CN108242260A - A kind of body-building monitoring method and device - Google Patents
A kind of body-building monitoring method and device Download PDFInfo
- Publication number
- CN108242260A CN108242260A CN201611216325.9A CN201611216325A CN108242260A CN 108242260 A CN108242260 A CN 108242260A CN 201611216325 A CN201611216325 A CN 201611216325A CN 108242260 A CN108242260 A CN 108242260A
- Authority
- CN
- China
- Prior art keywords
- action
- data
- action classification
- classification
- physiological index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention provides a kind of body-building monitoring method and device, wherein, the body-building monitoring method includes：User is obtained in body-building with a corresponding data of physiological index of action and exercise data, according to the data of physiological index and exercise data, the action classification belonging to the action is determined, based on the action classification belonging to the action, the user is reminded.The solution of the present invention can carry out different promptings based on user and the body-building corresponding data of physiological index of action and exercise data under different action classifications, realize to body-building action whether comprehensive reliable monitoring of standard.
Description
Technical field
The present invention relates to wearable device technical field more particularly to a kind of body-building monitoring method and devices.
Background technology
Due to the limitation of time, space, expense etc., current people can be seldom selected in body-building when selecting physical training style
Carry out body-building under the accompanying of Fang coaches, and the physical training style usually selected is based on video class or picture category application program, mould
The action and combination trained in imitative video or picture, which explain, carries out body-building.
At this moment, since people will appear deviation to the understanding for receiving information, so when body builder is based on application program
When carrying out body-building, it sometimes appear that be standard with the action for oneself, but actually and non-type situation, body-building is caused to be imitated
Fruit is bad.Also, the body-building effect that non-type body-building action has not only been not achieved is also easy to make body builder injured.
During traditional health effect monitoring, often passed using wearable device, such as the displacement that forearm and postbrachium are worn
The moving situation of the rough monitoring body builder such as sensor, Intelligent bracelet, and whether standard is without comprehensively reliable for body-building action
Monitoring.
Invention content
The purpose of the present invention is to provide a kind of body-building monitoring method and device, with action that can be to user in body-building
Whether standard carries out reliable monitoring comprehensively.
In order to realize above-mentioned purpose, on the one hand, the present invention provides a kind of body-building monitoring method, including：
Obtain user in body-building with a corresponding data of physiological index of action and exercise data；
According to the data of physiological index and exercise data, the action classification belonging to the action, the action class are determined
Whether standard is not related to the action；
Based on the action classification belonging to the action, the user is reminded.
Preferably, it is described according to the data of physiological index and exercise data, determine the action classification belonging to the action
The step of, including：
Using at least one action classification disaggregated model, the data of physiological index and exercise data are handled, really
Under fixed each action classification disaggregated model, the possibility action classification belonging to the action；
Possibility action classification belonging to the action is counted, the most possibility action classification of statistics number is chosen and makees
For the action classification belonging to the action.
Preferably, it is described acquisition user in body-building with a corresponding data of physiological index of action and exercise data the step of
Before, the body-building monitoring method further includes：
Determine at least one action classification training dataset of the user and base categories model, each action classification instruction
Practice data set and include multigroup data for being divided into two class action classifications, every group of data are the use under a kind of action classification
The data of physiological index and exercise data at family, the base categories model are used to embody data of physiological index, exercise data and move
Make the incidence relation between classification；
It is trained, obtained described using base categories model described at least one action classification training data set pair
At least one action classification disaggregated model.
Preferably, the action classification belonging to based on the action, the step of prompting the user, including：
Based on the action classification belonging to the action, indicating mode corresponding with the action classification is determined；
According to the determining indicating mode, the user is reminded.
Preferably, the action classification belonging to the action is movement range standard, movement range is not up to standard or action
Amplitude is above standard.
Preferably, the data of physiological index includes at least one of following data：Pulse rate, heart rate variability number
Value, body temperature numerical value and myoelectricity numerical value.
Preferably, the exercise data includes at least one of following data：Moving displacement, movement angle and arc of motion
Degree.
On the other hand, the present invention also provides a kind of body-building monitoring device, including：
Acquisition module, for obtain user in body-building with a corresponding data of physiological index of action and exercise data；
Determining module, for according to the data of physiological index and exercise data, determining the action class belonging to the action
Not, whether standard is related to the action for the action classification；
Reminding module for the action classification belonging to based on the action, reminds the user.
Preferably, the determining module includes：
Processing unit, for utilizing at least one action classification disaggregated model, to the data of physiological index and movement number
It according to being handled, determines under each action classification disaggregated model, the possibility action classification belonging to the action；
For being counted to the possibility action classification belonging to the action, it is most to choose statistics number for statistic unit
Action classification of the possible action classification belonging to as the action.
Preferably, the body-building monitoring device further includes：
Determining module, for determining at least one action classification training dataset of the user and base categories model,
Each action classification training data concentration includes multigroup data for being divided into two class action classifications, and every group of data are acted to be a kind of
The data of physiological index and exercise data of the user of classification, the base categories model for embody data of physiological index,
Incidence relation between exercise data and action classification；
Training module, for being carried out using base categories model described at least one action classification training data set pair
Training, obtains at least one action classification disaggregated model.
Preferably, the reminding module includes：
Determination unit for the action classification belonging to based on the action, determines prompting corresponding with the action classification
Pattern；
Reminding unit, for according to the determining indicating mode, reminding the user.
Preferably, the action classification belonging to the action is movement range standard, movement range is not up to standard or action
Amplitude is above standard.
Preferably, the data of physiological index includes at least one of following data：Pulse rate, heart rate variability number
Value, body temperature numerical value and myoelectricity numerical value.
Preferably, the exercise data includes at least one of following data：Moving displacement, movement angle and arc of motion
Degree.
The present invention body-building monitoring method, by obtain user in body-building with a corresponding data of physiological index of action and
Exercise data according to the data of physiological index and exercise data, determines the action classification belonging to the action, based on described dynamic
Action classification belonging to making, reminds the user, can be based on user's physical signs number corresponding with body-building action
According to and exercise data, different promptings is carried out under different action classifications, realize to body-building action whether standard it is comprehensive reliable
Monitoring.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, it will make below to required in the embodiment of the present invention
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present invention, for
For those of ordinary skill in the art, without having to pay creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 shows the flow charts of the body-building monitoring method of first embodiment of the invention.
Fig. 2 represents the flow chart of the body-building monitoring method of second embodiment of the invention.
Fig. 3 represents the structure diagram of the body-building monitoring device of third embodiment of the invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is part of the embodiment of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained without creative efforts
Example, shall fall within the protection scope of the present invention.
First embodiment
Shown in Figure 1, first embodiment of the invention provides a kind of body-building monitoring method, includes the following steps 101 to step
Rapid 103, details are as follows.
Step 101：Obtain user in body-building with a corresponding data of physiological index of action and exercise data.
In the embodiment of the present invention, which includes but not limited at least one of following data：Pulse
Number, heart rate variability numerical value, body temperature numerical value and myoelectricity numerical value etc..The exercise data includes but not limited in following data at least
It is a kind of：Moving displacement, movement angle and movement radian etc..
It wherein, can be by acquisitions such as the sports type bracelets that user wears in the data of physiological index for obtaining user.The fortune
Ejector half bracelet can monitor pulse, heart rate variability, body temperature and myoelectricity numerical value of relative users etc. in real time.In the movement for obtaining user
During data, the acquisitions such as each sensor of body key position can be worn on by user.The sensor worn by user, can
The monitoring moving displacement (such as relative displacement between body key position) of relative users, movement angle (such as body in real time
Angle between key position) and movement radian etc..
Step 102：According to the data of physiological index and exercise data, the action classification belonging to the action, institute are determined
Stating action classification, whether standard is related to the action.
In the embodiment of the present invention, the action classification belonging to the action be according to data of physiological index corresponding with the action and
What exercise data determined.In general, the action classification is to corresponding actions, whether standard is related, can embody whether corresponding actions reach pre-
The movement effects of phase.Only in the case of action criteria, movement effects just can be best.If action is nonstandard, not only it is not achieved
Expected movement effects, it is also possible to bring danger to user, such as muscle injury etc..
Specifically, the action classification belonging to the action can be not up to standard or dynamic for movement range standard, movement range
It is above standard as amplitude, or action is in place, action is not in place or action is too quickly, and the present invention is not limited.
Step 103：Based on the action classification belonging to the action, the user is reminded.
In the embodiment of the present invention, the mode reminded user can be vibration, the tinkle of bells etc., and the present invention does not limit it
System.
And the action classification belonging to based on action, user, which is reminded, to be specially：
Based on the action classification belonging to the action, indicating mode corresponding with the action classification is determined；
According to the determining indicating mode, the user is reminded.
In this way, different action classifications uses different indicating modes, family can be used to understand the state of current action in time,
And it is non-type in the case that acting, it makes correctly action and corrects, realize the monitoring to body-building effect and exercise guide.
For example, the correspondence between preset type of action and indicating mode is：
Movement range standard~without friction；
Movement range be not up to standard~with the first oscillation intensity vibrate；
Movement range is above standard~is vibrated with the second oscillation intensity；Wherein, it is strong to be more than the first vibration for the second oscillation intensity
Degree.
In this case, when it is movement range standard to determine action classification, prompting without friction family can be used to understand current
The movement range standard of action, without correcting；It is strong with the first vibration when determining that action classification is not up to standard for movement range
Degree carries out vibrating alert, and the movement range that family understands current action can be used to be not up to standard, to increase movement range；It is determining
When action classification is above standard for movement range, vibrating alert is carried out with the second oscillation intensity, family can be used to understand current action
Movement range be above standard, suitably to reduce movement range.
The body-building monitoring method of first embodiment of the invention, by obtain user in body-building with the corresponding physiology of action
Achievement data and exercise data according to the data of physiological index and exercise data, determine the action classification belonging to the action,
Based on the action classification belonging to the action, the user is reminded, it can be corresponding with body-building action based on user
Data of physiological index and exercise data carry out different promptings under different action classifications, realize to body-building action whether standard
Comprehensive reliable monitoring.
Second embodiment
Shown in Figure 2, second embodiment of the invention provides a kind of body-building monitoring method, includes the following steps 201 to step
Rapid 206, details are as follows.
Step 201：Determine at least one action classification training dataset of user and base categories model.
In the embodiment of the present invention, each action classification training data concentration includes multigroup two class action classifications that are divided into
Data, every group of data are the data of physiological index and exercise data of the user under a kind of action classification.Determining action class
During other training dataset, can data of physiological index of the user under every class action classification be recorded by the observation of fitness
And exercise data, so as to form the data set for training base categories model.
The base categories model is used to embody the incidence relation between data of physiological index, exercise data and action classification,
The base categories model can be analyzed the unknown pattern of input based on known classificating knowledge, to determine the class of input
Belong to.Specifically, for the base categories model, the data of physiological index and exercise data are input, and corresponding action classification is
Output.The base categories model is to pre-establish, and can be the support vector machines using the progress two classification of RBF kernel functions
(Support Vector Machine, abbreviation SVM) disaggregated model, certain embodiment of the present invention can also use other machines
Practise the identification that model carries out action classification.
When pre-establishing base categories model, if the data parameters that include of the data of physiological index and exercise data compared with
It is more, in order to reduce data redundancy, principal component analysis (Principal Component Analysis, abbreviation PCA) calculation can be used
Method carries out dimensionality reduction, and preserve corresponding covariance matrix and dimension to data parameters, is used for subsequent model training.
For example, the data of physiological index includes 4 data parameters, i.e. pulse rate, heart rate variability numerical value, body temperature numerical value
With myoelectricity numerical value, which includes 3 data parameters, i.e. moving displacement, movement angle and movement radian, then, the base
Plinth disaggregated model, which can be related to 7 data parameters i.e. 7, to be tieed up, and because the dimension being related to is more, PCA algorithms can be used and carry out dimensionality reduction, such as
It is reduced to 6 dimensions.Existing common method can be used in specific reduction process, and details are not described herein.
Step 202：It is trained using base categories model described at least one action classification training data set pair,
Obtain at least one action classification disaggregated model.
In the embodiment of the present invention, when using action classification training dataset training base categories model, to refer to advance
Processing when establishing base categories model to data parameters, such as reduction process, to ensure the accurate of the disaggregated model trained
Property.
Step 203：Obtain the user in body-building with a corresponding data of physiological index of action and exercise data.
In the embodiment of the present invention, which includes but not limited at least one of following data：Pulse
Number, heart rate variability numerical value, body temperature numerical value and myoelectricity numerical value etc..The exercise data includes but not limited in following data at least
It is a kind of：Moving displacement, movement angle and movement radian etc..
Step 204：Using at least one action classification disaggregated model, to the data of physiological index and exercise data
It is handled, is determined under each action classification disaggregated model, the possibility action classification belonging to the action.
In the embodiment of the present invention, the action classification disaggregated model is corresponding with an action by pair for carrying out two classification
Data of physiological index and exercise data processing, it may be determined which kind of action classification the action belongs to.
Wherein, whether standard is related to the action for the possibility action classification belonging to the action.The possible action classification can be with
Be not up to standard for movement range standard, movement range or movement range be above standard, or action in place, action less than
Position or action are too quickly.
Step 205：Possibility action classification belonging to the action is counted, choose statistics number it is most can be active
Make action classification of the classification belonging to as the action.
In the embodiment of the present invention, by least one action classification disaggregated model, determine to move in a manner that ballot counts
Action classification belonging to making can improve the accuracy for differentiating type of action, promote the monitoring effect of body-building.
For example, action classification has 3 classes, respectively classification 1, classification 2 and classification 3, action classification disaggregated model has 3, point
It Wei not disaggregated model 1, disaggregated model 2 and disaggregated model 3；If determine the possibility action classification belonging to action D using disaggregated model 1
For classification 1, determine that the possibility action classification belonging to action D is classification 2 using disaggregated model 2, action is determined using disaggregated model 3
Possibility action classification belonging to D is classification 1, then can choose the action classification of " classification 1 " belonging to as action D.
Step 206：Based on the action classification belonging to the action, the user is reminded.
In the embodiment of the present invention, the mode reminded user can be vibration, the tinkle of bells etc., and the present invention does not limit it
System.
And the action classification belonging to based on action, user, which is reminded, to be specially：
Based on the action classification belonging to the action, indicating mode corresponding with the action classification is determined；
According to the determining indicating mode, the user is reminded.
In this way, different action classifications uses different indicating modes, family can be used to understand the state of current action in time,
And it is non-type in the case that acting, it makes correctly action and corrects, realize the monitoring to body-building effect and exercise guide.
In the following, for lifting the dumbbell, the body-building monitoring method of the specific embodiment of the invention is illustrated.
Wherein, the body-building monitoring method of the specific embodiment is broadly divided into three steps, and details are as follows：
Step 1：Establish base categories model
Based on the data of physiological index and exercise data of experiment body builder, the association relation model with action classification is established,
That is base categories model.The data of physiological index includes pulse rate, heart rate variability numerical value, body temperature numerical value and myoelectricity numerical value,
The sports type bracelet worn by experiment body builder when lifting the dumbbell obtains.The exercise data includes moving displacement, movement angle
With movement radian, the sensor for being worn on key position when lifting the dumbbell by experiment body builder obtains.The action classification has three
Class respectively acts (action classification 1), action (action classification 2) not in place in place and acts too quickly (action classification 3).
When establishing base categories model, first, by the observation of fitness, record experiment body builder is when lifting the dumbbell
In action in place, action is not in place or the data of physiological index and exercise data of the too quickly state of action, obtain 3 kinds of data samples
Originally, the corresponding action number of each data sample is identical.
Then, according to three classes action classification, 3 svm classifier models i.e. base categories model is established, is inputted to test body-building
Pulse rate (X1) of the person when lifting the dumbbell, heart rate variability numerical value (X2), body temperature numerical value (X3), myoelectricity numerical value (X4), movement
Displacement (X5), movement angle (X6) and movement radian (X7), export as action classification.The svm classifier model is two classification mould
Type.
When establishing svm classifier model, using SVM algorithm, disaggregated model parameter is determined.Specifically, first each can be counted
It is normalized according to the data of physiological index in sample and exercise data, normalization mode is Xi'=(Xi-Ximin)/
(Ximax-Ximin), XimaxFor data of physiological index or exercise data XiMaximum value, XiminFor XiMinimum value；Dimensionality reduction is carried out again,
It is tieed up because being related to 7 data parameters i.e. 7, in order to reduce data redundancy, using PCA algorithms, 7 dimension data parameters is mapped as smaller dimension
The data parameters of degree, such as the data parameters of 6 dimensions, and the covariance matrix C being related to and dimension 6 are preserved, for subsequent model
Training uses；The grid optimizing of sorting parameter is carried out again, using in the svm classifier model of RBF kernel functions, is related to penalty coefficient C
With included parameter gamma, by the cross validation of 3 kinds of data samples, best C and gamma are determined；Finally, using RBF core letters
Number carries out two classification, substitutes into best C and gamma, while setting needs probability Estimation, determines disaggregated model parameter.
Step 2：Training action category classification model
In the specific embodiment, for body builder's A training action category classification models.Under the supervision of fitness, note
Record pulse rate (X1), heart rate variability numerical value (X2), body temperature numerical value (X3), myoelectricity numerical value of the n times body builder A when lifting the dumbbell
(X4), moving displacement (X5), movement angle (X6) and movement radian (X7), and the classification of action classification is carried out, number is trained as follows
According to shown in collection.
One action classification disaggregated model of training between arbitrary two classes action classification, that is, train three svm classifier models,
Respective action classification 1 and action classification 2, action classification 1 and action classification 3 and action classification 2 and action classification 3 respectively.
In this way, above-mentioned training dataset is divided into three action classification training datasets, respectively：
Action classification training dataset 1, corresponding SVM1 (action classification 1 and action classification 2)
Action classification training dataset 2, corresponding SVM2 (action classification 1 and action classification 3)
Action classification training dataset 3, corresponding SVM3 (action classification 2 and action classification 3)
In training action category classification model, with reference first to the process of establishing of base categories model, respectively to acting class
Data in other training dataset 1, action classification training dataset 2 and action classification training dataset 3 are normalized
And dimensionality reduction, then using treated, action classification training dataset 1 trains SVM1 to obtain action classification disaggregated model 1, utilizes
Treated action classification training dataset 2 trains SVM2 to obtain action classification disaggregated model 2, utilizes treated action classification
Training dataset 3 trains SVM3 to obtain action classification disaggregated model 3.
Step 3：Body-building monitoring is carried out using action classification disaggregated model
In body-building monitoring process, body builder A data of physiological index corresponding with action α and movement when lifting the dumbbell are obtained
Data, i.e. monitoring data (X1a、X2a、X3a、X4a、X5a、X6a、X7a), which is normalized and dimensionality reduction, and point
Using 1,2 and 3 pair of action classification disaggregated model, treated that monitoring data are analyzed, and determines each action classification classification mould
Under type, the possibility action classification belonging to action α.If under action classification disaggregated model 1, the possibility action belonging to action α
Classification is action classification 1, and under action classification disaggregated model 2, the possibility action classification belonging to action α is action classification 2,
Under action classification disaggregated model 3, the possibility action classification belonging to action α is action classification 2, it is determined that belonging to action α
Action classification is action classification 2.
If pre-setting under action classification 1, prompting without friction, under action classification 2, relatively slow vibrating alert, action classification 3
Under, more anxious vibrating alert, it is determined that the action classification belonging to action α is after action classification 2, will carry out more anxious vibration and carry
It wakes up.
Furthermore, it is necessary to explanation, user can measure body-building position after interim (two weeks/mono- month) body-building
Degree of enclosing (such as arm perimeter, muscle hardness etc.), to detect body-building effect.If body-building effect miss the mark, such as muscle are hard
Degree is inadequate, then can be under the help of fitness, corrective action classification training dataset, adjusts data of physiological index and/or fortune
Dynamic incidence relation between data and action classification, so as to promote exercise guide effect.For example, prior actions classification training data
It concentrates, heart rate variability numerical value thinks that body-building effect is best, but body-building effect miss the mark when being s1, then can adjust heart rate and become
Different in nature numerical value, such as s2 is adjusted to, then detect body-building effect.Finally, by constantly adjusting action classification training dataset, make profit
When carrying out body-building monitoring with the SVM models of its training, reach expected body-building effect.
The body-building monitoring method of second embodiment of the invention, by trained at least one action classification disaggregated model,
It pair handles, is determined under each action classification disaggregated model with the corresponding data of physiological index of action and exercise data, this is dynamic
Possibility action classification belonging to making, and being counted to determining possibility action classification, choose statistics number it is most can be active
Make action classification of the classification belonging to as the action, the action classification based on selection reminds user, can not only realize
To body-building action whether comprehensive reliable monitoring of standard, additionally it is possible to improve differentiate type of action accuracy, promote body-building
Monitoring effect.
3rd embodiment
Shown in Figure 3, third embodiment of the invention provides a kind of body-building monitoring device, is monitored with body-building shown in FIG. 1
Method is corresponding, including：
Acquisition module 31, for obtain user in body-building with a corresponding data of physiological index of action and exercise data；
Determining module 32, for according to the data of physiological index and exercise data, determining the action belonging to the action
Classification, whether standard is related to the action for the action classification；
Reminding module 33 for the action classification belonging to based on the action, reminds the user.
In the embodiment of the present invention, the determining module 32 includes：
Processing unit, for utilizing at least one action classification disaggregated model, to the data of physiological index and movement number
It according to being handled, determines under each action classification disaggregated model, the possibility action classification belonging to the action；
For being counted to the possibility action classification belonging to the action, it is most to choose statistics number for statistic unit
Action classification of the possible action classification belonging to as the action.
Specifically, the body-building monitoring device further includes：
Determining module, for determining at least one action classification training dataset of the user and base categories model,
Each action classification training data concentration includes multigroup data for being divided into two class action classifications, and every group of data are acted to be a kind of
The data of physiological index and exercise data of the user of classification, the base categories model for embody data of physiological index,
Incidence relation between exercise data and action classification；
Training module, for being carried out using base categories model described at least one action classification training data set pair
Training, obtains at least one action classification disaggregated model.
Specifically, the reminding module 33 includes：
Determination unit for the action classification belonging to based on the action, determines prompting corresponding with the action classification
Pattern；
Reminding unit, for according to the determining indicating mode, reminding the user.
Wherein, the action classification belonging to the action is movement range standard, movement range is not up to standard or action width
Degree is above standard.
Wherein, the data of physiological index includes but not limited at least one of following data：Pulse rate, heart rate become
Different in nature numerical value, body temperature numerical value and myoelectricity numerical value.
Wherein, the exercise data includes but not limited at least one of following data：Moving displacement, movement angle and
Move radian.
The body-building monitoring device of third embodiment of the invention, by obtain user in body-building with the corresponding physiology of action
Achievement data and exercise data according to the data of physiological index and exercise data, determine the action classification belonging to the action,
Based on the action classification belonging to the action, the user is reminded, it can be corresponding with body-building action based on user
Data of physiological index and exercise data carry out different promptings under different action classifications, realize to body-building action whether standard
Comprehensive reliable monitoring.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or device including a series of elements not only include those elements, and
And it further includes other elements that are not explicitly listed or further includes intrinsic for this process, method, article or device institute
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this
Also there are other identical elements in the process of element, method, article or device.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be embodied in the form of software product, which is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), used including some instructions so that a station terminal equipment (can be mobile phone, computer takes
Be engaged in device, air conditioner or the network equipment etc.) perform method described in each embodiment of the present invention.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of body-building monitoring method, which is characterized in that including：
Obtain user in body-building with a corresponding data of physiological index of action and exercise data；
According to the data of physiological index and exercise data, determine the action classification belonging to the action, the action classification with
Whether standard is related for the action；
Based on the action classification belonging to the action, the user is reminded；
It is described according to the data of physiological index and exercise data, the step of determining the action classification belonging to the action, including：
Using at least one action classification disaggregated model, the data of physiological index and exercise data are handled, determined every
Under one action classification disaggregated model, the possibility action classification belonging to the action；
Possibility action classification belonging to the action is counted, chooses the most possibility action classification of statistics number as institute
State the action classification belonging to action；
The acquisition user is in body-building with before a step of corresponding data of physiological index of action and exercise data, also wrapping
It includes：
Determine at least one action classification training dataset of the user and base categories model, each action classification trains number
Include multigroup data for being divided into two class action classifications according to concentrating, every group of data are the user under a kind of action classification
Data of physiological index and exercise data, the base categories model are used to embody data of physiological index, exercise data and action class
Incidence relation between not；
Be trained using base categories model described at least one action classification training data set pair, obtain it is described at least
One action classification disaggregated model.
2. body-building monitoring method according to claim 1, which is characterized in that the action class based on belonging to the action
Not, the step of reminding the user, including：
Based on the action classification belonging to the action, indicating mode corresponding with the action classification is determined；
According to the determining indicating mode, the user is reminded.
3. body-building monitoring method according to claim 1, which is characterized in that the action classification belonging to the action is action
Amplitude criteria, movement range are not up to standard or movement range is above standard.
4. according to the body-building monitoring method any in claim 1-3, which is characterized in that the data of physiological index includes
At least one of following data：Pulse rate, heart rate variability numerical value, body temperature numerical value and myoelectricity numerical value.
5. according to the body-building monitoring method any in claim 1-3, which is characterized in that the exercise data includes as follows
At least one of data：Moving displacement, movement angle and movement radian.
6. a kind of body-building monitoring device, which is characterized in that including：
Acquisition module, for obtain user in body-building with a corresponding data of physiological index of action and exercise data；
Determining module, for according to the data of physiological index and exercise data, determining the action classification belonging to the action, institute
Stating action classification, whether standard is related to the action；
Reminding module for the action classification belonging to based on the action, reminds the user；
The determining module includes：
Processing unit, for utilizing at least one action classification disaggregated model, to the data of physiological index and exercise data into
Row processing, determines under each action classification disaggregated model, the possibility action classification belonging to the action；
Statistic unit for being counted to the possibility action classification belonging to the action, chooses the most possibility of statistics number
Action classification of the action classification belonging to as the action；
The body-building monitoring device, further includes：
Determining module, it is each for determining at least one action classification training dataset of the user and base categories model
Action classification training data concentration includes multigroup data for being divided into two class action classifications, and every group of data are a kind of action classification
The user data of physiological index and exercise data, the base categories model for embody data of physiological index, movement
Incidence relation between data and action classification；
Training module, for being instructed using base categories model described at least one action classification training data set pair
Practice, obtain at least one action classification disaggregated model.
7. body-building monitoring device according to claim 6, which is characterized in that the reminding module includes：
Determination unit for the action classification belonging to based on the action, determines indicating mode corresponding with the action classification；
Reminding unit, for according to the determining indicating mode, reminding the user.
8. body-building monitoring device according to claim 6, which is characterized in that the action classification belonging to the action is action
Amplitude criteria, movement range are not up to standard or movement range is above standard.
9. according to the body-building monitoring device any in claim 6-8, which is characterized in that the data of physiological index includes
At least one of following data：Pulse rate, heart rate variability numerical value, body temperature numerical value and myoelectricity numerical value.
10. according to the body-building monitoring device any in claim 6-8, which is characterized in that the exercise data is included such as
At least one of lower data：Moving displacement, movement angle and movement radian.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611216325.9A CN108242260B (en) | 2016-12-26 | 2016-12-26 | Fitness monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611216325.9A CN108242260B (en) | 2016-12-26 | 2016-12-26 | Fitness monitoring method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108242260A true CN108242260A (en) | 2018-07-03 |
| CN108242260B CN108242260B (en) | 2020-12-08 |
Family
ID=62704767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611216325.9A Active CN108242260B (en) | 2016-12-26 | 2016-12-26 | Fitness monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108242260B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109102859A (en) * | 2018-07-24 | 2018-12-28 | 北京大学第医院 | A kind of motion control method and system |
| CN109544188A (en) * | 2018-11-27 | 2019-03-29 | 湖南共睹互联网科技有限责任公司 | Based on user behavior monitoring method, terminal and the readable storage medium storing program for executing for ensureing transaction |
| CN111028911A (en) * | 2019-12-04 | 2020-04-17 | 广州华立科技职业学院 | Motion data analysis method and system based on big data |
| CN113457105A (en) * | 2020-03-30 | 2021-10-01 | 乔山健身器材（上海）有限公司 | Intelligent mirror with body-building menu |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090085864A1 (en) * | 2007-10-02 | 2009-04-02 | Gershom Kutliroff | Method and system for gesture classification |
| CN101785927A (en) * | 2010-03-08 | 2010-07-28 | 游图明 | Interactive body building system |
| TW201111014A (en) * | 2009-09-25 | 2011-04-01 | Footwear & Recreation Technology Res Inst | Human-body muscle training feedback system and method |
| CN103810504A (en) * | 2014-01-14 | 2014-05-21 | 三星电子（中国）研发中心 | Image processing method and device |
| CN104888444A (en) * | 2015-05-20 | 2015-09-09 | 深圳大学 | Intelligent gloves, method and system for calorie consumption and hand posture recognition |
| CN105233485A (en) * | 2015-10-30 | 2016-01-13 | 山西睿智健科技有限公司 | A bodybuilding-assisting motion mode correction system and method |
-
2016
- 2016-12-26 CN CN201611216325.9A patent/CN108242260B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090085864A1 (en) * | 2007-10-02 | 2009-04-02 | Gershom Kutliroff | Method and system for gesture classification |
| TW201111014A (en) * | 2009-09-25 | 2011-04-01 | Footwear & Recreation Technology Res Inst | Human-body muscle training feedback system and method |
| CN101785927A (en) * | 2010-03-08 | 2010-07-28 | 游图明 | Interactive body building system |
| CN103810504A (en) * | 2014-01-14 | 2014-05-21 | 三星电子（中国）研发中心 | Image processing method and device |
| CN104888444A (en) * | 2015-05-20 | 2015-09-09 | 深圳大学 | Intelligent gloves, method and system for calorie consumption and hand posture recognition |
| CN105233485A (en) * | 2015-10-30 | 2016-01-13 | 山西睿智健科技有限公司 | A bodybuilding-assisting motion mode correction system and method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109102859A (en) * | 2018-07-24 | 2018-12-28 | 北京大学第医院 | A kind of motion control method and system |
| CN109544188A (en) * | 2018-11-27 | 2019-03-29 | 湖南共睹互联网科技有限责任公司 | Based on user behavior monitoring method, terminal and the readable storage medium storing program for executing for ensureing transaction |
| CN109544188B (en) * | 2018-11-27 | 2020-09-15 | 湖南共睹互联网科技有限责任公司 | User behavior monitoring method based on guarantee transaction, terminal and readable storage medium |
| CN111028911A (en) * | 2019-12-04 | 2020-04-17 | 广州华立科技职业学院 | Motion data analysis method and system based on big data |
| CN113457105A (en) * | 2020-03-30 | 2021-10-01 | 乔山健身器材（上海）有限公司 | Intelligent mirror with body-building menu |
| CN113457105B (en) * | 2020-03-30 | 2022-09-13 | 乔山健身器材（上海）有限公司 | Intelligent mirror with body-building menu |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108242260B (en) | 2020-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Quaid et al. | Wearable sensors based human behavioral pattern recognition using statistical features and reweighted genetic algorithm | |
| US10422810B2 (en) | Calculating pace and energy expenditure from athletic movement attributes | |
| CN106984027B (en) | A kind of movement comparative analysis method, apparatus and a kind of display | |
| US20180133551A1 (en) | System and method for personalized exercise training and coaching | |
| CN108242260A (en) | A kind of body-building monitoring method and device | |
| US20190366154A1 (en) | Physical activity training assistant | |
| CN105358046A (en) | Automatic exercise segmentation and recognition | |
| CN107920783A (en) | The system and method for monitoring and the movement and alignment mode of user's body activity association | |
| CN109300521A (en) | Trained determination method and device, system, storage medium, processor | |
| US20190290181A1 (en) | Analytics System for Detecting Athletic Fatigue, and Associated Methods | |
| O'Reilly et al. | Technology in strength and conditioning tracking lower-limb exercises with wearable sensors | |
| CN108514421A (en) | The method for promoting mixed reality and routine health monitoring | |
| Meechan et al. | A comparison of kinetic and kinematic variables during the midthigh pull and countermovement shrug, across loads | |
| CA2815224A1 (en) | Consumer useable testing kit | |
| Stewart et al. | Practical automated activity recognition using standard smartphones | |
| US20170076618A1 (en) | Physical Object Training Feedback Based On Object-Collected Usage Data | |
| Akpa et al. | Gift: glove for indoor fitness tracking system | |
| Ma et al. | [Retracted] Recognition of Badminton Shot Action Based on the Improved Hidden Markov Model | |
| CN114341947A (en) | System and method for exercise type recognition using wearable devices | |
| Gang et al. | Prediction of physical load level by machine learning analysis of heart activity after exercises | |
| Pernek et al. | How hard am I training? Using smart phones to estimate sport activity intensity | |
| TWI777140B (en) | Method and system for generating exercise course | |
| Baudry et al. | Amplitude variables of circle on the pedagogic pommel horse in gymnastics | |
| Yen et al. | Feature Fusion-Based Deep Learning Network to Recognize Table Tennis Actions. | |
| Sosopoulos et al. | IoT smart athletics: Boxing glove sensors implementing machine learning for an integrated training solution |
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 |