CN110600132B - Digital twin intelligent health prediction method and device based on vibration detection - Google Patents
Digital twin intelligent health prediction method and device based on vibration detection Download PDFInfo
- Publication number
- CN110600132B CN110600132B CN201910819837.1A CN201910819837A CN110600132B CN 110600132 B CN110600132 B CN 110600132B CN 201910819837 A CN201910819837 A CN 201910819837A CN 110600132 B CN110600132 B CN 110600132B
- Authority
- CN
- China
- Prior art keywords
- user
- motion
- vibration
- stress
- video
- 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 106
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 230000033001 locomotion Effects 0.000 claims abstract description 179
- 230000009471 action Effects 0.000 claims abstract description 66
- 230000008569 process Effects 0.000 claims description 24
- 238000001228 spectrum Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 230000003321 amplification Effects 0.000 claims description 12
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 11
- 238000005192 partition Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 8
- 206010050031 Muscle strain Diseases 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000009877 rendering Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 210000003205 muscle Anatomy 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 210000000577 adipose tissue Anatomy 0.000 claims description 2
- 230000036772 blood pressure Effects 0.000 claims description 2
- 238000004088 simulation Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 12
- 210000002310 elbow joint Anatomy 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 7
- 238000001914 filtration Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 4
- 230000002265 prevention Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 210000001217 buttock Anatomy 0.000 description 2
- 238000011960 computer-aided design Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000009087 cell motility Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Signal Processing (AREA)
- Public Health (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application provides a digital twin intelligent health prediction method and device based on vibration detection. A digital twin intelligent health prediction method based on vibration detection comprises the following steps: when a health prediction instruction is received, acquiring a motion video of a user; identifying a stress part corresponding to the current action of the user based on the motion video of the user; judging whether the stressed part is positioned in the shooting range of the mobile terminal; if the stressed part is positioned in the shooting range of the mobile terminal, acquiring a vibration video of the stressed part according to the motion video; determining first vibration information of the stress part according to the vibration video of the stress part; acquiring a first stress condition of a stress part from the digital twin intelligent health prediction model according to the first vibration information; and determining a first risk score of the current action of the user according to the first stress condition. The technical scheme of the embodiment of the application realizes real-time monitoring of the risk of the current action of the user during body building.
Description
Technical Field
The application relates to the technical field of Internet, in particular to a digital twin intelligent health prediction method and device based on vibration detection.
Background
With the continuous development of the Internet, the Internet plus is a new state of Internet development under innovation 2.0, and in popular terms, the Internet plus is the Internet plus each traditional industry, but the Internet plus and each traditional industry are not simply added together, and the Internet and the traditional industry are deeply fused by utilizing an information communication technology and an Internet platform to create a new development ecology. The method represents a new social form, namely, the optimization and integration of the Internet in the social resource allocation are fully exerted, the innovation achievement of the Internet is deeply integrated into each economic and social domain, the innovation force and the productivity of the whole society are improved, and a new economic development form which takes the Internet as an infrastructure and realizes tools is formed.
The traditional health monitoring mechanism generally adopts a localized detection device, such as a bracelet worn by a user in the movement process, the bracelet can acquire body data of the user in the movement process, localized vibration detection, health prediction and the like are carried out through the bracelet, but the bracelet with the vibration detection function is required to be purchased, and as the bracelet is only worn on the hand, other parts of the body cannot be detected, the detection area is small, and the intelligent health prediction requirements of increasingly more users in various movement scenes are difficult to meet.
Disclosure of Invention
The embodiment of the application provides a digital twin intelligent health prediction method and device based on vibration detection, which are used for detecting vibration of a body-building action of a user, and obtaining a risk score of the current action of the user through a digital twin intelligent health prediction model, so that the risk of the current action of the user during body-building is monitored in real time.
Specifically, the data transmission flow in the vibration detection method disclosed by the embodiment of the application can be based on the internet+technology to form a local+cloud or server distributed intelligent vibration detection system, on one hand, the local can perform accurate original image acquisition and preprocessing through the acquisition device, and on the other hand, the cloud or server can predict the health condition of a detected target based on the acquired distributed data and combined with various special health prediction models obtained through statistical analysis of big data technology, thereby realizing the deep integration of the internet and the traditional health monitoring industry, improving the intelligence and accuracy of health monitoring and meeting the intelligent health prediction requirements in increasingly various sports scenes.
The first aspect of the application provides a digital twin intelligent health prediction method based on vibration detection, which is applied to a mobile terminal, wherein the mobile terminal comprises a camera, and the method comprises the following steps:
When a health prediction instruction is received, acquiring a motion video of a user;
identifying a stress part corresponding to the current action of the user based on the motion video of the user;
judging whether the stressed part is positioned in the shooting range of the mobile terminal or not;
if the stressed part is positioned in the shooting range of the mobile terminal, acquiring a vibration video of the stressed part according to the motion video;
determining first vibration information of the stress part according to the vibration video of the stress part;
acquiring a first stress condition of the stress part from a digital twin intelligent health prediction model according to the first vibration information, wherein the digital twin intelligent health prediction model stores analog vibration information of different body parts of the user under different stress conditions;
and determining a first risk score of the current action of the user according to the first stress condition.
The second aspect of the present application provides a digital twin intelligent health prediction device based on vibration detection, the device comprising:
the acquisition unit is used for acquiring a motion video of a user when a health prediction instruction is received;
the identification unit is used for identifying a stress part corresponding to the current action of the user based on the motion video of the user;
The judging unit is used for judging whether the stressed part is positioned in the shooting range of the mobile terminal;
the first acquisition unit is used for acquiring a vibration video of the stress part according to the motion video if the stress part is positioned in the shooting range of the mobile terminal;
the first determining unit is used for determining first vibration information of the stress part according to the vibration video of the stress part;
the second acquisition unit acquires a first stress condition of the stress part from a digital twin intelligent health prediction model according to the first vibration information, and the digital twin intelligent health prediction model stores simulation vibration information of different body parts of the user under different stress conditions;
and the second determining unit is used for determining a first risk score of the current action of the user according to the first stress condition.
A third aspect of the present application provides a mobile terminal comprising a processor, a memory, a communications interface, and one or more programs stored in the memory and configured for execution by the processor, the programs comprising instructions for performing the steps of any of the methods described above.
A fourth aspect of the present application provides a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to perform some or all of the steps described in any of the methods above.
It can be seen that by the digital twin intelligent health prediction method and device based on vibration detection, when a health prediction instruction is received, a motion video of a user is collected, a stress part corresponding to the current action of the user is identified based on the motion video of the user, a vibration video of the stress part is obtained according to the motion video, first vibration information of the stress part is determined according to the vibration video of the stress part, a first stress condition of the stress part is obtained from a digital twin intelligent health prediction model according to the first vibration information, and a first risk score of the current action of the user is determined according to the first stress condition. Therefore, when a user exercises, the mobile terminal can acquire the motion video of the user in real time, the mobile terminal processes the motion video of the user to obtain the risk score of the current action of the user, the risk of the current action of the user during exercise is monitored in real time, and when the mobile terminal detects the user, the detection area is large, so that the health prediction requirement of the user in various motion scenes can be met.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1a is a schematic diagram of a digital twin intelligent health prediction system based on vibration detection according to an embodiment of the present application;
FIG. 1b is a flowchart of a digital twin intelligent health prediction method based on vibration detection according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a digital twin intelligent health prediction device based on vibration detection according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a part mechanical model according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a mobile terminal according to an embodiment of the present application;
fig. 5 is a schematic diagram of elbow movement of a user according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides a digital twin intelligent health prediction method and device based on vibration detection, which are used for detecting vibration of a body-building action of a user, and obtaining a risk score of the current action of the user through a digital twin intelligent health prediction model, so that the risk of the current action of the user during body-building is monitored in real time.
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application 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 application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims and drawings are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The following describes embodiments of the present application in detail.
According to the digital twin intelligent health prediction method and device based on vibration detection, when a user exercises, vibration videos of stressed parts in the exercise process of the user are collected through the mobile terminal, the vibration videos of the stressed parts are processed to obtain vibration information, and the risk score of the current action of the user is obtained through the digital twin intelligent health prediction model. Therefore, when a user exercises, the mobile terminal can acquire the motion video of the user in real time, the mobile terminal processes the motion video of the user to obtain the risk score of the current action of the user, the risk of the current action of the user during exercise is monitored in real time, and when the mobile terminal detects the user, the detection area is large, so that the health prediction requirement of the user in various motion scenes can be met.
Referring first to fig. 1a, fig. 1a is a schematic diagram of a digital twin intelligent health prediction system based on vibration detection according to an embodiment of the present application, where the health prediction system includes a mobile terminal and a user, the mobile terminal may be a mobile phone, a tablet computer, a notebook computer, a mobile internet device, or other types of terminal devices with cameras, the user may perform various exercise actions, the mobile terminal includes a camera, and the mobile terminal may capture real-time actions of the user through the camera. In the health prediction system 100 shown in fig. 1a, the mobile terminal 101 is a mobile phone, the mobile phone includes a rear camera, the rear camera has a certain shooting range, and the exercise of the user 102 is push-up, wherein:
The mobile terminal 101 is configured to collect a motion video of the user 102 when receiving a health prediction instruction; identifying a stress part corresponding to the current action of the user 102 based on the motion video of the user 102; judging whether the stress part is positioned in the shooting range of the mobile terminal 101; if the stressed part is positioned in the shooting range of the mobile terminal 101, acquiring a vibration video of the stressed part according to the motion video; determining first vibration information of the stress part according to the vibration video of the stress part; acquiring a first stress condition of the stress part from a digital twin intelligent health prediction model according to the first vibration information, wherein the digital twin intelligent health prediction model stores analog vibration information of different body parts of the user 102 under different stress conditions; a first risk score for the current action of the user 102 is determined based on the first force condition.
Specifically, as shown in fig. 1a, when the mobile terminal 101 receives a health prediction instruction, a motion video of the user 102 is acquired through a camera, that is, a motion video of the user 102 for push-up is acquired, the mobile terminal 101 recognizes that the current motion of the user 102 is push-up based on the video of the user 102 for push-up, further determines that a stress portion corresponding to the current motion of the user 102 is an elbow joint, the mobile terminal 101 determines that the elbow joint is located in a shooting range, further acquires a vibration video of the elbow joint, and as the user 102 performs push-up, the mobile terminal 101 acquires vibration videos of the elbow joints of the two arms respectively, then determines a risk score of the current push-up motion of the user 102, if the frequency of the user 102 for push-up is too high, the obtained risk score is too high, and the mobile terminal 101 can timely send an alarm or prompt to the user 102 to reduce the frequency or temporarily stop motion. Therefore, when a user exercises, the mobile terminal can acquire the motion video of the user in real time, the mobile terminal processes the motion video of the user to obtain the risk score of the current action of the user, the risk of the current action of the user during exercise is monitored in real time, and when the mobile terminal detects the user, the detection area is large, so that the health prediction requirement of the user in various motion scenes can be met.
Referring to fig. 1b, fig. 1b is a flowchart of a digital twin intelligent health prediction method based on vibration detection according to an embodiment of the present application, where the digital twin intelligent health prediction method based on vibration detection according to the embodiment of the present application is applied to a mobile terminal, and the mobile terminal includes a camera. As shown in fig. 1b, the digital twin intelligent health prediction method based on vibration detection according to an embodiment of the present application may include:
101. and when a health prediction instruction is received, acquiring a motion video of the user.
Specifically, when a user exercises, the health prediction function of the mobile terminal can be started, and when the mobile terminal receives a health prediction instruction, the camera is started to collect the motion video of the user.
The mobile terminal may be a mobile phone, a tablet computer, a notebook computer, a mobile internet device, or other types of terminal devices with cameras.
102. And identifying a stress part corresponding to the current action of the user based on the motion video of the user.
In the motion process of a user, the user is subjected to real-time image acquisition through the mobile terminal, and the current action of the user is identified based on the acquired motion video of the user, so that the stress part corresponding to the current action of the user is determined.
Specifically, when the mobile terminal is a mobile phone, the mobile phone interface displays an entrance of a body-building strain prevention function, after a user clicks the body-building strain prevention function, the mobile phone starts a camera to collect real-time body-building images of the user, and in the body-building process of the user, the mobile phone can identify a stressed part corresponding to the current action of the user based on the current action of the user. For example, when the current motion of the user is push-up, the force receiving part is an arm, and when the current motion of the user is sit-up, the force receiving part is an abdomen.
103. And judging whether the stressed part is positioned in the shooting range of the mobile terminal.
Specifically, because the positions of the mobile terminals are different, or angles of shooting users of the mobile terminals are different, there are situations that the mobile terminals do not shoot stress parts of the users, so that whether the stress parts are located in the shooting range of the mobile terminals needs to be judged.
In one possible example, the method for determining whether the stress portion is located within the shooting range of the mobile terminal may be:
comparing the characteristic points of the stressed part with the characteristic points of each body part of the user in the image frame of the motion video, if the comparison is successful, the stressed part is indicated to be positioned in the shooting range of the mobile terminal, and if the comparison is failed, the stressed part is indicated to be not positioned in the shooting range of the mobile terminal.
104. And if the stressed part is positioned in the shooting range of the mobile terminal, acquiring a vibration video of the stressed part according to the motion video.
Specifically, if the stress part is located in the shooting range of the mobile terminal, determining the position of the stress part in the motion video, and then selecting the vibration video of the stress part from the motion video.
105. And determining first vibration information of the stress part according to the vibration video of the stress part.
Specifically, a Lagrange motion amplification method is adopted to process the vibration video of the stressed part so as to obtain a vibration amplification video, and the vibration amplification video is processed so as to obtain first vibration information of the stressed part.
106. And acquiring a first stress condition of the stress part from a digital twin intelligent health prediction model according to the first vibration information, wherein the digital twin intelligent health prediction model stores the analog vibration information of different body parts of the user under different stress conditions.
The digital twin technology is used as a core technology for realizing interactive fusion between the physical world and the information world of manufacturing, and is another technical wind direction besides artificial intelligence, machine learning, AR/VR and blockchain. Digital twinning techniques dynamically present past and present behaviors or processes of a physical entity in a digitized form. As a technology that fully utilizes data, intelligence, and integrates multiple disciplines, digital twin technology provides more real-time, efficient, intelligent services in practicing intelligent manufacturing concepts and goals.
Specifically, the digital twin intelligent health prediction model and the mobile terminal run synchronously, the motion condition of a human body is simulated through the digital twin intelligent health prediction model, whether the motion part is easy to be pulled or not in the body building process can be predicted timely, the spatial graphic processing and the digital twin technology are combined through the digital twin intelligent health prediction method based on vibration detection, the combination of the computer vision technology and the artificial intelligence is realized, and the motion condition of the human body is judged through vibration detection. The digital twin intelligent health prediction model needs to be built in advance, and because heights, weights, sexes, ages, physical conditions, environments and the like of users can be different for different users, when the digital twin intelligent health prediction model is built in advance, human body parameters of the users are firstly acquired through a mobile terminal, the human body parameters of the users are input to generate the digital twin intelligent health prediction model, after the digital twin intelligent health prediction model is built, vibration information of different physical parts of the users under different stress conditions is simulated, and the simulated vibration information is stored in the digital twin intelligent health prediction model.
107. And determining a first risk score of the current action of the user according to the first stress condition.
Specifically, different stress positions of the user have different stress ranges and stress frequencies, if the stress is too large or the stress frequency is too high, the stress positions of the user are likely to be pulled or the body of the user is likely to be damaged, so that the risk degree score of the current action of the user can be determined according to the first stress condition.
For example, when a user performs push-ups, if the frequency of arm movements is too high, muscle strain of the arms is easily caused; for another example, if the height of the buttocks lifted is too high when the user is performing a dynamic buttocks bridge, it is easy to cause damage to the muscle of the waist.
It can be seen that, according to the digital twin intelligent health prediction method based on vibration detection provided by the embodiment of the application, when a health prediction instruction is received, a motion video of a user is collected, a stress part corresponding to the current action of the user is identified based on the motion video of the user, a vibration video of the stress part is obtained according to the motion video, first vibration information of the stress part is determined according to the vibration video of the stress part, a first stress condition of the stress part is obtained from a digital twin intelligent health prediction model according to the first vibration information, and a first risk score of the current action of the user is determined according to the first stress condition. Therefore, when a user exercises, the mobile terminal can acquire the motion video of the user in real time, the mobile terminal processes the motion video of the user to obtain the risk score of the current action of the user, the risk of the current action of the user during exercise is monitored in real time, and when the mobile terminal detects the user, the detection area is large, so that the health prediction requirement of the user in various motion scenes can be met.
Another embodiment of the present application provides another digital twin intelligent health prediction method based on vibration detection, which may include:
201. and when a health prediction instruction is received, acquiring a motion video of the user.
Specifically, when a user exercises, the health prediction function of the mobile terminal can be started, and when the mobile terminal receives a health prediction instruction, the camera is started to collect the motion video of the user.
The mobile terminal may be a mobile phone, a tablet computer, a notebook computer, a mobile internet device, or other types of terminal devices with cameras.
202. And identifying a stress part corresponding to the current action of the user based on the motion video of the user.
In the motion process of a user, the user is subjected to real-time image acquisition through the mobile terminal, and the current action of the user is identified based on the acquired motion video of the user, so that the stress part corresponding to the current action of the user is determined.
Specifically, when the mobile terminal is a mobile phone, the mobile phone interface displays an entrance of a body-building strain prevention function, after a user clicks the body-building strain prevention function, the mobile phone starts a camera to collect real-time body-building images of the user, and in the body-building process of the user, the mobile phone can identify a stressed part corresponding to the current action of the user based on the current action of the user.
203. And judging whether the stressed part is positioned in the shooting range of the mobile terminal.
Specifically, because the positions of the mobile terminals are different, or angles of shooting users of the mobile terminals are different, there are situations that the mobile terminals do not shoot stress parts of the users, so that whether the stress parts are located in the shooting range of the mobile terminals needs to be judged.
In one possible example, the method for determining whether the stress portion is located within the shooting range of the mobile terminal may be: comparing the characteristic points of the stressed part with the characteristic points of each body part of the user in the image frame of the motion video, if the comparison is successful, the stressed part is indicated to be positioned in the shooting range of the mobile terminal, and if the comparison is failed, the stressed part is indicated to be not positioned in the shooting range of the mobile terminal.
204. And if the stressed part is positioned in the shooting range of the mobile terminal, acquiring a vibration video of the stressed part according to the motion video.
Specifically, if the stress part is located in the shooting range of the mobile terminal, determining the position of the stress part in the motion video, and then selecting the vibration video of the stress part from the motion video.
The vibration video of the stress part contains the motion process of the stress part, the motion process is very tiny, and the amplification is needed to be carried out so as to extract the follow-up vibration information. By adopting the Lagrange motion amplification method, the amplification of the micro motion can be realized by tracking motion tracks and clustering of target feature points in the video.
205. And calibrating the image frame of the vibration video of the stressed part to obtain a plurality of stable motion characteristic points.
In one possible example, the method for calibrating the image frame of the vibration video of the stress part to obtain the plurality of motion feature points of the temperature may be: selecting at least one frame of image in the vibration video of the stressed part; determining a reference characteristic point in a relatively static state in a vibration video of the stressed part in a video acquisition process according to the at least one frame of image; each frame of image included in the at least one frame of image is subjected to circular image interception according to N different circle centers to obtain N basic circular partitions, wherein N is an integer greater than 3; selecting a target circular partition from the N basic circular partitions, wherein the target circular partition comprises relative motion characteristic points which are motion characteristic points for relative motion aiming at the reference characteristic points; intercepting the target circular subareas according to a preset window to obtain a plurality of intercepting subareas, wherein the size and the shape of the preset window are determined according to the muscle shape of the stressed part; sequentially acquiring relative motion characteristic points with the motion distance in a preset range from the plurality of intercepting partitions, and accumulating the numerical values of the acquired relative motion characteristic points, wherein the preset range is the vibration amplitude range of the stressed part in a normal stressed state; and when the accumulated value is not smaller than the preset value, determining the acquired relative motion characteristic points as the stable multiple motion characteristic points.
Specifically, the lagrangian amplification method is adopted to amplify the vibration video, and stable multiple motion characteristic points, namely tiny motion points, in the vibration video are needed to be obtained firstly so as to be distinguished from a stationary point (background point) and a violent motion point in the vibration video, wherein the vibration video comprises a plurality of relatively stationary background images besides shooting vibration images, for example, a cross bar supported by the user is the relatively stationary background image when the user makes pull-up, and for example, the ground is the relatively stationary background image when the user makes push-up. And acquiring points on the object in a relatively static state as reference feature points, and extracting a plurality of stable motion feature points in the vibration video according to a preset motion feature point extraction strategy.
It can be seen that not every region contains a moving point for at least one image in the vibration video, and if each region in the image frame is examined one by one, a lot of time is required to obtain a stable moving feature point. Then, a proper partitioning strategy can be adopted to extract motion feature points to improve efficiency.
206. And processing the stable multiple motion characteristic points to obtain a first vibration amplification video.
In one possible example, the method for processing the stable plurality of motion feature points to obtain the first vibration amplified video may be: tracking the plurality of motion feature points to obtain track vectors of the plurality of motion feature points; clustering the track vectors of the motion feature points by adopting a clustering algorithm to obtain K-type motion layers; obtaining a target motion layer needing to be amplified from the K-type motion layer; multiplying the offset distance of the motion feature point in the target motion layer by a magnification to obtain a magnified motion layer; rendering the amplified motion layer to obtain the first vibration amplified video.
Specifically, tracking a plurality of motion feature points to obtain corresponding track vectors, wherein the track vectors describe the motion direction, the motion distance, the brightness change and the like of the motion feature points by using numerical values; and clustering the track vectors of the motion feature points by adopting a clustering algorithm to obtain K-type motion layers, and dividing the K-type motion layers according to the correlation and the similarity of the track vectors so that different motion layers contain different types of motions, and then selecting the motion layer corresponding to the micro motion in the K-type motion layers for amplification processing to obtain the amplified motion layer. Finally, because the image frame corresponding to the target video includes some blank areas due to the enlargement of the motion layer, rendering is needed to fill the image frame.
It can be seen that, in the process of user movement, some vibrations are tiny, if vibration information is directly extracted, accuracy is reduced, and by amplifying the vibrations, the accuracy of vibration information extraction can be improved, so that subsequent processing is facilitated.
207. And acquiring an image frame corresponding to the first vibration amplification video, and calculating the image frame by adopting a phase correlation algorithm to obtain a first cross-power spectrum among the image frames.
The formula for calculating the image frame by adopting the phase correlation algorithm is as follows:
wherein F is a For the fourier transform of an a-frame image,the lower side of the division is the modulo of the correlation product of the two fourier transformed signals, which is the fourier transformed conjugate signal of the b frame image. R is the calculated result cross-power spectrum of the step.
After the cross-over power spectrum is obtained, the cross-over power spectrum contains frequency domain noise, so that the cross-over power spectrum can be subjected to filtering processing, and the signal to noise ratio is improved, so that the accuracy of vibration information extracted later is improved.
Optionally, after calculating the image frames by using a phase correlation algorithm to obtain a cross-power spectrum between the image frames, the method further includes:
acquiring one or more correlation peaks in the cross-over power spectrum, wherein the correlation peaks are frequency domain signals; determining a filtering strategy corresponding to each correlation peak according to the corresponding position of each correlation peak in the vibration video and the frequency band of the correlation peak; and carrying out filtering treatment on each correlation peak according to a filtering strategy corresponding to each correlation peak.
208. And performing inverse Fourier transform on the first cross-power spectrum to obtain first vibration information.
Specifically, the cross-power spectrum reflects vibration information in the frequency domain, and the vibration information needs to be analyzed in the time domain, and then an inverse fourier transform (or an inverse fourier transform) needs to be performed. The inverse fourier transform is performed using the formula:
wherein,the cross-over power spectrum is subjected to inverse Fourier transform, R' is the cross-over power spectrum obtained after filtering processing, and R is vibration information of pixels in a vibration video.
209. And acquiring a first stress condition of the stress part from the digital twin intelligent health prediction model according to the first vibration information.
The digital twin intelligent health prediction model stores the simulated vibration information of different body parts of the user under different stress conditions.
In one possible example, before obtaining the first stress condition of the stress part from the digital twin intelligent health prediction model according to the first vibration information, the method further includes: acquiring human body parameters of a user, wherein the human body parameters comprise any one combination of age, gender, height, weight, body fat rate, heart rate and blood pressure; constructing M part mechanical models corresponding to M body parts of a user according to human body parameters, wherein M is a positive integer, and the M body parts correspond to the M part mechanical models one by one; radial forces are respectively applied to M appointed positions in the M position mechanical models, wherein the M position mechanical models correspond to the M appointed positions one by one, and the radial forces simulate the stress of M body parts; determining M moving distances of the M position mechanical models, wherein the M position mechanical models are in one-to-one correspondence with the M moving distances; and inputting the M moving distances into a preset dynamics algorithm for calculation to obtain M pieces of simulated vibration information of the mechanical models of the M parts.
In particular, the part mechanical model is a virtual body part, i.e. the virtualization of the body part of the user is achieved by using the structural part mechanical model. Further, a site mechanics model is constructed by three-dimensionally scanning the user's body site.
In the step of applying radial forces to M designated positions in the M part mechanical models, the radial forces are friction forces of radial movement, and the radial forces y are uniformly applied to the designated positions in the part mechanical models in the radial direction, so that vibrations from the radial forces are counteracted, and therefore, the friction forces are assumed to move only in the radial direction.
When a radial force is applied to the site mechanics model, the radial force needs to be calculated.
For example, referring to fig. 3, fig. 3 is a schematic view of a part mechanical model according to an embodiment of the present application. Let the unit length be h, the inlet radius be R1 and the outlet radius be R2. Correspondingly, the import and export regions thereofLet t be a unit vector acting on this axial element, n1 and n2 be normal unit vectors for the inlet and outlet, respectively. Assuming that the angle between n1 and n2 is small enough, the mechanical model is considered as a cone or cylinder. Let v1 and v2 be the average of the import and export speeds, respectively. The formula for calculating the radial force applied to the mechanical model of the part is as follows:
Wherein,
this force, calculated in each cell unit of the site, creates all the forces on the site due to cell movement. The relative position of the designated part relative to the position of the axle center point is determined through a scanned Computer Aided Design (CAD) model, and the friction force is related with the vibration model.
In the step of inputting the M moving distances into a preset dynamics algorithm for calculation, the preset dynamics algorithm is as follows:
wherein Is an inertia matrix, ks Is a stiffness matrix, cs Is a coupling matrix, and Mb Is a moment matrix.
Wherein the radial force is represented by the formulaCalculated, can be decomposed into three parts of forces parallel to three axes, and the moments M1, M2 and M3 on the three axes at the designated position are determined to generate a matrix M b ＝[M 1 M 2 M 3 ] T Substituting the preset dynamics algorithm to calculate to obtain angular displacement, further converting the calculated angular displacement into linear displacement by utilizing the fixed distance between the detected area and the designated position, and projecting the linear displacement onto a two-dimensional (Y-Z) plane by using a triangular relation.
The simulated vibration information stored in the digital twin intelligent health prediction model comprises a vibration waveform diagram, a modal diagram and a thermodynamic diagram.
It can be seen that the human body contains a large number of body parts, and the health condition of all the body parts is too complicated to analyze, so that a single mechanical model can be adopted to analyze the motion condition of each body part under different health conditions, and the motion condition of each body part under different conditions is measured to simulate the energy generated by the combined action of the body parts without considering the mutual influence caused by the motion of the body parts. Since the body parts involved in the movement of the human body are substantially stationary, only these body parts mainly involved in the movement are analyzed, thereby reducing the complexity of modeling.
210. And determining a first risk score of the current action of the user according to the first stress condition.
Specifically, different stress positions of the user have different stress ranges and stress frequencies, if the stress is too large or the stress frequency is too high, the stress positions of the user are likely to be pulled or the body of the user is likely to be damaged, so that the risk degree score of the current action of the user can be determined according to the first stress condition.
In one possible example, after determining the first risk score for the current action of the user based on the first stress condition, further comprising: when the first risk score is a muscle strain probability score, judging whether the muscle strain probability score exceeds a preset probability score; if the probability score of the muscle strain exceeds the preset probability score, a first early warning message is sent out, and the first early warning message is used for prompting a user to adjust the movement posture or stop movement so as to avoid strain of the stressed part; when the first risk score is a body function score, judging whether the body function score is lower than a preset score; if the physical function score is lower than the preset score, a second early warning message is sent, and the second early warning message is used for prompting the user to slow down the movement frequency or stop the movement so as to avoid physical damage of the user.
According to the method, the mobile terminal can acquire the motion video of the user in real time when the user exercises, and the mobile terminal processes the motion video of the user to obtain the risk score of the current action of the user, so that the risk of the current action of the user when the user exercises is monitored in real time, and early warning prompt is carried out on the user.
211. If the stress part is not located in the shooting range of the mobile terminal, determining an association part which is associated with the stress part and located in the shooting range of the mobile terminal.
In one possible example, the method for determining the association part which is associated with the stress part and is located within the shooting range of the mobile terminal may be: determining at least one associated location associated with the force-receiving location; judging whether a first associated part positioned in the shooting range of the mobile terminal exists in at least one associated part or not; if the first association part exists, determining the first association part as the association part which is associated with the stress part and is positioned in the shooting range of the mobile terminal; if the mobile terminal does not exist, starting a wide-angle shooting mode to enable a second associated part which is located in the shooting range of the mobile terminal to exist in at least one associated part; and determining the second association part as an association part which is associated with the stress part and is positioned in the shooting range of the mobile terminal.
It can be seen that when the stress part is not located in the shooting range of the mobile terminal, the relevant part of the stress part located in the shooting range can be determined, or the wide-angle shooting mode is started to determine the relevant part of the stress part located in the shooting range, so that the vibration information of the stress part can be determined according to the vibration information of the relevant part.
In another possible example, if the stress part is within the shooting range of the mobile terminal, the clothing feature of the user needs to be identified, so as to determine whether the vibration video of the stress part can be accurately acquired, if the clothing feature of the user at the stress part is identified to cover the vibration feature of the stress part, the vibration video of the stress part cannot be accurately acquired, then the relevant part which is related to the stress part and can accurately acquire the vibration video needs to be redetermined within the shooting range of the mobile terminal, and based on the position of the relevant part, the vibration video of the relevant part is acquired.
212. And obtaining vibration videos of the associated parts according to the motion videos.
213. And determining vibration information of the associated part according to the vibration video of the associated part.
214. And obtaining second vibration information of the stressed part according to the vibration information of the associated part.
215. And obtaining a second stress condition of the stress part from the digital twin intelligent health prediction model according to the second vibration information.
216. And determining a second risk score of the current action of the user according to the second stress condition.
It can be seen that in the embodiment of the application, a motion video of a user in a body building process is acquired through a mobile terminal, a stress part is confirmed, vibration information of the stress part is obtained according to whether the stress part is processed differently in a shooting range of the mobile terminal, the vibration information of the stress part is compared with simulated vibration information of the stress part under an unstressed condition stored in a digital twin intelligent health prediction model, so that stress condition of the stress part is determined, and therefore, risk degree scores of current actions of the user are determined, and early warning is carried out on the user according to the risk degree scores. Therefore, when the exercise action of the user is overlarge in amplitude, too high in frequency or wrong in posture, the user can be warned and prompted, so that the risk of the current action of the user during exercise is detected in real time, the exercise action of the user is normalized, and negative effects on physical health are avoided.
Referring to fig. 5, fig. 5 is a schematic diagram of elbow movement of a user according to an embodiment of the present application. As shown in fig. 5, when a user performs elbow exercise, for example, the user performs elbow exercise, the elbow is in a repeated process of bending and straightening the biceps brachii, when the user straightens the elbow, the elbow joint part is from the elbow 1 shown in fig. 5, during the exercise, the elbow joint part is from the elbow 2 and the elbow 3 shown in fig. 5, when the user bends the elbow, the elbow joint part is from the elbow 4 shown in fig. 5, and when the user performs elbow exercise, the elbow joint part regularly vibrates, so that vibration videos of the elbow joint part can be obtained through a terminal such as a mobile phone of the user, so that the vibration videos can be analyzed, whether the exercise action of the user is standard or not is judged, and whether the elbow joint damage can be caused.
Referring to fig. 2, fig. 2 is a schematic diagram of a digital twin intelligent health prediction device based on vibration detection according to another embodiment of the present application. As shown in fig. 2, a digital twin intelligent health prediction device based on vibration detection according to another embodiment of the present application may include:
the acquisition unit 201 is used for acquiring a motion video of a user when a health prediction instruction is received;
an identifying unit 202, configured to identify a stress location corresponding to a current action of the user based on the motion video of the user;
a judging unit 203, configured to judge whether the stressed portion is located within a shooting range of the mobile terminal;
a first obtaining unit 204, configured to obtain a vibration video of the stress portion according to the motion video if the stress portion is located in a shooting range of the mobile terminal;
a first determining unit 205, configured to determine first vibration information of the force receiving portion according to a vibration video of the force receiving portion;
the second obtaining unit 206 obtains the first stress condition of the stress part from a digital twin intelligent health prediction model according to the first vibration information, where the digital twin intelligent health prediction model stores the simulated vibration information of different body parts of the user under different stress conditions;
A second determining unit 207, configured to determine a first risk score of the current action of the user according to the first stress condition.
The specific implementation of the digital twin intelligent health prediction device based on vibration detection in the embodiment of the present application can be found in each embodiment of the above-mentioned digital twin intelligent health prediction method based on vibration detection, and will not be described herein.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a mobile terminal according to an embodiment of the present application. As shown in fig. 4, a mobile terminal provided in an embodiment of the present application may include:
a processor 401, such as a CPU.
The memory 402 may alternatively be a high-speed RAM memory or a stable memory, such as a disk memory.
A communication interface 403 for enabling a connected communication between the processor 401 and the memory 402.
Those skilled in the art will appreciate that the structure of the mobile terminal shown in fig. 4 is not limiting of the mobile terminal and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 4, memory 402 may include an operating system, a network communication module, and a program for health prediction. The operating system is a program that manages and controls the mobile terminal hardware and software resources, programs that support health prediction, and other software or program runs. The network communication module is used to enable communication between components within the memory 402 and with other hardware and software in the mobile terminal.
In the mobile terminal shown in fig. 4, the processor 401 is configured to execute a program for health prediction stored in the memory 402, and the following steps are implemented:
when a health prediction instruction is received, acquiring a motion video of a user;
identifying a stress part corresponding to the current action of the user based on the motion video of the user;
judging whether the stressed part is positioned in the shooting range of the mobile terminal or not;
if the stressed part is positioned in the shooting range of the mobile terminal, acquiring a vibration video of the stressed part according to the motion video;
determining first vibration information of the stress part according to the vibration video of the stress part;
acquiring a first stress condition of the stress part from a digital twin intelligent health prediction model according to the first vibration information, wherein the digital twin intelligent health prediction model stores analog vibration information of different body parts of the user under different stress conditions;
and determining a first risk score of the current action of the user according to the first stress condition.
The specific implementation of the mobile terminal provided by the embodiment of the present application can be found in each embodiment of the above-mentioned digital twin intelligent health prediction method based on vibration detection, and will not be described herein.
Another embodiment of the present application provides a computer-readable storage medium storing a computer program that is executed by a processor to implement the steps of:
when a health prediction instruction is received, acquiring a motion video of a user;
identifying a stress part corresponding to the current action of the user based on the motion video of the user;
judging whether the stressed part is positioned in the shooting range of the mobile terminal or not;
if the stressed part is positioned in the shooting range of the mobile terminal, acquiring a vibration video of the stressed part according to the motion video;
determining first vibration information of the stress part according to the vibration video of the stress part;
acquiring a first stress condition of the stress part from a digital twin intelligent health prediction model according to the first vibration information, wherein the digital twin intelligent health prediction model stores analog vibration information of different body parts of the user under different stress conditions;
and determining a first risk score of the current action of the user according to the first stress condition.
The embodiment of the computer readable storage medium of the present application can be seen from the above embodiments of the digital twin intelligent health prediction method based on vibration detection, and will not be described herein.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application. In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application.
Claims (9)
1. A digital twin intelligent health prediction method based on vibration detection, characterized in that the method is applied to a mobile terminal, the mobile terminal comprises a camera, the method comprises:
when a health prediction instruction is received, acquiring a motion video of a user;
identifying a stress part corresponding to the current action of the user based on the motion video of the user;
judging whether the stressed part is positioned in the shooting range of the mobile terminal or not;
if the stressed part is positioned in the shooting range of the mobile terminal, acquiring a vibration video of the stressed part according to the motion video;
calibrating an image frame of the vibration video of the stress part to obtain a plurality of stable motion characteristic points;
tracking the plurality of motion feature points to obtain track vectors of the plurality of motion feature points;
clustering the track vectors of the motion feature points by adopting a clustering algorithm to obtain K-type motion layers;
obtaining a target motion layer needing to be amplified from the K-type motion layer;
multiplying the offset distance of the motion feature points in the target motion layer by a magnification to obtain a magnified motion layer;
Rendering the amplified motion layer to obtain a first vibration amplified video;
acquiring an image frame corresponding to the first vibration amplification video, and calculating the image frame by adopting a phase correlation algorithm to obtain a first cross power spectrum among the image frames;
performing inverse Fourier transform on the first cross-power spectrum to obtain first vibration information;
acquiring a first stress condition of the stress part from a digital twin intelligent health prediction model according to the first vibration information, wherein the digital twin intelligent health prediction model stores analog vibration information of different body parts of the user under different stress conditions;
and determining a first risk score of the current action of the user according to the first stress condition.
2. The method of claim 1, wherein calibrating the image frames of the vibration video of the force-receiving portion to obtain stable plurality of motion feature points comprises:
selecting at least one frame of image in the vibration video of the stress part;
determining a reference characteristic point which is in a relatively static state in a video acquisition process in a vibration video of the stressed part according to the at least one frame of image;
Each frame of image included in at least one frame of image is subjected to circular image interception according to N different circle centers to obtain N basic circular partitions, wherein N is an integer greater than 3;
selecting a target circular partition from the N basic circular partitions, wherein the target circular partition comprises relative motion characteristic points which are motion characteristic points for relative motion aiming at the reference characteristic points;
intercepting the target circular subareas according to a preset window to obtain a plurality of intercepting subareas, wherein the size and the shape of the preset window are determined according to the muscle morphology of the stressed part;
sequentially acquiring relative motion characteristic points with the motion distance in a preset range from the plurality of intercepting partitions, and accumulating the numerical values of the acquired relative motion characteristic points, wherein the preset range is the vibration amplitude range of the stressed part in a normal stressed state;
and when the accumulated value is not smaller than the preset value, determining the acquired relative motion characteristic points as the stable multiple motion characteristic points.
3. The method according to claim 1 or 2, characterized in that the method further comprises:
if the stress part is not located in the shooting range of the mobile terminal, determining an associated part which is associated with the stress part and located in the shooting range of the mobile terminal;
Acquiring a vibration video of the associated part according to the motion video;
determining vibration information of the associated part according to the vibration video of the associated part;
obtaining second vibration information of the stressed part according to the vibration information of the associated part;
acquiring a second stress condition of the stress part from a digital twin intelligent health prediction model according to the second vibration information;
and determining a second risk score of the current action of the user according to the second stress condition.
4. A method according to claim 3, wherein the determining an associated location associated with the force-receiving location and located within the shooting range of the mobile terminal comprises:
determining at least one associated location associated with the force-receiving location;
judging whether a first associated part positioned in the shooting range of the mobile terminal exists in the at least one associated part or not;
if the first association part exists, determining the first association part as the association part which is associated with the stress part and is positioned in the shooting range of the mobile terminal;
if the mobile terminal does not exist, starting a wide-angle shooting mode to enable a second associated part which is located in the shooting range of the mobile terminal to exist in the at least one associated part;
And determining the second association part as an association part which is associated with the stress part and is positioned in the shooting range of the mobile terminal.
5. The method of claim 1, wherein prior to obtaining the first stress condition of the stress location from a digital twin intelligent health prediction model based on the first vibration information, the method further comprises:
acquiring human body parameters of the user, wherein the human body parameters comprise any one combination of age, gender, height, weight, body fat rate, heart rate and blood pressure;
constructing M part mechanical models corresponding to M body parts of the user according to the human body parameters, wherein M is a positive integer, and the M body parts are in one-to-one correspondence with the M part mechanical models;
radial forces are respectively applied to M appointed positions in the M position mechanical models, wherein the M position mechanical models are in one-to-one correspondence with the M appointed positions, and the radial forces simulate the stress of the M body parts;
determining M moving distances of the M position mechanical models, wherein the M position mechanical models are in one-to-one correspondence with the M moving distances;
And inputting the M moving distances into a preset dynamics algorithm for calculation to obtain M pieces of simulated vibration information of the M part mechanical models.
6. The method of claim 1, wherein after determining a first risk score for the user's current action based on the first force condition, the method further comprises:
when the first risk score is a muscle strain probability score, judging whether the muscle strain probability score exceeds a preset probability score;
if the muscle strain probability score exceeds the preset probability score, a first early warning message is sent out, and the first early warning message is used for prompting the user to adjust the movement posture or stop movement so as to avoid strain of the stressed part;
when the first risk score is a body function score, judging whether the body function score is lower than a preset score;
and if the physical function score is lower than the preset score, sending a second early warning message, wherein the second early warning message is used for prompting the user to slow down the movement frequency or stop the movement so as to avoid the physical damage of the user.
7. A digital twin intelligent health prediction device based on vibration detection, the device comprising:
The acquisition unit is used for acquiring a motion video of a user when a health prediction instruction is received;
the identification unit is used for identifying a stress part corresponding to the current action of the user based on the motion video of the user;
the judging unit is used for judging whether the stressed part is positioned in the shooting range of the mobile terminal;
the first acquisition unit is used for acquiring a vibration video of the stress part according to the motion video if the stress part is positioned in the shooting range of the mobile terminal;
the first determining unit is used for calibrating the image frames of the vibration video of the stress part so as to obtain a plurality of stable motion characteristic points; tracking the plurality of motion feature points to obtain track vectors of the plurality of motion feature points; clustering the track vectors of the motion feature points by adopting a clustering algorithm to obtain K-type motion layers; obtaining a target motion layer needing to be amplified from the K-type motion layer; multiplying the offset distance of the motion feature points in the target motion layer by a magnification to obtain a magnified motion layer; rendering the amplified motion layer to obtain a first vibration amplified video; acquiring an image frame corresponding to the first vibration amplification video, and calculating the image frame by adopting a phase correlation algorithm to obtain a first cross power spectrum among the image frames; performing inverse Fourier transform on the first cross-power spectrum to obtain first vibration information;
The second acquisition unit acquires a first stress condition of the stress part from a digital twin intelligent health prediction model according to the first vibration information, and the digital twin intelligent health prediction model stores simulation vibration information of different body parts of the user under different stress conditions;
and the second determining unit is used for determining a first risk score of the current action of the user according to the first stress condition.
8. A mobile terminal comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the method of any of claims 1 to 6.
9. A computer readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to perform the method of any one of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910819837.1A CN110600132B (en) | 2019-08-31 | 2019-08-31 | Digital twin intelligent health prediction method and device based on vibration detection |
| PCT/CN2020/104822 WO2021036635A1 (en) | 2019-08-31 | 2020-07-27 | Digital twin intelligent health prediction method and device based on vibration detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910819837.1A CN110600132B (en) | 2019-08-31 | 2019-08-31 | Digital twin intelligent health prediction method and device based on vibration detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110600132A CN110600132A (en) | 2019-12-20 |
| CN110600132B true CN110600132B (en) | 2023-12-15 |
Family
ID=68856704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910819837.1A Active CN110600132B (en) | 2019-08-31 | 2019-08-31 | Digital twin intelligent health prediction method and device based on vibration detection |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110600132B (en) |
| WO (1) | WO2021036635A1 (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110600132B (en) * | 2019-08-31 | 2023-12-15 | 深圳市广宁股份有限公司 | Digital twin intelligent health prediction method and device based on vibration detection |
| CN112132955B (en) * | 2020-09-01 | 2024-02-06 | 大连理工大学 | Method for constructing digital twin body of human skeleton |
| CN114822849B (en) * | 2022-05-06 | 2023-09-05 | 深圳市第二人民医院(深圳市转化医学研究院) | Digital twinning-based data monitoring method, device, equipment and storage medium |
| CN114918976B (en) * | 2022-06-16 | 2022-12-02 | 慧之安信息技术股份有限公司 | Joint robot health state assessment method based on digital twinning technology |
| CN114968162B (en) * | 2022-06-20 | 2023-08-01 | 阿维塔科技(重庆)有限公司 | Information display method and device for vehicle-mounted food |
| CN115597659B (en) * | 2022-09-21 | 2023-04-14 | 山东锐翊电力工程有限公司 | Intelligent safety management and control method for transformer substation |
| CN115543094B (en) * | 2022-11-28 | 2023-05-30 | 杭州轻宇宙科技有限公司 | Interaction method, system and electronic equipment of digital twin virtual person and human body |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448815A (en) * | 2018-11-28 | 2019-03-08 | 平安科技（深圳）有限公司 | Self-service body building method, device, computer equipment and storage medium |
| CN109621331A (en) * | 2018-12-13 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Fitness-assisting method, apparatus and storage medium, server |
| CN109635644A (en) * | 2018-11-01 | 2019-04-16 | 北京健康有益科技有限公司 | A kind of evaluation method of user action, device and readable medium |
| CN109819233A (en) * | 2019-01-21 | 2019-05-28 | 哈工大机器人（合肥）国际创新研究院 | A kind of digital twinned system based on virtual image technology |
| CN110090012A (en) * | 2019-03-15 | 2019-08-06 | 上海图灵医疗科技有限公司 | A kind of human body diseases detection method and testing product based on machine learning |
| CN110189363A (en) * | 2019-05-30 | 2019-08-30 | 南京林业大学 | A kind of low multi-view video speed-measuring method of the mobile target of airdrome scene |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101665386B1 (en) * | 2010-11-15 | 2016-10-12 | 한화테크윈 주식회사 | Method and apparatus for estimating position in a mobile robot |
| US20180011389A1 (en) * | 2016-07-11 | 2018-01-11 | Petrica-Sandel Baciu | Modular Instant and Digital Back for Film TLR Cameras |
| US20190005200A1 (en) * | 2017-06-28 | 2019-01-03 | General Electric Company | Methods and systems for generating a patient digital twin |
| CN110109532A (en) * | 2018-06-11 | 2019-08-09 | 成都思悟革科技有限公司 | A kind of human action Compare System obtaining system based on human body attitude |
| CN109453497B (en) * | 2018-09-30 | 2021-02-05 | 深圳市科迈爱康科技有限公司 | Interactive training method, system and computer readable storage medium |
| CN110045608B (en) * | 2019-04-02 | 2022-04-05 | 太原理工大学 | Mechanical equipment part structure parameter dynamic optimization method based on digital twinning |
| CN110600132B (en) * | 2019-08-31 | 2023-12-15 | 深圳市广宁股份有限公司 | Digital twin intelligent health prediction method and device based on vibration detection |
-
2019
- 2019-08-31 CN CN201910819837.1A patent/CN110600132B/en active Active
-
2020
- 2020-07-27 WO PCT/CN2020/104822 patent/WO2021036635A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109635644A (en) * | 2018-11-01 | 2019-04-16 | 北京健康有益科技有限公司 | A kind of evaluation method of user action, device and readable medium |
| CN109448815A (en) * | 2018-11-28 | 2019-03-08 | 平安科技（深圳）有限公司 | Self-service body building method, device, computer equipment and storage medium |
| CN109621331A (en) * | 2018-12-13 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Fitness-assisting method, apparatus and storage medium, server |
| CN109819233A (en) * | 2019-01-21 | 2019-05-28 | 哈工大机器人（合肥）国际创新研究院 | A kind of digital twinned system based on virtual image technology |
| CN110090012A (en) * | 2019-03-15 | 2019-08-06 | 上海图灵医疗科技有限公司 | A kind of human body diseases detection method and testing product based on machine learning |
| CN110189363A (en) * | 2019-05-30 | 2019-08-30 | 南京林业大学 | A kind of low multi-view video speed-measuring method of the mobile target of airdrome scene |
Non-Patent Citations (2)
| Title |
|---|
| 基于聚类和α-β-γ滤波的运动跟踪;包晓敏;汪亚明;郝保明;;测试技术学报(第04期);全文 * |
| 数字孪生及其应用跟踪;廖晓红;《广东通信技术》;20190731(第07期);正文第38页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110600132A (en) | 2019-12-20 |
| WO2021036635A1 (en) | 2021-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110600132B (en) | Digital twin intelligent health prediction method and device based on vibration detection | |
| WO2021057810A1 (en) | Data processing method, data training method, data identifying method and device, and storage medium | |
| Javeed et al. | Wearable sensors based exertion recognition using statistical features and random forest for physical healthcare monitoring | |
| EP3753489B1 (en) | Monitoring the performance of physical exercises | |
| CN108875510A (en) | Method, apparatus, system and the computer storage medium of image procossing | |
| Wang et al. | Fall detection based on dual-channel feature integration | |
| JP7160932B2 (en) | Generating prescriptive analytics using motion identification and motion information | |
| US8175326B2 (en) | Automated scoring system for athletics | |
| CN109214366A (en) | Localized target recognition methods, apparatus and system again | |
| CN114724241A (en) | Motion recognition method, device, equipment and storage medium based on skeleton point distance | |
| JP2008168133A (en) | Method, system and program for tracking range of user's body movement | |
| WO2021190321A1 (en) | Image processing method and device | |
| CN111507301B (en) | Video processing method, video processing device, computer equipment and storage medium | |
| CN110751039A (en) | Multi-view 3D human body posture estimation method and related device | |
| CN110287848A (en) | The generation method and device of video | |
| WO2024060978A1 (en) | Key point detection model training method and apparatus and virtual character driving method and apparatus | |
| CN114049683A (en) | Post-healing rehabilitation auxiliary detection system, method and medium based on three-dimensional human skeleton model | |
| CN108875506A (en) | Face shape point-tracking method, device and system and storage medium | |
| CN113392743B (en) | Abnormal action detection method, abnormal action detection device, electronic equipment and computer storage medium | |
| CN110314344B (en) | Exercise reminding method, device and system | |
| CN115035037A (en) | Limb rehabilitation training method and system based on image processing and multi-feature fusion | |
| CN114343618A (en) | Training motion detection method and device | |
| Wu et al. | Video-based fall detection using human pose and constrained generative adversarial network | |
| CN113553893A (en) | Human body falling detection method and device based on deep neural network and electronic equipment | |
| Wang | Research on the evaluation of sports training effect based on artificial intelligence technology |
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 |