CN116453693B - Exercise risk protection method and device based on artificial intelligence and computing equipment - Google Patents
Exercise risk protection method and device based on artificial intelligence and computing equipment Download PDFInfo
- Publication number
- CN116453693B CN116453693B CN202310440535.XA CN202310440535A CN116453693B CN 116453693 B CN116453693 B CN 116453693B CN 202310440535 A CN202310440535 A CN 202310440535A CN 116453693 B CN116453693 B CN 116453693B
- Authority
- CN
- China
- Prior art keywords
- motion
- exercise
- category
- track
- risk
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 29
- 230000033001 locomotion Effects 0.000 claims abstract description 392
- 238000004088 simulation Methods 0.000 claims abstract description 89
- 238000012502 risk assessment Methods 0.000 claims abstract description 81
- 238000013145 classification model Methods 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 19
- 238000012937 correction Methods 0.000 claims description 18
- 238000002372 labelling Methods 0.000 claims description 14
- 230000000386 athletic effect Effects 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 206010060820 Joint injury Diseases 0.000 claims description 7
- 206010050031 Muscle strain Diseases 0.000 claims description 7
- 206010061363 Skeletal injury Diseases 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 206010020651 Hyperkinesia Diseases 0.000 claims description 5
- 208000000269 Hyperkinesis Diseases 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 4
- 230000001960 triggered effect Effects 0.000 claims description 4
- 238000013210 evaluation model Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000036541 health Effects 0.000 description 10
- 230000007613 environmental effect Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 239000008280 blood Substances 0.000 description 4
- 210000004369 blood Anatomy 0.000 description 4
- 230000036772 blood pressure Effects 0.000 description 4
- 230000036760 body temperature Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 2
- 239000008103 glucose Substances 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 206010042434 Sudden death Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Data Mining & Analysis (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physical Education & Sports Medicine (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses an artificial intelligence-based exercise risk protection method, an artificial intelligence-based exercise risk protection device and a computing device, wherein the exercise risk protection method comprises the following steps: acquiring human body posture data within a preset duration; generating a motion simulation track within the preset duration based on the human body posture data; determining a motion category matched with the motion simulation track and a standard motion track under the motion category; extracting deviation coordinate parameters between the motion simulation track and the standard motion track; inputting the deviation coordinate parameters and the motion categories into a pre-trained motion risk assessment model to obtain a motion risk assessment result; outputting safety protection information if the exercise risk assessment result indicates that exercise risk exists, wherein the safety protection information is used for prompting that exercise risk exists in the current exercise; it can be seen that the present invention can improve the safety of sports.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an artificial intelligence-based exercise risk protection method, an artificial intelligence-based exercise risk protection device and computing equipment.
Background
At present, with increasing importance of people for healthy life, sports are an indispensable part of life.
In practice, it is found that in the current exercise process of people, due to lack of exercise risk related knowledge, a plurality of risks exist in the exercise process, and if the risks are serious, the risks can cause exercise injury, exercise diseases and even exercise sudden death, so that great potential safety hazards are caused to physical and mental health and life safety of people.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the invention provides an artificial intelligence-based exercise risk protection method, an artificial intelligence-based exercise risk protection device and a computing device, which can improve exercise safety.
According to an aspect of an embodiment of the present invention, there is provided an artificial intelligence-based exercise risk protection method, including:
acquiring human body posture data within a preset duration;
generating a motion simulation track within the preset duration based on the human body posture data;
determining a motion category matched with the motion simulation track and a standard motion track under the motion category;
extracting deviation coordinate parameters between the motion simulation track and the standard motion track;
Inputting the deviation coordinate parameters and the motion categories into a pre-trained motion risk assessment model to obtain a motion risk assessment result;
and if the exercise risk assessment result indicates that exercise risk exists, outputting safety protection information, wherein the safety protection information is used for prompting that the current exercise has exercise risk.
As an alternative embodiment, the pre-trained exercise risk assessment model is trained based on the following steps:
acquiring coordinate parameters of deviated samples under each sample motion category;
determining the labeling movement risk category deviating from the sample coordinate parameter;
taking each deviated sample coordinate parameter and the labeling risk category corresponding to each deviated sample coordinate parameter as training parameters of a multi-classification model to be trained, and carrying out iterative training on the multi-classification model to be trained to obtain a pre-trained motion risk assessment model aiming at each sample motion category;
wherein the sample motion category includes at least the motion category.
As an alternative embodiment, the exercise risk assessment result includes an exercise risk category; and
The method further comprises the steps of:
if the exercise risk category is a preset category, determining that the exercise risk assessment result indicates that exercise risk exists;
wherein the predetermined categories include muscle strain, hyperkinesia, skeletal injury, and joint injury.
As an alternative embodiment, the method further comprises:
if the exercise risk assessment result indicates that the exercise risk does not exist, generating exercise posture correction information according to the deviation coordinate parameters;
and outputting a motion guide prompt based on the motion gesture correction information.
As an alternative embodiment, the method further comprises:
collecting current environment image data;
performing image recognition on the current environment image data to obtain environment types corresponding to the current environment image data; and
determining a motion category matching the motion simulation track and a standard motion track under the motion category, comprising:
and determining a motion category matched with the motion simulation track and the environment category and a standard motion track under the motion category.
According to another aspect of the embodiments of the present invention, there is also provided an artificial intelligence based exercise risk protection device, including:
The data acquisition unit is used for acquiring human body posture data within a preset duration;
the track generation unit is used for generating a motion simulation track within the preset duration based on the human body posture data;
the data determining unit is used for determining a motion category matched with the motion simulation track and a standard motion track under the motion category;
the parameter extraction unit is used for extracting deviation coordinate parameters between the motion simulation track and the standard motion track;
the evaluation unit is used for inputting the deviation coordinate parameters and the motion categories into a pre-trained motion risk evaluation model to obtain a motion risk evaluation result;
and the information output unit is used for outputting safety protection information if the exercise risk assessment result indicates that the exercise risk exists, and the safety protection information is used for prompting that the exercise risk exists in the current exercise.
According to yet another aspect of an embodiment of the present invention, there is also provided a computing device including: at least one processor, memory, and input output unit; the memory is used for storing a computer program, and the processor is used for calling the computer program stored in the memory to execute the exercise risk protection method based on artificial intelligence.
According to yet another aspect of embodiments of the present application, there is also provided a computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform the above-described artificial intelligence-based exercise risk protection method.
In the embodiment of the application, the human body posture data in the preset time length is acquired; generating a motion simulation track within the preset duration based on the human body posture data; determining a motion category matched with the motion simulation track and a standard motion track under the motion category; extracting deviation coordinate parameters between the motion simulation track and the standard motion track; inputting the deviation coordinate parameters and the motion categories into a pre-trained motion risk assessment model to obtain a motion risk assessment result; outputting safety protection information if the exercise risk assessment result indicates that exercise risk exists, wherein the safety protection information is used for prompting that exercise risk exists in the current exercise; it can be seen that the present application can improve the safety of sports.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a flow diagram of an alternative artificial intelligence based exercise risk protection method in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of an alternative artificial intelligence based exercise risk guard in accordance with an embodiment of the present invention;
FIG. 3 schematically illustrates a schematic structural diagram of a medium according to an embodiment of the present invention;
FIG. 4 schematically illustrates a structural diagram of a computing device in accordance with embodiments of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring now to fig. 1, fig. 1 is a schematic flow chart of an exercise risk protection method based on artificial intelligence according to an embodiment of the present invention. It should be noted that embodiments of the present invention may be applied to any scenario where applicable.
The process of the exercise risk protection method based on artificial intelligence according to an embodiment of the present invention shown in fig. 1 includes:
step S101, acquiring human body posture data in a preset time period.
In this embodiment, the execution body may be a wearable device, which may be worn by the user during the exercise. In addition, the wearable device has an image acquisition function, a positioning function, a pose estimation function and the like.
The human body posture data can be posture change data of a user in a motion process, and the posture refers to position and posture. The execution main body can collect pose data corresponding to each moment in a preset time period according to a preset pose collection period, and takes the pose data corresponding to each moment in the preset time period as human body pose data.
Optionally, the executing body may also collect human health data within a preset time period, where the human health data may include, but is not limited to, heart rate, blood pressure, electrocardiogram, body temperature, blood sugar, etc. of the user.
As an optional implementation manner, acquiring the human body posture data within the preset time period may include: receiving a motion starting instruction and a motion ending instruction triggered by a user, and determining starting time corresponding to the motion starting instruction and ending time corresponding to the motion ending instruction; collecting initial attitude data from a starting moment to a terminating moment; and carrying out data analysis on the initial posture data, determining the real motion starting time and the motion ending time, determining the time length between the real motion starting time and the motion ending time as the preset time length, and determining the initial posture data between the real motion starting time and the motion ending time as the human posture data. It will be appreciated that the actual start of the movement is generally later than the start of the movement corresponding to the start of the movement command and that the actual end of the movement is generally earlier than the end of the movement corresponding to the end of the movement command. By implementing this alternative embodiment, the determination accuracy of the human body posture data can be improved.
Step S102, generating a motion simulation track within the preset duration based on the human body posture data.
In this embodiment, after the execution body obtains the human body posture data, the execution body may generate a motion simulation track within a preset duration according to the mapping relationship between each acquisition time and the pose data in the human body posture data. The motion simulation track is used for describing the change condition of the pose data at each acquisition moment.
As an optional implementation manner, based on the human body posture data, generating a motion simulation track within the preset duration includes: dividing pose data in the human body pose data into a plurality of sets based on a preset duration; the longer the preset time length is, the more the number of the sets is; performing pose optimization on pose data in each set to obtain optimized pose data, and generating segmented tracks corresponding to each set based on the optimized pose data; constructing an error function between segmented tracks of adjacent sets, wherein the adjacent sets refer to sets with adjacent acquisition time; optimizing the pose data of each set by utilizing an error function to obtain optimized target pose data; and generating a motion simulation track within a preset duration based on the optimized target pose data of each set. By implementing the alternative implementation mode, the human body posture data can be divided into a plurality of sets of posture data, then the posture optimization in the sets and the posture optimization among the sets are performed, and the accuracy of the target posture data is reasonably improved, so that the accuracy of the motion simulation track is improved.
Step S103, determining a motion category matched with the motion simulation track and a standard motion track under the motion category.
In this embodiment, the execution body may store in advance standard motion trajectories corresponding to different motion categories. After the motion simulation track is obtained, the execution body can match the motion simulation track with each pre-stored standard motion track, calculate the coordinate matching degree between the tracks, and then determine the motion category corresponding to the standard motion track with the highest coordinate matching degree as the motion category matched with the motion simulation track.
As an alternative embodiment, determining a motion category matching the motion simulation trajectory, and a standard motion trajectory under the motion category, includes: inputting a motion simulation track into a motion classification model which is trained in advance to obtain a plurality of candidate motion categories output by the motion classification model; acquiring a standard motion trail associated with each candidate motion category; calculating the coincidence degree, the maximum offset of coordinates and the track fitting error of the standard motion tracks and the motion simulation tracks associated with each candidate motion category, calculating the matching degree between the standard motion tracks and the motion simulation tracks based on the coincidence degree, the maximum offset of coordinates and the track fitting error of the tracks, and determining the motion category corresponding to the standard motion track with the highest coordinate matching degree as the motion category matched with the motion simulation tracks.
And step S104, extracting the deviation coordinate parameters between the motion simulation track and the standard motion track.
In this embodiment, after the execution body obtains the motion simulation track and the standard motion track corresponding to the motion simulation track, the execution body may perform track fitting on the motion simulation track and the standard motion track, and calculate the deviation coordinate parameters in the fitted track. Wherein the offset coordinate parameter is used to describe a distance parameter between a discrete point in the trajectory after the trajectory fitting and the trajectory after the fitting.
As an optional implementation manner, extracting a deviation coordinate parameter between the motion simulation track and the standard motion track includes: extracting a first track point set of a motion simulation track and extracting a second track point set of a standard motion track; fitting to obtain a target fitting track based on the coordinate data of each track point in the first track point set and the second track point set; calculating distance values between each track point in the first track point set and the second track point set and the target fitting track; determining a track point with a distance value larger than a preset distance threshold value as a deviation coordinate; and taking the offset coordinates and the distance values between the offset coordinates and the target fitting track as the offset coordinate parameters.
Step S105, inputting the deviation coordinate parameters and the exercise category into a exercise risk assessment model which is trained in advance, and obtaining an exercise risk assessment result.
In this embodiment, the exercise risk assessment model trained in advance is used to output a corresponding exercise risk assessment result according to the input deviation coordinate parameters and the exercise category. The exercise risk assessment result is used for indicating the risk condition of the exercise, and may be specifically an exercise risk category. In addition, the exercise risk assessment model which is trained in advance can be a multi-classification model, and the exercise risk classification can be carried out on different exercise categories in a targeted manner.
Optionally, the executing body may also collect human health data within a preset time period, where the human health data may include, but is not limited to, heart rate, blood pressure, electrocardiogram, body temperature, blood sugar, etc. of the user. For this, the exercise risk assessment model may be trained in advance, the human health data, the deviation coordinate parameters and the exercise category may be input, and the corresponding exercise risk assessment result may be output. By introducing parameter consideration to human health data in the model training stage, more accurate exercise risk assessment can be realized.
And step S106, if the exercise risk assessment result indicates that exercise risk exists, outputting safety protection information, wherein the safety protection information is used for prompting that the current exercise has exercise risk.
In this embodiment, if the exercise risk assessment result indicates that there is an exercise risk, the safety protection information may be output to early warn the exercise risk. The safety protection information may include text prompts, voice prompts, light prompts, and the like.
As an alternative embodiment, the pre-trained exercise risk assessment model is trained based on the following steps:
acquiring coordinate parameters of deviated samples under each sample motion category;
determining the labeling movement risk category deviating from the sample coordinate parameter;
taking each deviated sample coordinate parameter and the labeling risk category corresponding to each deviated sample coordinate parameter as training parameters of a multi-classification model to be trained, and carrying out iterative training on the multi-classification model to be trained to obtain a pre-trained motion risk assessment model aiming at each sample motion category;
wherein the sample motion category includes at least the motion category.
In this embodiment, when the executing body trains the exercise risk assessment model, multiple sample exercise categories may be determined first, and for each sample exercise category, a corresponding offset sample coordinate parameter may be further obtained, and the calculation method of the offset sample coordinate parameter refers to the calculation method of the offset coordinate parameter described above, which is not described herein. And, for each deviated sample coordinate parameter, the corresponding labeling exercise risk category can be labeled. And then, taking each deviation sample coordinate parameter and the labeling risk category corresponding to each deviation sample coordinate parameter as training parameters of the multi-classification model to be trained, and carrying out iterative training on the multi-classification model to be trained by combining a preset loss function to obtain a pre-trained motion risk assessment model aiming at each sample motion category. It is understood that the sample motion classes herein include at least the motion classes described above.
As an alternative embodiment, the exercise risk assessment result includes an exercise risk category; and
the method further comprises the steps of:
if the exercise risk category is a preset category, determining that the exercise risk assessment result indicates that exercise risk exists;
Wherein the predetermined categories include muscle strain, hyperkinesia, skeletal injury, and joint injury.
In this embodiment, the preset categories may be categories with exercise risk, including muscle strain, excessive exercise, bone injury, joint injury, and the like, and when the exercise risk category is these categories, it may be determined that there is exercise risk at this time, and safety protection information may be output.
As an alternative embodiment, the method further comprises:
if the exercise risk assessment result indicates that the exercise risk does not exist, generating exercise posture correction information according to the deviation coordinate parameters;
and outputting a motion guide prompt based on the motion gesture correction information.
In this embodiment, if the exercise risk assessment result is not the above-mentioned category, for example, the exercise risk category is a no-risk category, it is determined that the exercise risk assessment result indicates that there is no exercise risk, and the safety protection information is not output. Also, in such a case, the execution subject may further generate the motion-posture correction information based on the off-coordinate parameter. Wherein the motion gesture correction information is used to guide the gesture of the user to reduce the offset indicated by the offset coordinate parameter. For example, the movement posture correction information may be information for the user to adjust the posture of the specified portion toward the specified direction. Further, the execution body may output a motion guidance prompt according to the motion posture correction information. The motion guidance prompt can be a text prompt or a voice prompt.
Alternatively, the executing body may establish a connection with the display device in advance, the motion guide prompt may be a guide animation, and the executing body may transmit the guide animation to the display device end for display, so as to correct the motion gesture more intuitively.
As an alternative embodiment, the method further comprises:
collecting current environment image data;
performing image recognition on the current environment image data to obtain environment types corresponding to the current environment image data; and
determining a motion category matching the motion simulation track and a standard motion track under the motion category, comprising:
and determining a motion category matched with the motion simulation track and the environment category and a standard motion track under the motion category.
In this embodiment, the execution body may further collect current environmental image data, and perform image recognition on the current environmental image data, where the image recognition may use an existing various picture tag matching manner to obtain an environmental category matched with the current environmental image data. Environmental categories herein may include, but are not limited to, indoor, outdoor, home, playground, gym, etc. And when determining the motion category matched with the current motion and the standard motion trail under the motion category, the candidate motion category can be determined in an auxiliary way by combining the environment category, and particularly, for the motion classification model, the motion category of the output label of the motion classification model can be controlled by considering two input parameters of the environment category and the motion simulation trail in the model training stage. And in the model use stage, inputting the environment category and the motion simulation track into a motion classification model to obtain a plurality of candidate motion categories. And calculating the matching degree between the standard motion trail of each candidate motion category and the motion simulation trail, obtaining the best matched candidate motion category based on the matching degree, taking the best matched candidate motion category as the motion category, and taking the standard motion trail corresponding to the candidate motion category as the standard motion trail under the motion category.
In the embodiment of the invention, the human body posture data in the preset time length is acquired; generating a motion simulation track within the preset duration based on the human body posture data; determining a motion category matched with the motion simulation track and a standard motion track under the motion category; extracting deviation coordinate parameters between the motion simulation track and the standard motion track; inputting the deviation coordinate parameters and the motion categories into a pre-trained motion risk assessment model to obtain a motion risk assessment result; outputting safety protection information if the exercise risk assessment result indicates that exercise risk exists, wherein the safety protection information is used for prompting that exercise risk exists in the current exercise; it can be seen that the present invention can improve the safety of sports.
Having described the method of an exemplary embodiment of the present invention, an artificial intelligence based exercise risk protection device of an exemplary embodiment of the present invention is described next with reference to fig. 2, the device comprising at least.
A data acquisition unit 201, configured to acquire human body posture data within a preset duration;
a track generating unit 202, configured to generate a motion simulation track within the preset duration based on the human body posture data;
A data determining unit 203, configured to determine a motion category matching the motion simulation track, and a standard motion track under the motion category;
a parameter extraction unit 204, configured to extract a coordinate parameter of deviation between the motion simulation track and the standard motion track;
the evaluation unit 205 is configured to input the deviation coordinate parameter and the exercise category into a exercise risk evaluation model that is trained in advance, so as to obtain an exercise risk evaluation result;
and the information output unit 206 is configured to output safety protection information if the exercise risk assessment result indicates that an exercise risk exists, where the safety protection information is used to prompt that an exercise risk exists in the current exercise.
In this embodiment, the exercise risk protection device based on artificial intelligence may be a wearable device, which may be worn by a user during exercise. In addition, the wearable device has an image acquisition function, a positioning function, a pose estimation function and the like.
The human body posture data can be posture change data of a user in a motion process, and the posture refers to position and posture. The pose data corresponding to each moment can be acquired within the preset time period according to the preset pose acquisition period, and the pose data corresponding to each moment within the preset time period is used as the human body pose data.
Optionally, human health data may also be collected for a preset period of time, which may include, but is not limited to, heart rate, blood pressure, electrocardiogram, body temperature, blood glucose, etc. of the user.
As an optional implementation manner, acquiring the human body posture data within the preset time period may include: receiving a motion starting instruction and a motion ending instruction triggered by a user, and determining starting time corresponding to the motion starting instruction and ending time corresponding to the motion ending instruction; collecting initial attitude data from a starting moment to a terminating moment; and carrying out data analysis on the initial posture data, determining the real motion starting time and the motion ending time, determining the time length between the real motion starting time and the motion ending time as the preset time length, and determining the initial posture data between the real motion starting time and the motion ending time as the human posture data. It will be appreciated that the actual start of the movement is generally later than the start of the movement corresponding to the start of the movement command and that the actual end of the movement is generally earlier than the end of the movement corresponding to the end of the movement command. By implementing this alternative embodiment, the determination accuracy of the human body posture data can be improved.
In this embodiment, after the above-mentioned human body posture data is obtained, a motion simulation track within a preset duration may be generated according to a mapping relationship between each acquisition time in the human body posture data and the pose data. The motion simulation track is used for describing the change condition of the pose data at each acquisition moment.
As an optional implementation manner, based on the human body posture data, generating a motion simulation track within the preset duration includes: dividing pose data in the human body pose data into a plurality of sets based on a preset duration; the longer the preset time length is, the more the number of the sets is; performing pose optimization on pose data in each set to obtain optimized pose data, and generating segmented tracks corresponding to each set based on the optimized pose data; constructing an error function between segmented tracks of adjacent sets, wherein the adjacent sets refer to sets with adjacent acquisition time; optimizing the pose data of each set by utilizing an error function to obtain optimized target pose data; and generating a motion simulation track within a preset duration based on the optimized target pose data of each set. By implementing the alternative implementation mode, the human body posture data can be divided into a plurality of sets of posture data, then the posture optimization in the sets and the posture optimization among the sets are performed, and the accuracy of the target posture data is reasonably improved, so that the accuracy of the motion simulation track is improved.
In this embodiment, standard motion trajectories corresponding to different motion categories may be stored in advance. After the motion simulation track is obtained, the motion simulation track can be matched with each pre-stored standard motion track, the coordinate matching degree between the tracks is calculated, and then the motion category corresponding to the standard motion track with the highest coordinate matching degree is determined as the motion category matched with the motion simulation track.
As an alternative embodiment, determining a motion category matching the motion simulation trajectory, and a standard motion trajectory under the motion category, includes: inputting a motion simulation track into a motion classification model which is trained in advance to obtain a plurality of candidate motion categories output by the motion classification model; acquiring a standard motion trail associated with each candidate motion category; calculating the coincidence degree, the maximum offset of coordinates and the track fitting error of the standard motion tracks and the motion simulation tracks associated with each candidate motion category, calculating the matching degree between the standard motion tracks and the motion simulation tracks based on the coincidence degree, the maximum offset of coordinates and the track fitting error of the tracks, and determining the motion category corresponding to the standard motion track with the highest coordinate matching degree as the motion category matched with the motion simulation tracks.
In this embodiment, after the motion simulation track and the standard motion track corresponding to the motion simulation track are obtained, the motion simulation track and the standard motion track may be subjected to track fitting, and the deviation coordinate parameters in the fitted track may be calculated. Wherein the offset coordinate parameter is used to describe a distance parameter between a discrete point in the trajectory after the trajectory fitting and the trajectory after the fitting.
As an optional implementation manner, extracting a deviation coordinate parameter between the motion simulation track and the standard motion track includes: extracting a first track point set of a motion simulation track and extracting a second track point set of a standard motion track; fitting to obtain a target fitting track based on the coordinate data of each track point in the first track point set and the second track point set; calculating distance values between each track point in the first track point set and the second track point set and the target fitting track; determining a track point with a distance value larger than a preset distance threshold value as a deviation coordinate; and taking the offset coordinates and the distance values between the offset coordinates and the target fitting track as the offset coordinate parameters.
In this embodiment, the exercise risk assessment model trained in advance is used to output a corresponding exercise risk assessment result according to the input deviation coordinate parameters and the exercise category. The exercise risk assessment result is used for indicating the risk condition of the exercise, and may be specifically an exercise risk category. In addition, the exercise risk assessment model which is trained in advance can be a multi-classification model, and the exercise risk classification can be carried out on different exercise categories in a targeted manner.
Optionally, human health data may also be collected for a preset period of time, which may include, but is not limited to, heart rate, blood pressure, electrocardiogram, body temperature, blood glucose, etc. of the user. For this, the exercise risk assessment model may be trained in advance, the human health data, the deviation coordinate parameters and the exercise category may be input, and the corresponding exercise risk assessment result may be output. By introducing parameter consideration to human health data in the model training stage, more accurate exercise risk assessment can be realized.
In this embodiment, if the exercise risk assessment result indicates that there is an exercise risk, the safety protection information may be output to early warn the exercise risk. The safety protection information may include text prompts, voice prompts, light prompts, and the like.
As an alternative embodiment, the pre-trained exercise risk assessment model is trained based on the following steps:
acquiring coordinate parameters of deviated samples under each sample motion category;
determining the labeling movement risk category deviating from the sample coordinate parameter;
taking each deviated sample coordinate parameter and the labeling risk category corresponding to each deviated sample coordinate parameter as training parameters of a multi-classification model to be trained, and carrying out iterative training on the multi-classification model to be trained to obtain a pre-trained motion risk assessment model aiming at each sample motion category;
Wherein the sample motion category includes at least the motion category.
In this embodiment, when training the exercise risk assessment model, a plurality of sample exercise categories may be determined first, and for each sample exercise category, a corresponding offset sample coordinate parameter may be further obtained, and the calculation method of the offset sample coordinate parameter refers to the calculation method of the offset coordinate parameter described above, which is not described herein. And, for each deviated sample coordinate parameter, the corresponding labeling exercise risk category can be labeled. And then, taking each deviation sample coordinate parameter and the labeling risk category corresponding to each deviation sample coordinate parameter as training parameters of the multi-classification model to be trained, and carrying out iterative training on the multi-classification model to be trained by combining a preset loss function to obtain a pre-trained motion risk assessment model aiming at each sample motion category. It is understood that the sample motion classes herein include at least the motion classes described above.
As an alternative embodiment, the exercise risk assessment result includes an exercise risk category; and
the apparatus further comprises:
the judging unit is used for determining that the exercise risk assessment result indicates that exercise risk exists if the exercise risk category is a preset category;
Wherein the predetermined categories include muscle strain, hyperkinesia, skeletal injury, and joint injury.
In this embodiment, the preset categories may be categories with exercise risk, including muscle strain, excessive exercise, bone injury, joint injury, and the like, and when the exercise risk category is these categories, it may be determined that there is exercise risk at this time, and safety protection information may be output.
As an alternative embodiment, the information output unit 206 is further configured to:
if the exercise risk assessment result indicates that the exercise risk does not exist, generating exercise posture correction information according to the deviation coordinate parameters;
and outputting a motion guide prompt based on the motion gesture correction information.
In this embodiment, if the exercise risk assessment result is not the above-mentioned category, for example, the exercise risk category is a no-risk category, it is determined that the exercise risk assessment result indicates that there is no exercise risk, and the safety protection information is not output. Also, in such a case, the motion-posture correction information may be generated further based on the deviated coordinate parameter. Wherein the motion gesture correction information is used to guide the gesture of the user to reduce the offset indicated by the offset coordinate parameter. For example, the movement posture correction information may be information for the user to adjust the posture of the specified portion toward the specified direction. Further, motion guidance cues may be output based on the motion profile correction information. The motion guidance prompt can be a text prompt or a voice prompt.
Alternatively, a connection may be established with the display device in advance, and the motion guide prompt may be a guide animation, and the guide animation may be transmitted to the display device end for display, so as to correct the motion gesture more intuitively.
As an alternative embodiment, the apparatus further comprises:
the environment recognition unit is used for collecting current environment image data; performing image recognition on the current environment image data to obtain environment types corresponding to the current environment image data; and
the data determining unit 203 is specifically configured to:
and determining a motion category matched with the motion simulation track and the environment category and a standard motion track under the motion category.
In this embodiment, the current environment image data may be collected and image-identified, where the image identification may use the existing various image tag matching methods to obtain the environment category matching with the current environment image data. Environmental categories herein may include, but are not limited to, indoor, outdoor, home, playground, gym, etc. And when determining the motion category matched with the current motion and the standard motion trail under the motion category, the candidate motion category can be determined in an auxiliary way by combining the environment category, and particularly, for the motion classification model, the motion category of the output label of the motion classification model can be controlled by considering two input parameters of the environment category and the motion simulation trail in the model training stage. And in the model use stage, inputting the environment category and the motion simulation track into a motion classification model to obtain a plurality of candidate motion categories. And calculating the matching degree between the standard motion trail of each candidate motion category and the motion simulation trail, obtaining the best matched candidate motion category based on the matching degree, taking the best matched candidate motion category as the motion category, and taking the standard motion trail corresponding to the candidate motion category as the standard motion trail under the motion category.
In the embodiment of the invention, the human body posture data in the preset time length is acquired; generating a motion simulation track within the preset duration based on the human body posture data; determining a motion category matched with the motion simulation track and a standard motion track under the motion category; extracting deviation coordinate parameters between the motion simulation track and the standard motion track; inputting the deviation coordinate parameters and the motion categories into a pre-trained motion risk assessment model to obtain a motion risk assessment result; outputting safety protection information if the exercise risk assessment result indicates that exercise risk exists, wherein the safety protection information is used for prompting that exercise risk exists in the current exercise; it can be seen that the present invention can improve the safety of sports.
Having described the method and apparatus of the exemplary embodiments of the present invention, reference will now be made to fig. 3 for describing a computer-readable storage medium of the exemplary embodiments of the present invention, and reference will be made to fig. 3 for showing a computer-readable storage medium as an optical disc 30, on which a computer program (i.e., a program product) is stored, which when executed by a processor, implements the steps described in the above-described method embodiments, for example, acquiring human posture data within a preset duration; generating a motion simulation track within the preset duration based on the human body posture data; determining a motion category matched with the motion simulation track and a standard motion track under the motion category; extracting deviation coordinate parameters between the motion simulation track and the standard motion track; inputting the deviation coordinate parameters and the motion categories into a pre-trained motion risk assessment model to obtain a motion risk assessment result; outputting safety protection information if the exercise risk assessment result indicates that exercise risk exists, wherein the safety protection information is used for prompting that exercise risk exists in the current exercise; the specific implementation of each step is not repeated here.
It should be noted that examples of the computer readable storage medium may also include, but are not limited to, a phase change memory (PRAM), a Static Random Access Memory (SRAM), a Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory, or other optical or magnetic storage medium, which will not be described in detail herein.
Having described the methods, media, and apparatus of exemplary embodiments of the present invention, next, computing devices for artificial intelligence based athletic risk protection of exemplary embodiments of the present invention are described with reference to FIG. 4.
FIG. 4 illustrates a block diagram of an exemplary computing device 40 suitable for use in implementing embodiments of the invention, the computing device 40 may be a computer system or a server. The computing device 40 shown in fig. 4 is merely an example and should not be taken as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 4, components of computing device 40 may include, but are not limited to: one or more processors or processing units 401, a system memory 402, a bus 403 that connects the various system components (including the system memory 402 and the processing units 401).
Computing device 40 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computing device 40 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 402 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 4021 and/or cache memory 4022. Computing device 40 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, ROM4023 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4 and commonly referred to as a "hard disk drive"). Although not shown in fig. 4, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media), may be provided. In such cases, each drive may be coupled to bus 403 through one or more data medium interfaces. The system memory 402 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the embodiments of the invention.
A program/utility 4025 having a set (at least one) of program modules 4024 may be stored, for example, in system memory 402, and such program modules 4024 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 4024 generally perform the functions and/or methodologies of the described embodiments of the present invention.
Computing device 40 may also communicate with one or more external devices 404 (e.g., keyboard, pointing device, display, etc.). Such communication may occur through an input/output (I/O) interface 405. Moreover, computing device 40 may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 406. As shown in fig. 4, network adapter 406 communicates with other modules of computing device 40, such as processing unit 401, etc., over bus 403. It should be appreciated that although not shown in fig. 4, other hardware and/or software modules may be used in connection with computing device 40.
The processing unit 401 executes various functional applications and data processing by running a program stored in the system memory 402, for example, acquires human body posture data for a preset period of time; generating a motion simulation track within the preset duration based on the human body posture data; determining a motion category matched with the motion simulation track and a standard motion track under the motion category; extracting deviation coordinate parameters between the motion simulation track and the standard motion track; inputting the deviation coordinate parameters and the motion categories into a pre-trained motion risk assessment model to obtain a motion risk assessment result; and if the exercise risk assessment result indicates that exercise risk exists, outputting safety protection information, wherein the safety protection information is used for prompting that the current exercise has exercise risk. The specific implementation of each step is not repeated here. It should be noted that while several units/modules or sub-units/sub-modules of an artificial intelligence based exercise risk guard are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more units/modules described above may be embodied in one unit/module in accordance with embodiments of the present invention. Conversely, the features and functions of one unit/module described above may be further divided into ones that are embodied by a plurality of units/modules.
In the description of the present invention, it should be noted that the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Furthermore, although the operations of the methods of the present invention are depicted in the drawings in a particular order, this is not required to either imply that the operations must be performed in that particular order or that all of the illustrated operations be performed to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.
Claims (10)
1. An artificial intelligence-based exercise risk protection method, which is characterized in that the method is applied to a wearable device, and a user wears the wearable device in the exercise process, and comprises the following steps:
acquiring human body posture data within a preset duration, including: receiving a motion starting instruction and a motion ending instruction triggered by a user, and determining starting time corresponding to the motion starting instruction and ending time corresponding to the motion ending instruction; collecting initial attitude data from the starting time to the ending time; carrying out data analysis on the initial gesture data to determine real motion starting time and motion ending time; determining the duration between the real motion starting time and the motion ending time as the preset duration, and determining the initial posture data between the real motion starting time and the motion ending time as the human posture data;
based on the human body posture data, generating a motion simulation track within the preset duration, including: dividing pose data in the human body pose data into a plurality of sets based on the preset duration; the longer the preset time length is, the more the number of the sets is; performing pose optimization on pose data in each set to obtain optimized pose data, and generating segmented tracks corresponding to each set based on the optimized pose data; constructing an error function between segmented tracks of adjacent sets, wherein the adjacent sets are sets adjacent in acquisition time; optimizing the pose data of each set by utilizing an error function to obtain optimized target pose data; generating a motion simulation track within the preset duration based on the optimized target pose data of each set;
Determining a motion category matched with the motion simulation track and a standard motion track under the motion category;
extracting deviation coordinate parameters between the motion simulation track and the standard motion track; the deviation coordinate parameters are used for describing distance parameters between discrete points in the track after the motion simulation track and the standard motion track are subjected to track fitting and the track after fitting;
inputting the deviation coordinate parameters and the motion categories into a pre-trained motion risk assessment model to obtain a motion risk assessment result; the exercise risk assessment model which is trained in advance is a multi-classification model and is used for carrying out targeted exercise risk division on different exercise categories;
and if the exercise risk assessment result indicates that exercise risk exists, outputting safety protection information, wherein the safety protection information is used for prompting that the current exercise has exercise risk.
2. The exercise risk protection method based on artificial intelligence according to claim 1, wherein the exercise risk assessment model trained in advance is obtained based on the following steps:
acquiring coordinate parameters of deviated samples under each sample motion category;
Determining the labeling movement risk category deviating from the sample coordinate parameter;
taking each deviated sample coordinate parameter and the labeling risk category corresponding to each deviated sample coordinate parameter as training parameters of a multi-classification model to be trained, and carrying out iterative training on the multi-classification model to be trained to obtain a pre-trained motion risk assessment model aiming at each sample motion category;
wherein the sample motion category includes at least the motion category.
3. The exercise risk protection method based on artificial intelligence according to claim 1, wherein the exercise risk assessment result comprises an exercise risk category; and
the method further comprises the steps of:
if the exercise risk category is a preset category, determining that the exercise risk assessment result indicates that exercise risk exists;
wherein the predetermined categories include muscle strain, hyperkinesia, skeletal injury, and joint injury.
4. The artificial intelligence based athletic risk protection method of claim 1, further comprising:
if the exercise risk assessment result indicates that the exercise risk does not exist, generating exercise posture correction information according to the deviation coordinate parameters;
And outputting a motion guide prompt based on the motion gesture correction information.
5. The artificial intelligence based athletic risk protection method of claim 1, further comprising:
collecting current environment image data;
performing image recognition on the current environment image data to obtain environment types corresponding to the current environment image data; and
determining a motion category matching the motion simulation track and a standard motion track under the motion category, comprising:
and determining a motion category matched with the motion simulation track and the environment category and a standard motion track under the motion category.
6. An artificial intelligence based exercise risk protection device, wherein the device is applied to a wearable device worn by a user during exercise, comprising:
the data acquisition unit is used for acquiring human body posture data in a preset duration and comprises the following components: receiving a motion starting instruction and a motion ending instruction triggered by a user, and determining starting time corresponding to the motion starting instruction and ending time corresponding to the motion ending instruction; collecting initial attitude data from the starting time to the ending time; carrying out data analysis on the initial gesture data to determine real motion starting time and motion ending time; determining the duration between the real motion starting time and the motion ending time as the preset duration, and determining the initial posture data between the real motion starting time and the motion ending time as the human posture data;
The track generating unit is used for generating a motion simulation track within the preset duration based on the human body posture data, and comprises the following steps: dividing pose data in the human body pose data into a plurality of sets based on the preset duration; the longer the preset time length is, the more the number of the sets is; performing pose optimization on pose data in each set to obtain optimized pose data, and generating segmented tracks corresponding to each set based on the optimized pose data; constructing an error function between segmented tracks of adjacent sets, wherein the adjacent sets are sets adjacent in acquisition time; optimizing the pose data of each set by utilizing an error function to obtain optimized target pose data; generating a motion simulation track within the preset duration based on the optimized target pose data of each set;
the data determining unit is used for determining a motion category matched with the motion simulation track and a standard motion track under the motion category;
the parameter extraction unit is used for extracting deviation coordinate parameters between the motion simulation track and the standard motion track; the deviation coordinate parameters are used for describing distance parameters between discrete points in the track after the motion simulation track and the standard motion track are subjected to track fitting and the track after fitting;
The evaluation unit is used for inputting the deviation coordinate parameters and the motion categories into a pre-trained motion risk evaluation model to obtain a motion risk evaluation result; the exercise risk assessment model which is trained in advance is a multi-classification model and is used for carrying out targeted exercise risk division on different exercise categories;
and the information output unit is used for outputting safety protection information if the exercise risk assessment result indicates that the exercise risk exists, and the safety protection information is used for prompting that the exercise risk exists in the current exercise.
7. The artificial intelligence based athletic risk protection device of claim 6, wherein the pre-trained athletic risk assessment model is trained based on the following steps:
acquiring coordinate parameters of deviated samples under each sample motion category;
determining the labeling movement risk category deviating from the sample coordinate parameter;
taking each deviated sample coordinate parameter and the labeling risk category corresponding to each deviated sample coordinate parameter as training parameters of a multi-classification model to be trained, and carrying out iterative training on the multi-classification model to be trained to obtain a pre-trained motion risk assessment model aiming at each sample motion category;
Wherein the sample motion category includes at least the motion category.
8. The artificial intelligence based athletic risk protection device of claim 6, wherein the athletic risk assessment result includes an athletic risk category; and
the apparatus further comprises:
the judging unit is used for determining that the exercise risk assessment result indicates that exercise risk exists if the exercise risk category is a preset category;
wherein the predetermined categories include muscle strain, hyperkinesia, skeletal injury, and joint injury.
9. The artificial intelligence based athletic risk protection device of claim 6, wherein the information output unit is further configured to:
if the exercise risk assessment result indicates that the exercise risk does not exist, generating exercise posture correction information according to the deviation coordinate parameters;
and outputting a motion guide prompt based on the motion gesture correction information.
10. A computing device, the computing device comprising:
at least one processor, memory, and input output unit;
wherein the memory is for storing a computer program and the processor is for invoking the computer program stored in the memory to perform the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310440535.XA CN116453693B (en) | 2023-04-20 | 2023-04-20 | Exercise risk protection method and device based on artificial intelligence and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310440535.XA CN116453693B (en) | 2023-04-20 | 2023-04-20 | Exercise risk protection method and device based on artificial intelligence and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116453693A CN116453693A (en) | 2023-07-18 |
| CN116453693B true CN116453693B (en) | 2023-11-14 |
Family
ID=87135484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310440535.XA Active CN116453693B (en) | 2023-04-20 | 2023-04-20 | Exercise risk protection method and device based on artificial intelligence and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116453693B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109344692A (en) * | 2018-08-10 | 2019-02-15 | 华侨大学 | A kind of motion quality evaluation method and system |
| CN111714125A (en) * | 2020-06-09 | 2020-09-29 | 北京海益同展信息科技有限公司 | Method, device and system for monitoring motion state and storage medium |
| CN112370048A (en) * | 2020-11-10 | 2021-02-19 | 南京紫金体育产业股份有限公司 | Movement posture injury prevention method and system based on joint key points and storage medium |
| CN112568898A (en) * | 2019-09-29 | 2021-03-30 | 杭州福照光电有限公司 | Method, device and equipment for automatically evaluating injury risk and correcting motion of human body motion based on visual image |
| CN112819852A (en) * | 2019-11-15 | 2021-05-18 | 微软技术许可有限责任公司 | Evaluating gesture-based motion |
| CN114926910A (en) * | 2022-07-18 | 2022-08-19 | 科大讯飞(苏州)科技有限公司 | Action matching method and related equipment thereof |
| CN115497626A (en) * | 2022-10-17 | 2022-12-20 | 北京新清泰克科技有限公司 | Body health assessment method based on joint point identification |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5284923B2 (en) * | 2009-10-28 | 2013-09-11 | 本田技研工業株式会社 | Control device for legged mobile robot |
-
2023
- 2023-04-20 CN CN202310440535.XA patent/CN116453693B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109344692A (en) * | 2018-08-10 | 2019-02-15 | 华侨大学 | A kind of motion quality evaluation method and system |
| CN112568898A (en) * | 2019-09-29 | 2021-03-30 | 杭州福照光电有限公司 | Method, device and equipment for automatically evaluating injury risk and correcting motion of human body motion based on visual image |
| CN112819852A (en) * | 2019-11-15 | 2021-05-18 | 微软技术许可有限责任公司 | Evaluating gesture-based motion |
| CN111714125A (en) * | 2020-06-09 | 2020-09-29 | 北京海益同展信息科技有限公司 | Method, device and system for monitoring motion state and storage medium |
| CN112370048A (en) * | 2020-11-10 | 2021-02-19 | 南京紫金体育产业股份有限公司 | Movement posture injury prevention method and system based on joint key points and storage medium |
| CN114926910A (en) * | 2022-07-18 | 2022-08-19 | 科大讯飞(苏州)科技有限公司 | Action matching method and related equipment thereof |
| CN115497626A (en) * | 2022-10-17 | 2022-12-20 | 北京新清泰克科技有限公司 | Body health assessment method based on joint point identification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116453693A (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108256433B (en) | Motion attitude assessment method and system | |
| EP3617815B1 (en) | Work support device, work support method, and work support program | |
| RU2756366C1 (en) | Estimation of errors in the local activation times (lat) measured using multielectrode catheter | |
| US8608481B2 (en) | Method and apparatus for identifying an instrument location based on measuring a characteristic | |
| CN111898642B (en) | Key point detection method and device, electronic equipment and storage medium | |
| US11403882B2 (en) | Scoring metric for physical activity performance and tracking | |
| CN112970074A (en) | Physical activity quantification and monitoring | |
| US9826923B2 (en) | Motion analysis method | |
| EP3617964A1 (en) | Performance measurement device, performance measurement method and performance measurement program | |
| WO2020084351A1 (en) | Systems and methods for assessment and measurement of reaction time in virtual/augmented reality | |
| EP3617965A1 (en) | Performance measurement device, performance measurement method and performance measurement program | |
| Mullineaux et al. | Research methods: sample size and variability effects on statistical power | |
| Lin et al. | Segmenting human motion for automated rehabilitation exercise analysis | |
| CN115331314A (en) | Exercise effect evaluation method and system based on APP screening function | |
| US20160331304A1 (en) | System and methods for automated administration and evaluation of physical therapy exercises | |
| CN116453693B (en) | Exercise risk protection method and device based on artificial intelligence and computing equipment | |
| EP3396319B1 (en) | Information processing system, information processing program, and information processing method | |
| CN114973048A (en) | Method and device for correcting rehabilitation action, electronic equipment and readable medium | |
| CN111353345A (en) | Method, device and system for providing training feedback, electronic equipment and storage medium | |
| Saponaro et al. | Estimating Physical Activity Intensity And Energy Expenditure Using Computer Vision On Videos | |
| Călin et al. | Improving Movement analysis in physical therapy systems based on kinect interaction | |
| EP3474290B1 (en) | Systems and methods for optimizing a joint cost function and detecting neuro muscular profiles thereof | |
| Jovanović et al. | Automated error detection in physiotherapy training | |
| CN113243032A (en) | Finding adverse events using natural language processing | |
| Clark et al. | A Priori Quantification of Transfer Learning Performance on Time Series Classification for Cyber-Physical Health Systems |
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 |