CN115910341B - Exercise health monitoring method, device and medium - Google Patents
Exercise health monitoring method, device and medium Download PDFInfo
- Publication number
- CN115910341B CN115910341B CN202211534573.3A CN202211534573A CN115910341B CN 115910341 B CN115910341 B CN 115910341B CN 202211534573 A CN202211534573 A CN 202211534573A CN 115910341 B CN115910341 B CN 115910341B
- Authority
- CN
- China
- Prior art keywords
- motion
- health monitoring
- user
- monitoring equipment
- actual
- 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.)
- Active
Links
- 230000036541 health Effects 0.000 title claims abstract description 168
- 238000012544 monitoring process Methods 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000033001 locomotion Effects 0.000 claims abstract description 219
- 238000012806 monitoring device Methods 0.000 claims description 57
- 239000013598 vector Substances 0.000 claims description 30
- 230000008569 process Effects 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 8
- 230000000386 athletic effect Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000000977 initiatory effect Effects 0.000 claims description 4
- 239000012634 fragment Substances 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 description 18
- 238000004590 computer program Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 210000000988 bone and bone Anatomy 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000036772 blood pressure Effects 0.000 description 2
- 230000036387 respiratory rate Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000035487 diastolic blood pressure Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 210000003414 extremity Anatomy 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 230000035488 systolic blood pressure Effects 0.000 description 1
- 210000000689 upper leg Anatomy 0.000 description 1
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a method, a device and a medium for monitoring sports health, which comprise the following steps: receiving actual physiological data and actual movement data of a user; acquiring a user ID, and searching to obtain a preset motion scheme matched with the user ID; dividing actual motion data based on motion types, and comparing partial motion data under each motion type with preset motion data of a corresponding type to obtain an actual motion state of a user; and calling preset physiological data matched with the actual motion state, and comparing the preset physiological data with the actual physiological data to obtain a health state monitoring result of the user. According to the invention, the preset exercise scheme can be customized for each user according to the different physical conditions of the users, and when the actual exercise state of the user is inconsistent with the preset exercise scheme, the exercise state of the user is considered to have health risks, so that personalized monitoring of the exercise states of different users is realized, and the monitoring result is more accurate.
Description
Technical Field
The invention belongs to the technical field of sports health monitoring, and particularly relates to a sports health monitoring method, a sports health monitoring device and a sports health monitoring medium.
Background
With economic development and social progress and promotion of health consciousness of people, daily health care becomes an indispensable part of life of many people, and therefore, portable health monitoring devices are widely used in life of people.
However, in the prior art, when health monitoring is performed on the motion state of people based on portable health equipment, various physiological data of users are generally simply collected, and the actual physiological data are compared with the standard physiological data range, so that the health state of the users is judged according to the comparison result. However, the normal physiological data of different users may be different, and the motion states adapted to different objects may also be different, and the existing motion health monitoring method cannot perform personalized motion health monitoring for each user, so that the monitoring result is not accurate enough.
Disclosure of Invention
The invention aims to provide a method, a device and a medium for monitoring sports health, which are used for solving the technical problem that the monitoring result is inaccurate because the conventional sports health monitoring method cannot perform personalized sports health monitoring for each user in the prior art.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a first aspect provides a method of athletic health monitoring, comprising:
receiving actual physiological data and actual movement data of a user in a movement process, which are sent by health monitoring equipment;
acquiring a user ID carried by the health monitoring equipment during data transmission, and searching to obtain a preset motion scheme matched with the user ID, wherein the preset motion scheme comprises preset physiological data and a motion state matched with the preset physiological data;
dividing the actual motion data based on the motion types, and comparing part of the motion data under each motion type with the preset motion data of the corresponding type to obtain the actual motion state of the user;
and calling preset physiological data matched with the actual motion state, and comparing the preset physiological data with the actual physiological data to obtain a health state monitoring result of the user.
In one possible design, before receiving the actual physiological data and the actual movement data of the user during the movement sent by the health monitoring device, the method further comprises:
and generating a corresponding user ID for the health monitoring equipment according to the user basic information sent by the health monitoring equipment, signing the user ID and returning the user ID to the health monitoring equipment.
In one possible design, before generating the corresponding user ID for the health monitoring device according to the user basic information sent by the health monitoring device, the method further includes:
initiating TCP connection to the health monitoring equipment through a preset guide node, and carrying out callback connection on the IP address of the health monitoring equipment, so as to judge the accessibility of the IP address of the health monitoring equipment;
if the callback connection is successful, randomly sending a hash problem to the health monitoring equipment through a preset guide node;
and receiving the solution of the hash problem by the health monitoring equipment, verifying the correctness of the solution, and if the answer is correct, establishing effective connection with the health monitoring equipment.
In one possible design, the segmenting the actual motion data based on the motion type includes:
processing the actual motion data into a motion sequence comprising a series of pose frames;
defining sliding windows of the motion sequences, and calculating cosine similarity among motion sequence fragments in each sliding window to construct a similarity curve of the motion sequences;
detecting the dividing points in the similarity curve, and dividing the similarity curve based on the detected dividing points to obtain partial motion data under each motion type; wherein the partition point is a minimum value of the similarity curve.
In one possible design, defining a sliding window of the motion sequence includes:
for moving sequencesSetting sliding window->The sliding window->The expression of (2) is as follows:
；（1）
；（2）
wherein,sequence number representing current window, ">Representing the motion sequence contained in the current window +.>The first of (3)Frame pose->Representing a movement sequence +.>The number of frames involved, ">The size of each sliding window is represented, and each sliding step of the sliding window is set to 1 frame.
In one possible design, calculating cosine similarity between motion sequence segments in each sliding window to construct a similarity curve for the motion sequence includes:
and calculating cosine similarity between the first motion sequence segment and the second motion sequence segment in each sliding window, wherein the calculation formula is as follows:
；（3）
wherein,feature vectors representing segments of the first motion sequence, < >>A feature vector representing a second motion sequence segment;
according to the calculation results of a plurality of cosine similarity, constructing and obtaining the motion sequenceIs a similarity curve of (2).
In one possible design, the feature vectors of the first motion sequence segmentThe extraction process of (2) is as follows:
calculating a histogram vector of each characteristic parameter in the first motion sequence segment, wherein the characteristic parameter is an included angle between every two joint points, and a calculation formula is as follows:
；（4）
；（5）
wherein,representing the number of frames comprised by the first motion sequence segment, is->Representing the +.sup.th in the first motion sequence segment>Histogram vector of individual angles +_>Indicate->Angle->Fall within the interval->Frequency of internal, ->Representing the number of sub-intervals dividing the value interval of the angle,/->Wherein the value interval of each included angle is +.>；
Connecting the histogram vectors of the characteristic parameters end to obtain the characteristic vector of the first motion sequence segment。
In one possible design, detecting the segmentation point in the similarity curve includes:
and detecting the dividing points in the similarity curve by adopting a curve simplification algorithm.
A second aspect provides a sports health monitoring device comprising:
the data receiving module is used for receiving actual physiological data and actual movement data of a user in the movement process, which are sent by the health monitoring equipment;
the ID matching module is used for acquiring a user ID carried by the health monitoring equipment during data transmission, and searching to obtain a preset exercise scheme matched with the user ID, wherein the preset exercise scheme comprises preset physiological data and an exercise state matched with the preset physiological data;
the state acquisition module is used for dividing the actual motion data based on the motion types, and comparing part of motion data under each motion type with preset motion data of the corresponding type to obtain the actual motion state of the user;
and the result acquisition module is used for calling preset physiological data matched with the actual motion state, and comparing the preset physiological data with the actual physiological data to obtain a health state monitoring result of the user.
A third aspect provides a computer readable storage medium having instructions stored thereon which, when run on a computer, perform the method of athletic health monitoring as described in any one of the possible designs of the first aspect.
A fourth aspect provides a computer device comprising a memory, a processor and a transceiver in communication with each other in sequence, wherein the memory is adapted to store a computer program and the transceiver is adapted to send and receive messages, and the processor is adapted to read the computer program and to perform the method of sports health monitoring as described in any one of the possible designs of the first aspect.
A fifth aspect provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of sports health monitoring as described in any one of the possible designs of the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the user ID carried in the data transmission process is obtained while the actual physiological data and the actual movement data transmitted by the health monitoring equipment are received, and the preset movement scheme matched with the user ID is searched according to the user ID; then, carrying out data segmentation on the actual motion data based on the motion types, so as to compare the motion data under each motion type with preset motion data, and further judging the actual motion state of the user according to each comparison result; finally, the preset physiological data matched with the actual motion state is obtained, the preset physiological data is compared with the actual physiological data, so that whether the physiological data of the user in the actual motion state is matched with the preset physiological data or not is judged, if not, the motion state of the user can be considered to have health risks, and then early warning can be sent to the user to remind the user to take corresponding measures. The invention can customize a preset exercise scheme for each user according to different physical conditions of the users, and when the actual exercise state of the user is not consistent with the preset exercise scheme, the exercise state of the user is considered to have health risks, so that personalized monitoring of the exercise states of different users is realized, and the monitoring result is more accurate.
Drawings
Fig. 1 is a flowchart of a method for monitoring sports health in an embodiment of the present application.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be briefly described below with reference to the accompanying drawings and the description of the embodiments or the prior art, and it is obvious that the following description of the structure of the drawings is only some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art. It should be noted that the description of these examples is for aiding in understanding the present invention, but is not intended to limit the present invention.
Examples
In order to solve the technical problem that the conventional exercise health monitoring method cannot perform personalized exercise health monitoring for each user, the embodiment of the application provides an exercise health monitoring method, which can customize a preset exercise scheme for each user according to different physical conditions of each user, and when the actual exercise state of the user is inconsistent with the preset exercise scheme, the exercise state of the user is considered to have health risks, so that personalized monitoring of the exercise states of different users is realized, and the monitoring result is more accurate.
The exercise health monitoring method provided in the embodiments of the present application will be described in detail below.
It should be noted that, the exercise health monitoring method provided in the embodiments of the present application may be applied to any terminal device that uses an operating system to remotely monitor the health status of a user, where the operating system includes, but is not limited to, a Windows system, a Mac system, a Linux system, a Chrome OS system, a UNIX operating system, an IOS system, an android system, and the like, and is not limited herein; the terminal device includes, but is not limited to, a smart phone, an IPAD tablet computer, a personal mobile computer, an industrial computer, a personal computer, and the like, which are not limited herein. For convenience of description, the embodiments of the present application will be described with respect to a personal computer as an execution subject, except for the specific description. It will be appreciated that the execution subject is not limited to the embodiments of the present application, and in other embodiments, a smart phone or other types of terminal devices may be used as the execution subject.
As shown in fig. 1, a flowchart of a method for monitoring sports health according to an embodiment of the present application is provided, where the method includes, but is not limited to, implementation by steps S1 to S4:
s1, receiving actual physiological data and actual movement data of a user in a movement process, which are sent by health monitoring equipment;
it should be noted that, the health monitoring device in this embodiment is mainly a portable wearable monitoring device in a sports process, including but not limited to a smart watch, a smart bracelet, a smart glasses, a smart ball shoe, a smart helmet, a smart garment, etc., and of course, it is understood that other currently known wearable health monitoring devices are also within the scope of protection in the embodiments of the present application, and the disclosure is not limited thereto.
It should be noted that, the health monitoring device in the embodiment of the present application may implement collection of actual physiological data and actual motion data in a user motion process based on a plurality of built-in detection components, specifically, collect actual physiological data through a physiological data detection component, and collect actual motion data through a motion data collection component. For example: collecting heart rate data by a heart rate sensor (e.g., PPG sensor), collecting pulse data by a pulse sensor, collecting electrocardiographic data by an ECG sensor, collecting respiratory rate data by a respiratory rate sensor, collecting blood pressure data by a blood pressure sensor, collecting temperature data by a temperature sensor, etc.; in addition, the motion gesture data of the user is collected through a motion gesture sensor (preferably an inertial sensor), the motion step number data of the user is collected through an acceleration sensor, and the like, and the hardware of the health monitoring equipment can be specifically configured according to actual requirements, and the detailed description is omitted here.
Before step S1, preferably, before receiving the actual physiological data and the actual movement data of the user during the movement sent by the health monitoring device, the method further includes:
and generating a corresponding user ID for the health monitoring equipment according to the user basic information sent by the health monitoring equipment, signing the user ID and returning the user ID to the health monitoring equipment.
Preferably, the health monitoring system or platform is established to monitor the health state of the user in the system or the platform. Specifically, each health monitoring device newly added into the system or the platform is used as a newly added node, and in order to ensure the uniqueness of user information, when the new health monitoring device is added into the system or the platform, a corresponding user ID is required to be generated for the health management device; of course, it can be understood that, since each user may hold a plurality of monitoring devices, when the user has previously bound other health monitoring devices, if a new health monitoring device is added, the user basic information sent by the health monitoring device is verified, if the new user information is the new user information, a new user ID is matched for the health monitoring device, and if the new user information is the existing user information, an existing user ID is matched for the health monitoring device; of course, it can be understood that when the same user holds multiple health monitoring devices, each health monitoring device may be further numbered to distinguish, or different identifiers may be assigned to each health monitoring device to distinguish, and the embodiment may implement the distinction between multiple health monitoring devices of the same user in multiple manners, which is not limited herein.
More preferably, before generating the corresponding user ID for the health monitoring device according to the user basic information sent by the health monitoring device, the method further includes:
initiating TCP connection to the health monitoring equipment through a preset guide node, and carrying out callback connection on the IP address of the health monitoring equipment, so as to judge the accessibility of the IP address of the health monitoring equipment;
the user privacy is related to the basic information (especially physiological data or health data) of the user, so that the health monitoring device is very important to ensure the communication safety during the communication with the remote monitoring terminal, and prevent information leakage. If any source IP address can be forged, any data packet can be intercepted, and the number of untrusted clients is not limited, so that the security of information during communication of the system cannot be ensured. Although there are no fully reliable nodes in the network, the mutual trust between the nodes is not high, but there are relatively reliable nodes in the network. Thus, when a new health monitoring device is added to the network, the connection between the server and the health monitoring device is established by setting up the guide nodes, which are relatively reliable, so that the information security is ensured, wherein the health monitoring device needs to trust the preset guide nodes when adding to the network.
(2) If the callback connection is successful, randomly sending a hash problem to the health monitoring equipment through a preset guide node; if the callback fails, rejecting the health monitoring equipment to join the network; wherein, by setting the difficulty level of the hash problem, the same user can be prevented from obtaining a large number of IDs in a short time.
(3) And receiving the solution of the hash problem by the health monitoring equipment, verifying the correctness of the solution, and if the answer is correct, establishing effective connection with the health monitoring equipment.
Based on the above disclosure, in the embodiment of the present application, when a new health monitoring device is added to a network, through weak authentication on the health monitoring device, that is, firstly, the health monitoring device is connected with a guide node, and an IP address of the health monitoring device is provided, the guide node signs the user ID matched with the health monitoring device by using a private key to generate ton if the callback fails, and refuses the health monitoring device to be added to the network, if the callback succeeds, the guide node randomly selects a hash problem to answer the health monitoring device, the health monitoring device sends the answer to the guide node, the guide node verifies the correctness of the answer, if not correct, the health monitoring device is also refused to be added, if correct, the actual connection with the health monitoring device is established according to the IP address and the port number of the health monitoring device, and the user ID matched with the health monitoring device is provided, and meanwhile, the guide node signs the user ID matched with the health monitoring device by using the private key to generate ton, returns the signed user ID and Token information to the health monitoring device, so that when the new health monitoring device is added to the network, the new health monitoring device can be shown to the guide node, and whether the health monitoring device can be authenticated by the guide node through the other keys, and whether the health monitoring device can be further verified by the fact that the health monitoring device can be leaked to other public node, and the health monitoring device can be judged.
S2, acquiring a user ID carried by the health monitoring equipment during data transmission, and searching to obtain a preset exercise scheme matched with the user ID, wherein the preset exercise scheme comprises preset physiological data and an exercise state matched with the preset physiological data;
it should be noted that, in the embodiment of the present application, for different users, a preset exercise scheme matched with physical attributes and historical exercise habits of the users is preconfigured, for example: the basic information of the user A is: sex men, age 25, height 175cm, weight 70kg; the historical physiological data are systolic blood pressure of 95-130mmHg, diastolic blood pressure of 65-80mmHg, body temperature of 36.1-37.2 ℃, heart rate of 80-100 times/min, etc., and the historical exercise habit is running, fast walking, stretching, etc. Based on the basic information, the historical physiological data and the historical exercise habit of the user A, an exercise preset scheme matched with the user A can be customized for the user A to refer to when the user A exercises, for example, the heart rate of the user A is kept in a higher state daily according to the historical heart rate range of 80-100 times per minute, so that the user A is not recommended to do long-time aerobic exercise to avoid discomfort to the heart.
Then, based on the above disclosure, when the user a wears the portable health monitoring device to perform exercise, the health monitoring device will send the actual physiological data and the actual exercise data generated during the exercise to the remote monitoring terminal in real time, and meanwhile, the ID information of the user a will be carried in the data sending process, so that after receiving the ID information of the user a, the remote monitoring terminal searches the preset exercise scheme matched with the ID information of the user a in the preset system database, and determines the health risk of the actual exercise state based on the preset exercise scheme, as described in detail below, and the exercise state is not expanded here.
Preferably, the remote monitoring terminal in the embodiment of the application is not limited to a system background, for example, a server, but also can be a terminal held by a parent of a user, so that the parent can know the motion state of the user in time and take a rescue measure in time when a danger occurs.
For example: the user B starts the morning running, and at the moment, the system sends physiological data and motion data generated by the user B in the morning running to a terminal held by a parent user C of the user B in real time, so that the user C knows the motion state of the user B in real time, and remote monitoring is realized.
S3, dividing the actual motion data based on the motion types, and comparing part of motion data under each motion type with preset motion data of the corresponding type to obtain an actual motion state of a user;
the exercise types in the embodiments of the present application include, but are not limited to, walking, running, sitting, jumping, climbing, arm stretching, punching, etc., and of course, it is understood that other existing exercise types are also within the scope of protection of the present application, and are not described herein.
In a specific embodiment of step S3, the segmentation of the actual motion data based on the motion type includes:
s31, processing the actual motion data into a motion sequence comprising a series of gesture frames;
it should be noted that, the original motion gesture data is a motion sequence composed of a series of gesture frames, each frame defines a hierarchical human skeleton model, where the root joint has multiple degrees of freedom for representing the position and orientation of the human skeleton in the coordinate system.
S32, defining sliding windows of the motion sequences, and calculating cosine similarity among motion sequence fragments in each sliding window to construct a similarity curve of the motion sequences;
in a specific embodiment in step S32, defining a sliding window of the motion sequence includes:
in one possible design, defining a sliding window of the motion sequence includes:
for moving sequencesSetting sliding window->The sliding window->The expression of (2) is as follows:
；（1）
；（2）
wherein,sequence number representing current window, ">Representing the motion sequence contained in the current window +.>The first of (3)Frame pose->Representing a movement sequence +.>The number of frames involved, ">The size of each sliding window is represented, and each sliding step of the sliding window is set to 1 frame.
In a specific embodiment in step S32, calculating cosine similarity between motion sequence segments in each sliding window to construct a similarity curve of the motion sequence includes:
and calculating cosine similarity between the first motion sequence segment and the second motion sequence segment in each sliding window, wherein the calculation formula is as follows:
；（3）
wherein,feature vectors representing segments of the first motion sequence, < >>A feature vector representing a second motion sequence segment;
and extracting the characteristic vector of the motion sequence segment corresponding to the first half window and the characteristic vector of the motion sequence segment corresponding to the second half window for each window in the sliding process, and then calculating the similarity of the motion sequence segments of the front part and the rear part of the window according to the cosine distance, so that the motion types can be distinguished.
According to the calculation results of a plurality of cosine similarity, constructing and obtaining the motion sequenceIs a similarity curve of (2).
For example: if the motion sequence only comprises one motion type, the front and back motion sections in each window should belong to the same motion type, and the obtained similarity curve should be a horizontal line close to 1; if the motion sequence includes 2 motion types, when the sliding window slides on the first motion type, the first motion type is the second half of the sliding window, at this time, the similarity of the front and rear motions of the window will gradually decrease, when the second motion type completely occupies the second half of the sliding window, the front and rear motions of the window are different motion types, therefore, the calculated similarity will be minimized, as the sliding window moves backwards, the second motion type starts to enter the first half of the window, at this time, the similarity between the front and rear motions of the window gradually starts to increase, and when the sliding window completely enters the second motion type, the similarity reaches the maximum.
Wherein the feature vector of the first motion sequence segmentThe extraction process of (2) is as follows:
calculating a histogram vector of each characteristic parameter in the first motion sequence segment, wherein the characteristic parameter is an included angle between every two joint points, and a calculation formula is as follows:
；（4）
；（5）
wherein,representing the number of frames comprised by the first motion sequence segment, is->Representing the +.sup.th in the first motion sequence segment>Histogram vector of individual angles +_>Indicate->Angle->Fall within the interval->Frequency of internal, ->Representing the number of sub-intervals dividing the value interval of the angle,/->Wherein the value interval of each included angle is +.>；
It should be noted that, the selected joint points in this embodiment include, but are not limited to, a root skeletal node, 8 segments of skeletal nodes of the four limbs, an upper arm skeletal node, and a thigh skeletal node, and the characteristics of the motion sequence are characterized by calculating the included angle between the root skeletal node and any other skeletal node.
Connecting the histogram vectors of the characteristic parameters end to obtain the characteristic vector of the first motion sequence segment。
For example: in the method, 8 bone included angles are selected, so that the histogram of each bone included angle in the first motion sequence segment is a 1 xL vector, and the histograms of the 8 bone included angles of the first motion sequence segment are connected end to obtain a new 1 x8 vectorAs a feature vector describing the first motion sequence segment. The included angle histogram feature in the embodiment is a high-dimensional sparse vector, and the similarity between any two high-dimensional feature vectors is measured through cosine distance, so that the dimension of original high-dimensional motion data can be reduced.
Of course, it can be understood that the extraction process of the feature vector of the second motion sequence is the same as the extraction process of the feature vector of the first motion sequence, and will not be described herein.
S33, detecting segmentation points in the similarity curve, and segmenting the similarity curve based on the detected segmentation points to obtain partial motion data under each motion type; wherein the partition point is a minimum value of the similarity curve.
Preferably, detecting the segmentation point in the similarity curve includes:
the segmentation points in the similarity curve are detected by adopting a curve simplification algorithm, so that smaller fluctuation changes in the similarity curve can be ignored, larger fluctuation changes are reserved, and the purpose of segmentation point detection is achieved. The threshold value of the curve simplification algorithm is an empirical value, and can be set through multiple priori experiments, preferably the threshold value is set to be 0.1, and then the dividing points of the curve can be obtained through calculating the slopes of adjacent connecting points.
S4, calling preset physiological data matched with the actual motion state, and comparing the preset physiological data with the actual physiological data to obtain a health state monitoring result of the user.
Based on the above disclosure, in the embodiment, the user ID carried in the data transmission process is obtained while the actual physiological data and the actual movement data sent by the health monitoring device are received, and the preset movement scheme matched with the user ID is found according to the user ID; then, carrying out data segmentation on the actual motion data based on the motion types, so as to compare the motion data under each motion type with preset motion data, and further judging the actual motion state of the user according to each comparison result; finally, the preset physiological data matched with the actual motion state is obtained, the preset physiological data is compared with the actual physiological data, so that whether the physiological data of the user in the actual motion state is matched with the preset physiological data or not is judged, if not, the motion state of the user can be considered to have health risks, and then early warning can be sent to the user to remind the user to take corresponding measures. The invention can customize a preset exercise scheme for each user according to different physical conditions of the users, and when the actual exercise state of the user is not consistent with the preset exercise scheme, the exercise state of the user is considered to have health risks, so that personalized monitoring of the exercise states of different users is realized, and the monitoring result is more accurate.
A second aspect provides a sports health monitoring device comprising:
the data receiving module is used for receiving actual physiological data and actual movement data of a user in the movement process, which are sent by the health monitoring equipment;
the ID matching module is used for acquiring a user ID carried by the health monitoring equipment during data transmission, and searching to obtain a preset exercise scheme matched with the user ID, wherein the preset exercise scheme comprises preset physiological data and an exercise state matched with the preset physiological data;
the state acquisition module is used for dividing the actual motion data based on the motion types, and comparing part of motion data under each motion type with preset motion data of the corresponding type to obtain the actual motion state of the user;
and the result acquisition module is used for calling preset physiological data matched with the actual motion state, and comparing the preset physiological data with the actual physiological data to obtain a health state monitoring result of the user.
The working process, working details and technical effects of the foregoing apparatus provided in the second aspect of the present embodiment may be referred to as the method described in the foregoing first aspect or any one of the possible designs of the first aspect, which are not described herein again.
A third aspect provides a computer readable storage medium having instructions stored thereon which, when run on a computer, perform the method of athletic health monitoring as described in any one of the possible designs of the first aspect.
The computer readable storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash Memory, and/or a Memory Stick (Memory Stick), etc., where the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
The working process, working details and technical effects of the foregoing computer readable storage medium provided in the third aspect of the present embodiment may refer to the method as described in the foregoing first aspect or any one of the possible designs of the first aspect, which are not repeated herein.
A fourth aspect provides a computer device comprising a memory, a processor and a transceiver in communication with each other in sequence, wherein the memory is adapted to store a computer program and the transceiver is adapted to send and receive messages, and the processor is adapted to read the computer program and to perform the method of sports health monitoring as described in any one of the possible designs of the first aspect.
By way of specific example, the Memory may include, but is not limited to, random-Access Memory (RAM), read-Only Memory (ROM), flash Memory (Flash Memory), first-in first-out Memory (First Input First Output, FIFO), and/or first-in last-out Memory (First Input Last Output, FILO), etc.; the processor may not be limited to use with a microprocessor of the STM32F105 family; the transceiver may be, but is not limited to, a WiFi (wireless fidelity) wireless transceiver, a bluetooth wireless transceiver, a GPRS (General Packet Radio Service, general packet radio service technology) wireless transceiver, and/or a ZigBee (ZigBee protocol, low power local area network protocol based on the ieee 802.15.4 standard), etc. In addition, the computer device may include, but is not limited to, a power module, a display screen, and other necessary components.
The working process, working details and technical effects of the foregoing computer device provided in the fourth aspect of the present embodiment may be referred to as the foregoing first aspect or any one of the possible designs of the first aspect, which are not described herein.
A fifth aspect provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of sports health monitoring as described in any one of the possible designs of the first aspect.
The working process, working details and technical effects of the foregoing computer program product containing instructions provided in the fifth aspect of the present embodiment may be referred to as the method described in the foregoing first aspect or any one of the possible designs of the first aspect, which are not repeated herein.
Finally, it should be noted that: the foregoing description is only of the preferred embodiments of the invention and is not intended to limit the scope of the invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A method of athletic health monitoring, comprising:
receiving actual physiological data and actual movement data of a user in a movement process, which are sent by health monitoring equipment;
acquiring a user ID carried by the health monitoring equipment during data transmission, and searching to obtain a preset motion scheme matched with the user ID, wherein the preset motion scheme comprises preset physiological data and a motion state matched with the preset physiological data;
dividing the actual motion data based on the motion types, and comparing part of the motion data under each motion type with the preset motion data of the corresponding type to obtain the actual motion state of the user;
invoking preset physiological data matched with the actual motion state, and comparing the preset physiological data with the actual physiological data to obtain a health state monitoring result of a user;
before receiving the actual physiological data and the actual movement data of the user during the movement sent by the health monitoring device, the method further comprises:
generating a corresponding user ID for the health monitoring equipment according to user basic information sent by the health monitoring equipment, signing the user ID and returning the user ID to the health monitoring equipment;
before generating the corresponding user ID for the health monitoring device according to the user basic information sent by the health monitoring device, the method further includes:
initiating TCP connection to the health monitoring equipment through a preset guide node, and carrying out callback connection on the IP address of the health monitoring equipment so as to judge the accessibility of the IP address of the health monitoring equipment, wherein the guide node is a reliable node in a network;
if the callback connection is successful, randomly sending a hash problem to the health monitoring equipment through a preset guide node;
receiving the solution of the hash problem by the health monitoring equipment, verifying the correctness of the answer, if the answer is correct, establishing the actual connection between the server and the health monitoring equipment, and matching the server with the corresponding user ID;
the method comprises the steps that a guide node signs a user ID matched with health monitoring equipment by using a private key to generate a Token, the signed user ID and Token information are returned to the health monitoring equipment, so that when the health monitoring equipment is added to a network, the Token is presented to other nodes in the network, and the other nodes verify the Token through the public key of the guide node to judge whether the health monitoring equipment is allowed to be added to the network.
2. The method of claim 1, wherein segmenting the actual motion data based on motion type comprises:
processing the actual motion data into a motion sequence comprising a series of pose frames;
defining sliding windows of the motion sequences, and calculating cosine similarity among motion sequence fragments in each sliding window to construct a similarity curve of the motion sequences;
detecting the dividing points in the similarity curve, and dividing the similarity curve based on the detected dividing points to obtain partial motion data under each motion type; wherein the partition point is a minimum value of the similarity curve.
3. The method of claim 2, wherein defining a sliding window of the motion sequence comprises:
for moving sequencesSetting sliding window->The sliding window->The expression of (2) is as follows:
；（1）
；（2）
wherein,sequence number representing current window, ">Representing the motion sequence contained in the current window +.>The%>Frame pose->Representing a movement sequence +.>The number of frames involved, ">The size of each sliding window is represented, and each sliding step of the sliding window is set to 1 frame.
4. A method of motion health monitoring according to claim 3, wherein calculating cosine similarity between motion sequence segments in each sliding window to construct a similarity curve for the motion sequence comprises:
and calculating cosine similarity between the first motion sequence segment and the second motion sequence segment in each sliding window, wherein the calculation formula is as follows:
；（3）
wherein,feature vectors representing segments of the first motion sequence, < >>The feature vector of the second motion sequence segment is represented, the first motion sequence segment refers to the motion sequence segment corresponding to the first half window of each sliding window, and the second motion sequence segment refers to the motion sequence segment corresponding to the second half window of each sliding window;
according to the calculation results of a plurality of cosine similarity, constructing and obtaining the motion sequenceIs a similarity curve of (2).
5. The method of claim 4, wherein the feature vector of the first motion sequence segmentThe extraction process of (2) is as follows:
calculating a histogram vector of each characteristic parameter in the first motion sequence segment, wherein the characteristic parameter is an included angle between every two joint points, and a calculation formula is as follows:
；（4）
；（5）
wherein,representing the number of frames comprised by the first motion sequence segment, is->Representing the first motion sequence segmentHistogram vector of individual angles +_>Indicate->Angle->Fall within the interval->Frequency of internal, ->Representing the number of sub-intervals dividing the value interval of the angle,/->Wherein the value interval of each included angle is +.>；
Connecting the histogram vectors of the characteristic parameters end to obtain the characteristic vector of the first motion sequence segment。
6. The method of claim 5, wherein detecting the segmentation points in the similarity curve comprises:
and detecting the dividing points in the similarity curve by adopting a curve simplification algorithm.
7. An athletic health monitoring device, comprising:
the data receiving module is used for receiving actual physiological data and actual movement data of a user in the movement process, which are sent by the health monitoring equipment;
the ID matching module is used for acquiring a user ID carried by the health monitoring equipment during data transmission, and searching to obtain a preset exercise scheme matched with the user ID, wherein the preset exercise scheme comprises preset physiological data and an exercise state matched with the preset physiological data;
the state acquisition module is used for dividing the actual motion data based on the motion types, and comparing part of motion data under each motion type with preset motion data of the corresponding type to obtain the actual motion state of the user;
the result acquisition module is used for calling preset physiological data matched with the actual motion state, and comparing the preset physiological data with the actual physiological data to obtain a health state monitoring result of the user;
the device is also for:
before receiving actual physiological data and actual movement data of a user in a movement process, which are sent by health monitoring equipment, generating a corresponding user ID for the health monitoring equipment according to user basic information sent by the health monitoring equipment, signing the user ID, and returning the user ID to the health monitoring equipment;
before generating a corresponding user ID for the health monitoring equipment according to user basic information sent by the health monitoring equipment, initiating TCP connection to the health monitoring equipment through a preset guide node, and carrying out callback connection on an IP address of the health monitoring equipment so as to judge the accessibility of the IP address of the health monitoring equipment, wherein the guide node is a reliable node in a network;
if the callback connection is successful, randomly sending a hash problem to the health monitoring equipment through a preset guide node;
receiving the solution of the hash problem by the health monitoring equipment, verifying the correctness of the answer, if the answer is correct, establishing the actual connection between the server and the health monitoring equipment, and matching the server with the corresponding user ID;
the method comprises the steps that a guide node signs a user ID matched with health monitoring equipment by using a private key to generate a Token, the signed user ID and Token information are returned to the health monitoring equipment, so that when the health monitoring equipment is added to a network, the Token is presented to other nodes in the network, and the other nodes verify the Token through the public key of the guide node to judge whether the health monitoring equipment is allowed to be added to the network.
8. A computer readable storage medium having instructions stored thereon which, when executed on a computer, perform the athletic health monitoring method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211534573.3A CN115910341B (en) | 2022-12-02 | 2022-12-02 | Exercise health monitoring method, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211534573.3A CN115910341B (en) | 2022-12-02 | 2022-12-02 | Exercise health monitoring method, device and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115910341A CN115910341A (en) | 2023-04-04 |
| CN115910341B true CN115910341B (en) | 2024-02-13 |
Family
ID=86486578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211534573.3A Active CN115910341B (en) | 2022-12-02 | 2022-12-02 | Exercise health monitoring method, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115910341B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101465888A (en) * | 2007-12-19 | 2009-06-24 | 索尼株式会社 | Network sytem, direct access method, network domestic appliance and program |
| CN101594367A (en) * | 2008-05-29 | 2009-12-02 | 索尼株式会社 | Content distributing server and content distribution method |
| CN102625011A (en) * | 2002-01-07 | 2012-08-01 | 西门子工业公司 | Modem function incorporated in a programmable logic controller |
| TW201424803A (en) * | 2012-12-28 | 2014-07-01 | Univ Far East | Intelligent physical fitness training system |
| CN205031267U (en) * | 2015-10-11 | 2016-02-17 | 深圳前海慧练天下网络科技有限公司 | Exercise prescription real -time monitoring system based on intelligence wearing equipment |
| CN106797371A (en) * | 2014-04-17 | 2017-05-31 | 康普特尔公开有限公司 | For the method and system of user authentication |
| CN108245145A (en) * | 2018-01-18 | 2018-07-06 | 日照职业技术学院 | A kind of health monitoring systems |
| CN109584989A (en) * | 2018-11-27 | 2019-04-05 | 北京羽扇智信息科技有限公司 | A kind of method for pushing, device, equipment and storage medium moving prompt information |
| CN109814934A (en) * | 2019-01-31 | 2019-05-28 | 安谋科技（中国）有限公司 | Data processing method, device, readable medium and system |
| CN110752934A (en) * | 2019-10-28 | 2020-02-04 | 江苏大周基业智能科技有限公司 | Network identity interactive authentication method under topological structure |
| CN111107075A (en) * | 2019-12-13 | 2020-05-05 | 中国工商银行股份有限公司 | Request response method and device, electronic equipment and computer-readable storage medium |
| CN113076825A (en) * | 2021-03-19 | 2021-07-06 | 云南电网有限责任公司西双版纳供电局 | Transformer substation worker climbing safety monitoring method |
| CN113626781A (en) * | 2021-07-19 | 2021-11-09 | 中国科学院信息工程研究所 | Block chain efficient authentication method based on trusted group |
-
2022
- 2022-12-02 CN CN202211534573.3A patent/CN115910341B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102625011A (en) * | 2002-01-07 | 2012-08-01 | 西门子工业公司 | Modem function incorporated in a programmable logic controller |
| CN101465888A (en) * | 2007-12-19 | 2009-06-24 | 索尼株式会社 | Network sytem, direct access method, network domestic appliance and program |
| CN101594367A (en) * | 2008-05-29 | 2009-12-02 | 索尼株式会社 | Content distributing server and content distribution method |
| TW201424803A (en) * | 2012-12-28 | 2014-07-01 | Univ Far East | Intelligent physical fitness training system |
| CN106797371A (en) * | 2014-04-17 | 2017-05-31 | 康普特尔公开有限公司 | For the method and system of user authentication |
| CN205031267U (en) * | 2015-10-11 | 2016-02-17 | 深圳前海慧练天下网络科技有限公司 | Exercise prescription real -time monitoring system based on intelligence wearing equipment |
| CN108245145A (en) * | 2018-01-18 | 2018-07-06 | 日照职业技术学院 | A kind of health monitoring systems |
| CN109584989A (en) * | 2018-11-27 | 2019-04-05 | 北京羽扇智信息科技有限公司 | A kind of method for pushing, device, equipment and storage medium moving prompt information |
| CN109814934A (en) * | 2019-01-31 | 2019-05-28 | 安谋科技（中国）有限公司 | Data processing method, device, readable medium and system |
| CN110752934A (en) * | 2019-10-28 | 2020-02-04 | 江苏大周基业智能科技有限公司 | Network identity interactive authentication method under topological structure |
| CN111107075A (en) * | 2019-12-13 | 2020-05-05 | 中国工商银行股份有限公司 | Request response method and device, electronic equipment and computer-readable storage medium |
| CN113076825A (en) * | 2021-03-19 | 2021-07-06 | 云南电网有限责任公司西双版纳供电局 | Transformer substation worker climbing safety monitoring method |
| CN113626781A (en) * | 2021-07-19 | 2021-11-09 | 中国科学院信息工程研究所 | Block chain efficient authentication method based on trusted group |
Non-Patent Citations (1)
| Title |
|---|
| "基于余弦距离的人体运动数据行为分割算法";邢薇薇，等;《中南大学学报(自然科学版)》;第45卷(第4期);第1128-1136页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115910341A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3094050B1 (en) | Wearable electronic apparatus | |
| KR20160063126A (en) | Exercise information providing method and electronic device supporting the same | |
| US11837361B2 (en) | System or method for real-time analysis of remote health data aggregated with vital signs to provide remote assistance | |
| CN113272913A (en) | System and method for collecting, analyzing and sharing biorhythm data between users | |
| CN106503468A (en) | Electronic health record analysis system and method for the medical information based on coupling keyword | |
| JP2018504960A (en) | Method and apparatus for processing human body feature data | |
| CN110378244A (en) | The detection method and device of abnormal posture | |
| Pourbemany et al. | A survey of wearable devices pairing based on biometric signals | |
| CN110249364A (en) | For providing the method and electronic equipment of health contents | |
| Frank et al. | Bayesian recognition of safety relevant motion activities with inertial sensors and barometer | |
| CN115910341B (en) | Exercise health monitoring method, device and medium | |
| US8990054B1 (en) | System and method for determining and training a peak performance state | |
| CN107403476A (en) | Mobile phone terminal dynamic facial identifies attendance checking system | |
| EP3448078B1 (en) | Electronic device, system and method for data communication | |
| CN108388842B (en) | Intelligent prompt method and Related product | |
| WO2021098488A1 (en) | Atrial fibrillation signal classification method and device, and terminal and storage medium | |
| EP4066730B1 (en) | Data acquisition method, terminal device, and storage medium | |
| CN203930836U (en) | Wearable electronic equipment | |
| CN115171196B (en) | Face image processing method, related device and storage medium | |
| ElAarag et al. | System Architecture of HatterHealthConnect: An Integration of Body Sensor Networks and Social Networks to Improve Health Awareness | |
| KR20190047644A (en) | Method and wearable device for providing feedback on exercise | |
| CN107832690A (en) | The method and Related product of recognition of face | |
| CN111613333A (en) | Self-service health detection method and device, storage medium and mobile terminal | |
| Tan | Digital Healthcare Innovations and Implementation Considerations Under the COVID-19 Pandemic | |
| Jokić et al. | Autonomic telemedical application for Android based mobile devices |
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 |