring device, and the wearable monitoring device comprises a wrist wearing device and a patch wearing device, and comprises:
The digital modeling module is used for carrying out digital modeling on the first park to generate a digital twin park, wearing the wrist type wearing equipment on the wrist of the user, and wearing the patch type wearing equipment on the waist of the user;
the characteristic information extraction module is used for communicating the wearable monitoring equipment, receiving fitting of user positioning information in the digital twin park, and extracting environment characteristic information, wherein the environment characteristic information comprises wrist type wearable equipment positioning information, patch type wearable equipment positioning information and ground positioning information;
the positioning abnormality analysis module is used for performing positioning abnormality analysis according to the wrist type wearable equipment positioning information, the patch type wearable equipment positioning information and the ground positioning information to generate a positioning abnormality coefficient;
the positioning information backtracking module is used for carrying out positioning information backtracking on the communication wrist wearing equipment to generate a first positioning sequence, carrying out positioning information backtracking on the communication patch wearing equipment to generate a second positioning sequence, carrying out positioning information backtracking on the communication ankle wearing equipment to generate a third positioning sequence when the positioning abnormal coefficient is larger than or equal to the positioning abnormal coefficient threshold;
the motion anomaly analysis module is used for performing motion anomaly analysis according to the first positioning sequence, the second positioning sequence and the third positioning sequence to generate falling motion probability;
A signal sending module for generating a fall safety early warning signal based on the user positioning information and sending the fall safety early warning signal to the adjacent mobile terminal when the fall motion probability is larger than or equal to a fall motion probability threshold value,
the proximity mobile terminal is worn by a campus manager.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311337662.3A CN117158955A (en) | 2023-10-17 | 2023-10-17 | User safety intelligent monitoring method based on wearable monitoring equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311337662.3A CN117158955A (en) | 2023-10-17 | 2023-10-17 | User safety intelligent monitoring method based on wearable monitoring equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117158955A true CN117158955A (en) | 2023-12-05 |
Family
ID=88943323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311337662.3A Pending CN117158955A (en) | 2023-10-17 | 2023-10-17 | User safety intelligent monitoring method based on wearable monitoring equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117158955A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117594253A (en) * | 2024-01-18 | 2024-02-23 | 山东鑫年信息科技有限公司 | Personnel health early warning method and system based on intelligent monitoring equipment |
-
2023
- 2023-10-17 CN CN202311337662.3A patent/CN117158955A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117594253A (en) * | 2024-01-18 | 2024-02-23 | 山东鑫年信息科技有限公司 | Personnel health early warning method and system based on intelligent monitoring equipment |
| CN117594253B (en) * | 2024-01-18 | 2024-05-28 | 山东鑫年信息科技有限公司 | Personnel health early warning method and system based on intelligent monitoring equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Fall detection based on dual-channel feature integration | |
| CN104038738B (en) | Intelligent monitoring system and intelligent monitoring method for extracting coordinates of human body joint | |
| Yu et al. | Posture-related data collection methods for construction workers: A review | |
| CN110502965A (en) | A kind of construction safety helmet wearing monitoring method based on the estimation of computer vision human body attitude | |
| CN106580282A (en) | Human body health monitoring device, system and method | |
| CN111126153B (en) | Safety monitoring method, system, server and storage medium based on deep learning | |
| CN117158955A (en) | User safety intelligent monitoring method based on wearable monitoring equipment | |
| CN104966327A (en) | System and method for monitoring health and registering attendance on basis of internet of things | |
| CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
| CN110717542A (en) | Emotion recognition method, device and equipment | |
| Balamurugan et al. | Wearables to improve efficiency, productivity, and safety of operations | |
| CN113397520A (en) | Information detection method and device for indoor object, storage medium and processor | |
| CN112270807A (en) | Old man early warning system that tumbles | |
| Kelly et al. | Automatic prediction of health status using smartphone-derived behavior profiles | |
| Li et al. | Collaborative fall detection using smart phone and Kinect | |
| Hemmatpour et al. | Nonlinear Predictive Threshold Model for Real‐Time Abnormal Gait Detection | |
| CN111603750A (en) | Motion capture recognition evaluation system and method based on edge calculation | |
| Xia et al. | [Retracted] Gesture Tracking and Recognition Algorithm for Dynamic Human Motion Using Multimodal Deep Learning | |
| CN113569671A (en) | Abnormal behavior alarm method and device | |
| CN116580359A (en) | Construction personnel severe fatigue detection system and method based on space-time characteristics | |
| De et al. | Fall detection approach based on combined two-channel body activity classification for innovative indoor environment | |
| CN115410113A (en) | Fall detection method and device based on computer vision and storage medium | |
| CN110135744B (en) | Construction worker safety behavior habit evaluation method | |
| CN113255462A (en) | Gait scoring method, system, computer program product and readable storage medium | |
| CN111028339A (en) | Behavior action modeling method and device, electronic equipment and storage medium |
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 |