CN110180154A - A kind of intermittent Training Administration System and method based on wearable device - Google Patents
A kind of intermittent Training Administration System and method based on wearable device Download PDFInfo
- Publication number
- CN110180154A CN110180154A CN201910393146.XA CN201910393146A CN110180154A CN 110180154 A CN110180154 A CN 110180154A CN 201910393146 A CN201910393146 A CN 201910393146A CN 110180154 A CN110180154 A CN 110180154A
- Authority
- CN
- China
- Prior art keywords
- training
- trainer
- interval
- period
- trained
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0605—Decision makers and devices using detection means facilitating arbitration
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B71/0622—Visual, audio or audio-visual systems for entertaining, instructing or motivating the user
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B2071/0647—Visualisation of executed movements
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B2071/065—Visualisation of specific exercise parameters
- A63B2071/0652—Visualisation or indication relating to symmetrical exercise, e.g. right-left performance related to spinal column
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B2071/0658—Position or arrangement of display
- A63B2071/0661—Position or arrangement of display arranged on the user
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B2071/0675—Input for modifying training controls during workout
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/806—Video cameras
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/83—Special sensors, transducers or devices therefor characterised by the position of the sensor
- A63B2220/836—Sensors arranged on the body of the user
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2230/00—Measuring physiological parameters of the user
- A63B2230/04—Measuring physiological parameters of the user heartbeat characteristics, e.g. ECG, blood pressure modulations
- A63B2230/06—Measuring physiological parameters of the user heartbeat characteristics, e.g. ECG, blood pressure modulations heartbeat rate only
Abstract
The present invention relates to a kind of intermittent Training Administration System and method based on wearable device, including being set to the camera in each trained region, the Intelligent bracelet for being set to each trained region, the Intelligent foot ring for being set to each trained region and the voice playing equipment for being set to each trained region, system further includes cloud server and database, and each trainer ID and the corresponding historic training data of each trainer ID are stored in database；Cloud server includes drill program generation module, Intelligent bracelet communication module, Intelligent foot ring communication module, camera communication module, subscriber identification module, voice playing equipment communication module, trainer's state determination module and timing module.By using the present invention, based on machine learning model come self study, drill program is intelligently formulated according to the historical data of trainer and current status data, to provide the drill program for being more in line with trainer's actual conditions, also improves the efficiency of interval training management.
Description
Technical field
The present invention relates to technical field of data processing, in particular to a kind of intermittent training pipes based on wearable device
Manage system and method.
Background technique
Intermittent training method, which refers to, proposes strict requirements to movement structure and load intensity, intermittent time, so that at body
Under incomplete recovery state, the training method of practice is repeated.The coaching method advantage is to train period and interval
Period can be such that heart rate holds within optimum range, improve cardiac pump function.Interval training, being trained between the period twice has one
The rest period of strict control time of having a rest, and the length of this rest period is controlled by measuring the heart rate of sportsman
's.Key is a little that sportsman will just start lower sector when not yet regaining one's strength completely.
In practical applications, the training period of interval training and the time of rest period are controlled.But
That can only rule of thumb set the plan of interval training every time for coach, may some are unilateral, can not be arranged
Meet the drill program of each trainer's actual conditions.And for coach, one-to-one real-time perfoming training management is needed,
It is very time-consuming and laborious.
Summary of the invention
The present invention provides a kind of intermittent Training Administration System and method based on wearable device, its object is to
Defect in the prior art is overcome, based on machine learning model come self study, according to the historical data of trainer and current shape
State data intelligently formulate drill program, so that the drill program for being more in line with trainer actual conditions is provided, between also improving
The efficiency of having a rest property training management.
To achieve the goals above, the present invention has following constitute:
The intermittent Training Administration System based on wearable device, the interval of the trainer for multiple trained regions
Property training process management, an interval training includes n trained period and n-1 rest period, wherein training the period and stop
It ceases period crossover to carry out, the system comprises the intelligence for being set to the camera in each trained region, being set to each trained region
Energy bracelet is set to the Intelligent foot ring in each trained region and is set to the voice playing equipment in each trained region, the system
System further includes cloud server and database, and each trainer ID, each trainer are stored in the database nearest one
The training period in interval training number, the Mean Time Between Replacement of interval training twice, each interval training in year
The average duration of rest period between par, every two training period and a preceding interval training and current time
Time interval；
The cloud server include drill program generation module, Intelligent bracelet communication module, Intelligent foot ring communication module,
Camera communication module, subscriber identification module, voice playing equipment communication module, trainer's state determination module and timing mould
Block；Wherein, the cloud server is for executing following steps:
The Intelligent bracelet communication module is communicated with the Intelligent bracelet, obtains the heart of the user of the Intelligent bracelet measurement
Rate data；
The Intelligent foot ring communication module is communicated with the Intelligent foot ring, obtains the vibration frequency of the Intelligent foot ring measurement
Data；
The camera communication module is communicated with the camera, obtains the acquisition picture of the camera；
The subscriber identification module obtains the face-image of trainer from the acquisition picture of the camera, and according to instruction
The ID of the face-image recognition training person of white silk person；
Trainer's state determination module obtains the heart rate data and vibration frequency data of the trainer, detects institute
The heart rate data for stating trainer is persistently greater than heart rate threshold within the scope of first time threshold and vibration frequency data are greater than first
When frequency threshold, determine that the trainer is in physical training condition, detects the heart rate data of the trainer in first time threshold
When being worth in range continuously less than heart rate threshold or vibration frequency data less than first frequency threshold value, determines that the trainer is in and stop
Breath state；
The drill program generation module for trainer be in do not start trained original state when, by trainer most
In the Mean Time Between Replacement of interval training number, interval training twice in nearly 1 year, each interval training when training
Par, a preceding interval training and the time interval of current time of section, trainer current heart rate value and trainer
Current vibration frequency value is input to trained frequency of training computation model, and the frequency of training computation model exports trainer
The quantity of training period in this time interval training；
When state of the drill program generation module for trainer switches to physical training condition from original state, it will train
Person is in the Mean Time Between Replacement of interval training number, interval training twice in nearest 1 year, each interval training
The current heart rate value of training par, a preceding interval training and the time interval of current time of period, trainer and
The current vibration frequency value of trainer is input to trained trained duration calculation model, the trained duration calculation model output
Trainer currently trains the plan duration of period；
When state of the drill program generation module for trainer switches to resting state from physical training condition, it will train
Person in nearest 1 year interval training number, the Mean Time Between Replacement of interval training twice, instruct in each interval training
The par of white silk period, every two are trained the average duration of the rest period between the period, a preceding interval training and are worked as
The current heart rate value of the time interval of preceding time, trainer and the current vibration frequency value of trainer are input to trained rest
Duration calculation model, the plan duration of rest duration calculation model output trainer's current rest period；
In this time interval training that the voice playing equipment communication module generates the drill program generation module
The quantity of training period, the plan duration of current training period and the plan duration of current rest period are sent to corresponding language
Sound playback equipment after the voice playing equipment receives data, plays to trainer by voice.
Optionally, the cloud server further includes training process supervision module and timing module, and the timing module is
Each trainer creates a timer, carries out timing using each state of the timer to trainer；
The training process supervision module obtains training when the state of trainer switches to resting state by physical training condition
Training duration of the person in the training period just terminated, the plan of the training period generated with the drill program generation module
Duration is compared, if difference is greater than second time threshold, the training process supervision module is played by the voice
Device communication module sends warning message to corresponding voice playing equipment；
The training process supervision module obtains training when the state of trainer switches to physical training condition by resting state
Rest duration of the person in the rest period just terminated, the plan of the rest period generated with the drill program generation module
Duration is compared, if difference is greater than third time threshold, the training process supervision module is played by the voice
Device communication module sends warning message to corresponding voice playing equipment.
Optionally, the frequency of training computation model, the trained duration calculation model and the rest duration calculation mould
Type is respectively convolutional neural networks model, and it includes sequentially connected first convolutional layer, the first pond that the drill program, which generates model,
Change layer, the second convolutional layer, the second pond layer, third convolutional layer, Volume Four lamination, the 5th convolutional layer and third pond layer, it is described
Between first convolutional layer and the first pond layer, between the second convolutional layer and the second pond layer, third convolutional layer and Volume Four lamination
Between and the 5th convolutional layer and third pond layer between be respectively arranged with a Relu function.
Optionally, the training set of the frequency of training computation model includes the sample data of multiple trainers, each described
The sample data of trainer includes that interval training number of the trainer in nearest 1 year, interval training twice are averaged
The par of period, the time of preceding an interval training and current time are trained in interval time, each interval training
It is spaced, the vibration frequency data of the heart rate data of trainer and trainer, and the sample data label of each trainer is once
The quantity of training period in interval training.
Optionally, the training set of the training time duration calculation model includes the sample data of multiple trainers, Ge Gesuo
State trainer sample data include interval training number of the trainer in nearest 1 year, interval training twice it is flat
The par of training period in equal interval time, each interval training, a preceding interval training and current time when
Between interval, the heart rate data of trainer and trainer vibration frequency data, and the sample data of each trainer is marked with one
The duration of a trained period；
Time training set of duration calculation model of resting includes the sample data of multiple trainers, each trainer
Sample data include interval training number of the trainer in nearest 1 year, interval training twice equispaced when
Between, in each interval training training the period par, every two training the period between the rest period average duration,
The time interval of a preceding interval training and current time, the heart rate data of trainer and the vibration frequency data of trainer,
And the sample data of each trainer is marked with the duration of a rest period.
Optionally, the cloud server further includes picture synthesis module, and the picture synthesis module is by each training center
The camera acquisition picture in domain synthesizes a picture, and the picture of synthesis is sent to manager's platform in trained region.
Optionally, the picture synthesis module shows picture according to the quantity and manager's platform in trained region currently in use
The resolution ratio in face calculates the resolution ratio of the camera collection image in each trained region；
The acquisition picture of the camera is adjusted to by the picture synthesis module each of is calculated trained region
The resolution ratio of camera collection image, and the image in the training region in each use is combined；
The picture synthesis module adds logo in the display picture in each trained region, and the logo includes corresponding
Training region in the ID of trainer, current state, the reality of the plan duration of current state and current state continued
Duration.
Optionally, when the Intelligent bracelet detects that heart rate is greater than default lowest threshold, judgement is not trained to person's binding, institute
It states Intelligent bracelet and sends enabling signal to camera bound in the Intelligent bracelet and Intelligent foot ring；
It is automatic to start when the camera receives enabling signal, start to acquire the image in corresponding training region；
It is automatic to start when the Intelligent foot ring receives enabling signal, start the foot's vibration data for acquiring trainer.
The embodiment of the present invention also provides a kind of intermittent training management method based on wearable device, using described
Intermittent Training Administration System based on wearable device, described method includes following steps:
The Intelligent bracelet communication module is communicated with the Intelligent bracelet, obtains the heart of the user of the Intelligent bracelet measurement
Rate data；
The Intelligent foot ring communication module is communicated with the Intelligent foot ring, obtains the vibration frequency of the Intelligent foot ring measurement
Data；
The camera communication module is communicated with the camera, obtains the acquisition picture of the camera；
The subscriber identification module obtains the face-image of trainer from the acquisition picture of the camera, and according to instruction
The ID of the face-image recognition training person of white silk person；
Trainer's state determination module obtains the heart rate data and vibration frequency data of the trainer, detects institute
The heart rate data for stating trainer is persistently greater than heart rate threshold within the scope of first time threshold and vibration frequency data are greater than first
When frequency threshold, determine that the trainer is in physical training condition, detects the heart rate data of the trainer in first time threshold
When being worth in range continuously less than heart rate threshold or vibration frequency data less than first frequency threshold value, determines that the trainer is in and stop
Breath state；
The drill program generation module for trainer be in do not start trained original state when, by trainer most
In the Mean Time Between Replacement of interval training number, interval training twice in nearly 1 year, each interval training when training
Par, a preceding interval training and the time interval of current time of section, trainer current heart rate value and trainer
Current vibration frequency value is input to trained frequency of training computation model, and the frequency of training computation model exports trainer
The quantity of training period in this time interval training；
When state of the drill program generation module for trainer switches to physical training condition from original state, it will train
Person is in the Mean Time Between Replacement of interval training number, interval training twice in nearest 1 year, each interval training
The current heart rate value of training par, a preceding interval training and the time interval of current time of period, trainer and
The current vibration frequency value of trainer is input to trained trained duration calculation model, the trained duration calculation model output
Trainer currently trains the plan duration of period；
When state of the drill program generation module for trainer switches to resting state from physical training condition, it will train
Person in nearest 1 year interval training number, the Mean Time Between Replacement of interval training twice, instruct in each interval training
The par of white silk period, every two are trained the average duration of the rest period between the period, a preceding interval training and are worked as
The current heart rate value of the time interval of preceding time, trainer and the current vibration frequency value of trainer are input to trained rest
Duration calculation model, the plan duration of rest duration calculation model output trainer's current rest period；
In this time interval training that the voice playing equipment communication module generates the drill program generation module
The quantity of training period, the plan duration of current training period and the plan duration of current rest period are sent to corresponding language
Sound playback equipment after the voice playing equipment receives data, plays to trainer by voice.
Using the intermittent Training Administration System and method based on wearable device in the invention, have has as follows
Beneficial effect:
The present invention detects the current status data of trainer by wearable device, and can be worked as according to trainer
Preceding status data judges automatically the current state of trainer, based on machine learning model come self study, according to going through for trainer
History data and current status data intelligently formulate drill program, to provide the training for being more in line with trainer's actual conditions
Plan can inform user after formulating corresponding drill program by way of voice broadcast, also improve interval training
The efficiency of management.
Detailed description of the invention
Fig. 1 is the structural representation of the intermittent Training Administration System based on wearable device of one embodiment of the invention
Figure；
Fig. 2 is that the drill program of the intermittent Training Administration System based on wearable device of one embodiment of the invention is raw
The work flow diagram of plan is generated at module；
Fig. 3 is the flow chart of the intermittent training management method based on wearable device of one embodiment of the invention.
Specific embodiment
It is further to carry out combined with specific embodiments below in order to more clearly describe technology contents of the invention
Description.
The technical issues of in order to solve in the prior art, the present invention provides a kind of based on the intermittent of wearable device
Training Administration System, the interval training process management of the trainer for multiple trained regions, an interval training includes n
A trained period and n-1 rest period, wherein training period and rest period crossover carry out.
As shown in Figure 1, in an embodiment of the present invention, the intermittent Training Administration System based on wearable device
Including being set to the camera M100 in each trained region, the Intelligent bracelet M200 for being set to each trained region, being set to respectively
The Intelligent foot ring M300 in a trained region and voice playing equipment M400 for being set to each trained region, the system also includes
Each trainer ID, each trainer are stored with most in cloud server M500 and database M600, the database M600
In the Mean Time Between Replacement of interval training number, interval training twice in nearly 1 year, each interval training when training
The par of section, the average duration of rest period between the every two training period and a preceding interval training and current
The time interval of time.
The cloud server M500 includes drill program generation module M510, Intelligent bracelet communication module M520, intelligence
Foot ring communication module M530, camera communication module M540, subscriber identification module M550, voice playing equipment communication module
M560, trainer state determination module M570 and timing module M580；Wherein, the cloud server is for executing following step
It is rapid:
The Intelligent bracelet communication module is communicated with the Intelligent bracelet, obtains the heart of the user of the Intelligent bracelet measurement
Rate data；
The Intelligent foot ring communication module is communicated with the Intelligent foot ring, obtains the vibration frequency of the Intelligent foot ring measurement
Data；
The camera communication module is communicated with the camera, obtains the acquisition picture of the camera；
The subscriber identification module obtains the face-image of trainer from the acquisition picture of the camera, and according to instruction
The ID of the face-image recognition training person of white silk person；
Trainer's state determination module obtains the heart rate data and vibration frequency data of the trainer, detects institute
The heart rate data for stating trainer is persistently greater than heart rate threshold within the scope of first time threshold and vibration frequency data are greater than first
When frequency threshold, determine that the trainer is in physical training condition, detects the heart rate data of the trainer in first time threshold
When being worth in range continuously less than heart rate threshold or vibration frequency data less than first frequency threshold value, determines that the trainer is in and stop
Breath state；
As shown in Fig. 2, generating the work flow diagram of plan for the drill program generation module.The drill program generates
Module is in for trainer when not starting trained original state, by interval training of the trainer in nearest 1 year time
Number, the Mean Time Between Replacement of interval training twice, the par of training period, preceding primary interval in each interval training
Property the current vibration frequency value of the trained heart rate value and trainer current with the time interval of current time, trainer be input to instruction
The frequency of training computation model perfected, the frequency of training computation model export the training period in trainer's this time interval training
Quantity；
When state of the drill program generation module for trainer switches to physical training condition from original state, it will train
Person is in the Mean Time Between Replacement of interval training number, interval training twice in nearest 1 year, each interval training
The current heart rate value of training par, a preceding interval training and the time interval of current time of period, trainer and
The current vibration frequency value of trainer is input to trained trained duration calculation model, the trained duration calculation model output
Trainer currently trains the plan duration of period；
When state of the drill program generation module for trainer switches to resting state from physical training condition, it will train
Person in nearest 1 year interval training number, the Mean Time Between Replacement of interval training twice, instruct in each interval training
The par of white silk period, every two are trained the average duration of the rest period between the period, a preceding interval training and are worked as
The current heart rate value of the time interval of preceding time, trainer and the current vibration frequency value of trainer are input to trained rest
Duration calculation model, the plan duration of rest duration calculation model output trainer's current rest period；
In this time interval training that the voice playing equipment communication module generates the drill program generation module
The quantity of training period, the plan duration of current training period and the plan duration of current rest period are sent to corresponding language
Sound playback equipment after the voice playing equipment receives data, plays to trainer by voice.
Therefore, the present invention detects the current status data of trainer by wearable device, specifically, using intelligence
Bracelet acquires heart rate data, acquires vibration frequency data, and status number that can be current according to trainer using Intelligent foot ring
According to the current state of trainer is judged automatically, using two kinds of monitoring data, state judges more accurate, reduction erroneous judgement probability, base
Carry out self study in machine learning model, trained meter is intelligently formulated according to the historical data of trainer and current status data
It draws, to provide the drill program for being more in line with trainer's actual conditions, language can be passed through after formulating corresponding drill program
The mode of sound casting informs trainer, correctly to know the training process of trainer.Drill program includes primary intermittent instruction
The quantity of training period during white silk, such as have five trained periods during an interval training, then rest period
Correspondingly have four times.And in each trained period, since the state of trainer is all different, going through according to trainer again
History data and current status data generate the drill program duration for being directed to the training period, more meet that trainer is practical to be instructed
Practice situation, rather than simply formulates an inflexible plan.
Further, in this embodiment, the function of automatic training supervision and guidance can also be provided.It is taken in the cloud
It is engaged in device, training process supervision module and timing module is further set, the timing module is that each trainer creates one
Timer carries out timing using each state of the timer to trainer.
The training process supervision module obtains training when the state of trainer switches to resting state by physical training condition
Training duration of the person in the training period just terminated, the plan of the training period generated with the drill program generation module
Duration is compared, if difference is greater than second time threshold, the training process supervision module is played by the voice
Device communication module sends warning message to corresponding voice playing equipment；Trainer can be with after receiving warning message
Adjust the training time of oneself in time according to drill program.
The training process supervision module obtains training when the state of trainer switches to physical training condition by resting state
Rest duration of the person in the rest period just terminated, the plan of the rest period generated with the drill program generation module
Duration is compared, if difference is greater than third time threshold, the training process supervision module is played by the voice
Device communication module sends warning message to corresponding voice playing equipment；Trainer can be with after receiving warning message
Adjust the time of having a rest of oneself in time according to drill program.
In this embodiment, the frequency of training computation model, the trained duration calculation model and the rest duration
Computation model is respectively convolutional neural networks model, the drill program generate model include sequentially connected first convolutional layer,
First pond layer, the second convolutional layer, the second pond layer, third convolutional layer, Volume Four lamination, the 5th convolutional layer and third pond
Layer, between first convolutional layer and the first pond layer, between the second convolutional layer and the second pond layer, third convolutional layer and the 4th
A Relu function is respectively arranged between convolutional layer and between the 5th convolutional layer and third pond layer.
Every layer of convolutional layer is made of several convolution units in convolutional neural networks, and the parameter of each convolution unit is to pass through
What back-propagation algorithm optimized.The purpose of convolution algorithm is to extract the different characteristic of input, and first layer convolutional layer may
Some rudimentary features such as levels such as edge, lines and angle can only be extracted, the network of more layers iteration can be mentioned from low-level features
Take more complicated feature.Pond layer is also sampling layer, after convolutional layer, is equally made of multiple characteristic faces, it every
One characteristic face corresponds to one layer thereon of a characteristic face, will not change the number of characteristic face.Pond layer is intended to pass through reduction
The resolution ratio of characteristic face obtains the feature with space-invariance.Pond layer plays the role of second extraction feature, it every
A neuron carries out pondization operation to local acceptance region.Common pond method has maximum pondization to take local acceptance region intermediate value most
Big point, mean value pondization average to all values in local acceptance region, random pool etc., this example mainly uses maximum pond
Change method.
In this embodiment, the training set of the frequency of training computation model includes the sample data of multiple trainers, respectively
The sample data of a trainer includes interval training number of the trainer in nearest 1 year, interval training twice
Mean Time Between Replacement, in each interval training the training period par, a preceding interval training and current time
Time interval, the heart rate data of trainer and the vibration frequency data of trainer, and each trainer sample data label
The quantity of period is once trained in interval training.Herein, the primary intermittent instruction of the sample data label of each trainer
The quantity of training period, which can be, in white silk asks special coach to carry out targeted terrestrial reference according to each different sample data
Note is also possible to the acquisition similar history number of multiple states on a large scale to be more in line with the training strength requirement that coach requires
According to come the suitable quantity of simulating different sample datas.
In this embodiment, the training set of the training time duration calculation model includes the sample data of multiple trainers,
The sample data of each trainer includes interval training number of the trainer in nearest 1 year, twice intermittent instruction
The par of training period in experienced Mean Time Between Replacement, each interval training, a preceding interval training and it is current when
Between time interval, the heart rate data of trainer and the vibration frequency data of trainer, and the sample data mark of each trainer
Note has the duration of a trained period.Herein, the duration of a trained period of the sample data label of each trainer can be with
It is to ask special coach targetedly to be marked according to each different sample data, to be more in line with coach's requirement
Training strength requirement is also possible to acquire conjunction of the similar historical data of large-scale multiple states to simulate different sample datas
Suitable training period duration.
Time training set of duration calculation model of resting includes the sample data of multiple trainers, each trainer
Sample data include interval training number of the trainer in nearest 1 year, interval training twice equispaced when
Between, in each interval training training the period par, every two training the period between the rest period average duration,
The time interval of a preceding interval training and current time, the heart rate data of trainer and the vibration frequency data of trainer,
And the sample data of each trainer is marked with the duration of a rest period.Herein, the sample data label of each trainer
The duration of a rest period can be special coach is asked to be carried out targetedly according to each different sample data
Label is also possible to the acquisition similar history of multiple states on a large scale to be more in line with the training strength requirement that coach requires
Data simulate the suitable rest period durations of different sample datas.
In this embodiment, the cloud server further includes picture synthesis module, and the picture synthesis module will be each
The camera acquisition picture in training region synthesizes a picture, and the manager that the picture of synthesis is sent to trained region is put down
Platform.
In this embodiment, the picture synthesis module is according to the quantity and manager's platform in trained region currently in use
The resolution ratio of display picture calculates the resolution ratio of the camera collection image in each trained region；
The acquisition picture of the camera is adjusted to by the picture synthesis module each of is calculated trained region
The resolution ratio of camera collection image, and the image in the training region in each use is combined；
The picture synthesis module adds logo in the display picture in each trained region, and the logo includes corresponding
Training region in the ID of trainer, current state, the reality of the plan duration of current state and current state continued
Duration.
In this embodiment, when the Intelligent bracelet detects that heart rate is greater than default lowest threshold, judgement is not trained to person
Binding, the Intelligent bracelet send enabling signal to camera bound in the Intelligent bracelet and Intelligent foot ring；
It is automatic to start when the camera receives enabling signal, start to acquire the image in corresponding training region；
It is automatic to start when the Intelligent foot ring receives enabling signal, start the foot's vibration data for acquiring trainer.
As shown in figure 3, the embodiment of the present invention also provides a kind of intermittent training management method based on wearable device,
Using the intermittent Training Administration System based on wearable device, described method includes following steps:
The Intelligent bracelet communication module is communicated with the Intelligent bracelet, obtains the heart of the user of the Intelligent bracelet measurement
Rate data；
The Intelligent foot ring communication module is communicated with the Intelligent foot ring, obtains the vibration frequency of the Intelligent foot ring measurement
Data；
The camera communication module is communicated with the camera, obtains the acquisition picture of the camera；
The subscriber identification module obtains the face-image of trainer from the acquisition picture of the camera, and according to instruction
The ID of the face-image recognition training person of white silk person；The extraction and recognition of face of facial image can use face in the prior art
Recognition methods is extracted human face region for example, by using existing active shape model etc., and is identified use by the way of images match
Family identity etc. recognizes trainer ID according to the collected facial image of camera as long as can be realized, so can be real
The binding of existing camera collection image, training region and trainer ID；
Trainer's state determination module obtains the heart rate data and vibration frequency data of the trainer, detects institute
The heart rate data for stating trainer is persistently greater than heart rate threshold within the scope of first time threshold and vibration frequency data are greater than first
When frequency threshold, determine that the trainer is in physical training condition, detects the heart rate data of the trainer in first time threshold
When being worth in range continuously less than heart rate threshold or vibration frequency data less than first frequency threshold value, determines that the trainer is in and stop
Breath state；
The drill program generation module for trainer be in do not start trained original state when, by trainer most
In the Mean Time Between Replacement of interval training number, interval training twice in nearly 1 year, each interval training when training
Par, a preceding interval training and the time interval of current time of section, trainer current heart rate value and trainer
Current vibration frequency value is input to trained frequency of training computation model, and the frequency of training computation model exports trainer
The quantity of training period in this time interval training；
When state of the drill program generation module for trainer switches to physical training condition from original state, it will train
Person is in the Mean Time Between Replacement of interval training number, interval training twice in nearest 1 year, each interval training
The current heart rate value of training par, a preceding interval training and the time interval of current time of period, trainer and
The current vibration frequency value of trainer is input to trained trained duration calculation model, the trained duration calculation model output
Trainer currently trains the plan duration of period；
When state of the drill program generation module for trainer switches to resting state from physical training condition, it will train
Person in nearest 1 year interval training number, the Mean Time Between Replacement of interval training twice, instruct in each interval training
The par of white silk period, every two are trained the average duration of the rest period between the period, a preceding interval training and are worked as
The current heart rate value of the time interval of preceding time, trainer and the current vibration frequency value of trainer are input to trained rest
Duration calculation model, the plan duration of rest duration calculation model output trainer's current rest period；
In this time interval training that the voice playing equipment communication module generates the drill program generation module
The quantity of training period, the plan duration of current training period and the plan duration of current rest period are sent to corresponding language
Sound playback equipment after the voice playing equipment receives data, plays to trainer by voice.
Compared with prior art, using in the invention based on wearable device intermittent Training Administration System and
Method has the following beneficial effects:
The present invention detects the current status data of trainer by wearable device, and can be worked as according to trainer
Preceding status data judges automatically the current state of trainer, based on machine learning model come self study, according to going through for trainer
History data and current status data intelligently formulate drill program, to provide the training for being more in line with trainer's actual conditions
Plan can inform user after formulating corresponding drill program by way of voice broadcast, also improve interval training
The efficiency of management.
In this description, the present invention is described with reference to its specific embodiment.But it is clear that can still make
Various modifications and alterations are without departing from the spirit and scope of the invention.Therefore, the description and the appended drawings should be considered as illustrative
And not restrictive.
Claims (9)
1. a kind of intermittent Training Administration System based on wearable device, which is characterized in that for multiple trained regions
The interval training process management of trainer, an interval training include n trained period and n-1 rest period, wherein
Training the period and rest period crossover carry out, the system comprises be set to the camera in each trained region, be set to it is each
The Intelligent bracelet in training region is set to the Intelligent foot ring in each trained region and is set to the voice broadcasting in each trained region
Equipment is stored with each trainer ID, each training the system also includes cloud server and database in the database
Person is in the Mean Time Between Replacement of interval training number, interval training twice in nearest 1 year, each interval training
The par of training period, every two train the average duration and a preceding interval training of the rest period between the period
With the time interval of current time；
The cloud server includes drill program generation module, Intelligent bracelet communication module, Intelligent foot ring communication module, camera shooting
Head communication module, subscriber identification module, voice playing equipment communication module, trainer's state determination module and timing module；Its
In, the cloud server is for executing following steps:
The Intelligent bracelet communication module is communicated with the Intelligent bracelet, obtains the heart rate number of the user of the Intelligent bracelet measurement
According to；
The Intelligent foot ring communication module is communicated with the Intelligent foot ring, obtains the vibration frequency number of the Intelligent foot ring measurement
According to；
The camera communication module is communicated with the camera, obtains the acquisition picture of the camera；
The subscriber identification module obtains the face-image of trainer from the acquisition picture of the camera, and according to trainer
Face-image recognition training person ID；
Trainer's state determination module obtains the heart rate data and vibration frequency data of the trainer, detects the instruction
The heart rate data of white silk person is persistently greater than heart rate threshold within the scope of first time threshold and vibration frequency data are greater than first frequency
When threshold value, determine that the trainer is in physical training condition, detects the heart rate data of the trainer in first time threshold model
When being less than first frequency threshold value continuously less than heart rate threshold or vibration frequency data in enclosing, determine that the trainer is in rest shape
State；
The drill program generation module for trainer be in do not start trained original state when, by trainer nearest one
The training period in interval training number, the Mean Time Between Replacement of interval training twice, each interval training in year
Par, a preceding interval training and the time interval of current time, trainer current heart rate value and trainer are current
Vibration frequency value be input to trained frequency of training computation model, the frequency of training computation model output trainer is this time
The quantity of training period in interval training；
When state of the drill program generation module for trainer switches to physical training condition from original state, trainer is existed
Training in the Mean Time Between Replacement of interval training number, interval training twice in nearest 1 year, each interval training
The par of period, a preceding interval training and the time interval of current time, trainer current heart rate value and training
The current vibration frequency value of person is input to trained trained duration calculation model, the trained duration calculation model output training
Person currently trains the plan duration of period；
When state of the drill program generation module for trainer switches to resting state from physical training condition, trainer is existed
Interval training number in nearest 1 year, the Mean Time Between Replacement of interval training twice, in each interval training when training
The par of section, the average duration of rest period between the every two training period, a preceding interval training and it is current when
Between time interval, the current current vibration frequency value of heart rate value and trainer of trainer be input to trained rest duration
Computation model, the plan duration of rest duration calculation model output trainer's current rest period；
Training in this time interval training that the voice playing equipment communication module generates the drill program generation module
The quantity of period, the plan duration of current training period and the plan duration of current rest period are sent to corresponding voice and broadcast
Equipment is put, after the voice playing equipment receives data, trainer is played to by voice.
2. the intermittent Training Administration System according to claim 1 based on wearable device, which is characterized in that described
Cloud server further includes training process supervision module and timing module, and the timing module is that each trainer creates a meter
When device, timing is carried out to each state of trainer using the timer；
The training process supervision module obtains trainer and exists when the state of trainer switches to resting state by physical training condition
The training duration in the training period just terminated, the plan duration of the training period generated with the drill program generation module
It is compared, if difference is greater than second time threshold, the training process supervision module passes through the voice playing equipment
Communication module sends warning message to corresponding voice playing equipment；
The training process supervision module obtains trainer and exists when the state of trainer switches to physical training condition by resting state
The rest duration in the rest period just terminated, the plan duration of the rest period generated with the drill program generation module
It is compared, if difference is greater than third time threshold, the training process supervision module passes through the voice playing equipment
Communication module sends warning message to corresponding voice playing equipment.
3. the intermittent Training Administration System according to claim 1 based on wearable device, which is characterized in that described
Frequency of training computation model, the trained duration calculation model and the rest duration calculation model are respectively convolutional neural networks
Model, it includes sequentially connected first convolutional layer, the first pond layer, the second convolutional layer, second that the drill program, which generates model,
Pond layer, third convolutional layer, Volume Four lamination, the 5th convolutional layer and third pond layer, first convolutional layer and the first pond
Between layer, between the second convolutional layer and the second pond layer, between third convolutional layer and Volume Four lamination and the 5th convolutional layer and
A Relu function is respectively arranged between the layer of third pond.
4. the intermittent Training Administration System according to claim 3 based on wearable device, which is characterized in that described
The training set of frequency of training computation model includes the sample data of multiple trainers, and the sample data of each trainer includes
Interval training number, the Mean Time Between Replacement of twice interval training, each intermittence of the trainer in nearest 1 year
In training training the par of period, the time interval of a preceding interval training and current time, trainer heart rate number
According to the vibration frequency data with trainer, and the sample data of each trainer marks the training period in once interval training
Quantity.
5. the intermittent Training Administration System according to claim 3 based on wearable device, which is characterized in that described
The training set of training time duration calculation model includes the sample data of multiple trainers, the sample data packet of each trainer
Include interval training number, the Mean Time Between Replacement of twice interval training, each interval of the trainer in nearest 1 year
Property training in training the par of period, the time interval of a preceding interval training and current time, trainer heart rate
The vibration frequency data of data and trainer, and the sample data of each trainer is marked with the duration of a trained period；
Time training set of duration calculation model of resting includes the sample data of multiple trainers, the sample of each trainer
Notebook data include interval training number of the trainer in nearest 1 year, interval training twice Mean Time Between Replacement,
It is the average duration of rest period in each interval training between the par of training period, every two training period, preceding
The time interval of interval training and current time, the heart rate data of trainer and the vibration frequency data of trainer, and
The sample data of each trainer is marked with the duration of a rest period.
6. the intermittent Training Administration System according to claim 1 based on wearable device, which is characterized in that described
Cloud server further includes picture synthesis module, and the picture synthesis module closes the camera acquisition picture in each trained region
As a picture, and the picture of synthesis is sent to manager's platform in trained region.
7. the intermittent Training Administration System according to claim 6 based on wearable device, which is characterized in that described
Picture synthesis module shows that the resolution ratio of picture calculates each according to the quantity and manager's platform in trained region currently in use
The resolution ratio of the camera collection image in training region；
The acquisition picture of the camera is adjusted to the camera shooting that trained region each of is calculated by the picture synthesis module
The resolution ratio of head acquisition image, and the image in the training region in each use is combined；
The picture synthesis module adds logo in the display picture in each trained region, and the logo includes corresponding instruction
Practice the reality of the ID of trainer in region, current state, the plan duration of current state and current state duration.
8. the intermittent Training Administration System according to claim 1 based on wearable device, which is characterized in that described
When Intelligent bracelet detects that heart rate is greater than default lowest threshold, judgement is not trained to person's binding, the Intelligent bracelet to the intelligence
Camera bound in energy bracelet and Intelligent foot ring send enabling signal；
It is automatic to start when the camera receives enabling signal, start to acquire the image in corresponding training region；
It is automatic to start when the Intelligent foot ring receives enabling signal, start the foot's vibration data for acquiring trainer.
9. a kind of intermittent training management method based on wearable device, which is characterized in that using in claim 1 to 8
Described in any item intermittent Training Administration Systems based on wearable device, described method includes following steps:
The Intelligent bracelet communication module is communicated with the Intelligent bracelet, obtains the heart rate number of the user of the Intelligent bracelet measurement
According to；
The Intelligent foot ring communication module is communicated with the Intelligent foot ring, obtains the vibration frequency number of the Intelligent foot ring measurement
According to；
The camera communication module is communicated with the camera, obtains the acquisition picture of the camera；
The subscriber identification module obtains the face-image of trainer from the acquisition picture of the camera, and according to trainer
Face-image recognition training person ID；
Trainer's state determination module obtains the heart rate data and vibration frequency data of the trainer, detects the instruction
The heart rate data of white silk person is persistently greater than heart rate threshold within the scope of first time threshold and vibration frequency data are greater than first frequency
When threshold value, determine that the trainer is in physical training condition, detects the heart rate data of the trainer in first time threshold model
When being less than first frequency threshold value continuously less than heart rate threshold or vibration frequency data in enclosing, determine that the trainer is in rest shape
State；
The drill program generation module for trainer be in do not start trained original state when, by trainer nearest one
The training period in interval training number, the Mean Time Between Replacement of interval training twice, each interval training in year
Par, a preceding interval training and the time interval of current time, trainer current heart rate value and trainer are current
Vibration frequency value be input to trained frequency of training computation model, the frequency of training computation model output trainer is this time
The quantity of training period in interval training；
When state of the drill program generation module for trainer switches to physical training condition from original state, trainer is existed
Training in the Mean Time Between Replacement of interval training number, interval training twice in nearest 1 year, each interval training
The par of period, a preceding interval training and the time interval of current time, trainer current heart rate value and training
The current vibration frequency value of person is input to trained trained duration calculation model, the trained duration calculation model output training
Person currently trains the plan duration of period；
When state of the drill program generation module for trainer switches to resting state from physical training condition, trainer is existed
Interval training number in nearest 1 year, the Mean Time Between Replacement of interval training twice, in each interval training when training
The par of section, the average duration of rest period between the every two training period, a preceding interval training and it is current when
Between time interval, the current current vibration frequency value of heart rate value and trainer of trainer be input to trained rest duration
Computation model, the plan duration of rest duration calculation model output trainer's current rest period；
Training in this time interval training that the voice playing equipment communication module generates the drill program generation module
The quantity of period, the plan duration of current training period and the plan duration of current rest period are sent to corresponding voice and broadcast
Equipment is put, after the voice playing equipment receives data, trainer is played to by voice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910393146.XA CN110180154A (en) | 2019-05-13 | 2019-05-13 | A kind of intermittent Training Administration System and method based on wearable device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910393146.XA CN110180154A (en) | 2019-05-13 | 2019-05-13 | A kind of intermittent Training Administration System and method based on wearable device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110180154A true CN110180154A (en) | 2019-08-30 |
Family
ID=67714479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910393146.XA Pending CN110180154A (en) | 2019-05-13 | 2019-05-13 | A kind of intermittent Training Administration System and method based on wearable device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110180154A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2095763A1 (en) * | 2008-02-27 | 2009-09-02 | Polar Electro Oy | Determination of sympathetic activity |
| US20090275442A1 (en) * | 2008-04-30 | 2009-11-05 | Polar Electro Oy | Method and Apparatus in Connection with Exercise |
| US20100236385A1 (en) * | 2009-03-20 | 2010-09-23 | Mariann Martin Willis | Method and apparatus for personal exercise trainer |
| CN108355322A (en) * | 2018-02-06 | 2018-08-03 | 苏州东巍网络科技有限公司 | A kind of the fitness equipment system and application method of intelligence customized user body-building scheme |
| CN109451257A (en) * | 2018-11-30 | 2019-03-08 | 苏州东巍网络科技有限公司 | A kind of the interval training Video transmission system and method for point-to-point |
| CN109529304A (en) * | 2018-11-09 | 2019-03-29 | 深圳市量子智能科技有限公司 | A kind of intelligent training method and system |
-
2019
- 2019-05-13 CN CN201910393146.XA patent/CN110180154A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2095763A1 (en) * | 2008-02-27 | 2009-09-02 | Polar Electro Oy | Determination of sympathetic activity |
| US20090275442A1 (en) * | 2008-04-30 | 2009-11-05 | Polar Electro Oy | Method and Apparatus in Connection with Exercise |
| US20100236385A1 (en) * | 2009-03-20 | 2010-09-23 | Mariann Martin Willis | Method and apparatus for personal exercise trainer |
| CN108355322A (en) * | 2018-02-06 | 2018-08-03 | 苏州东巍网络科技有限公司 | A kind of the fitness equipment system and application method of intelligence customized user body-building scheme |
| CN109529304A (en) * | 2018-11-09 | 2019-03-29 | 深圳市量子智能科技有限公司 | A kind of intelligent training method and system |
| CN109451257A (en) * | 2018-11-30 | 2019-03-08 | 苏州东巍网络科技有限公司 | A kind of the interval training Video transmission system and method for point-to-point |
Non-Patent Citations (1)
| Title |
|---|
| 韦鹏程，冉维，段昂: "《大数据巨量分析与机器学习的整合与开发》", 31 May 2017 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6086379A (en) | System and method for training a swimmer | |
| WO2022183698A1 (en) | Artificial intelligence fault identification system and method based on power transmission line transient waveform | |
| CN106984027B (en) | A kind of movement comparative analysis method, apparatus and a kind of display | |
| CN105320944B (en) | A kind of human body behavior prediction method based on human skeleton motion information | |
| CN106709235A (en) | Exercise training data processing method and device | |
| CN110478883A (en) | A kind of body-building movement teaching and correction system and method | |
| CN109621331A (en) | Fitness-assisting method, apparatus and storage medium, server | |
| CN108579020A (en) | A kind of intelligence science movement technique and kinematic system | |
| CN110464356B (en) | Comprehensive monitoring method and system for exercise capacity | |
| CN112836105B (en) | Large-scale student aerobic capacity clustering method based on movement physiological characterization fusion | |
| CN104436535A (en) | Cardiopulmonary endurance training method based on rowing machine | |
| US20230149774A1 (en) | Handle Motion Counting Method and Terminal | |
| CN103390193A (en) | Automatic training device for navigation-oriented rat robot, and rat behavior identification method and training method | |
| CN105797320B (en) | A kind of intelligence house exercycle perseverance work(output control system and its control method | |
| Huang et al. | Miss yoga: a yoga assistant mobile application based on keypoint detection | |
| Yang et al. | Research on face recognition sports intelligence training platform based on artificial intelligence | |
| CN114783611A (en) | Neural recovered action detecting system based on artificial intelligence | |
| CN110060756A (en) | A kind of more people's online management systems and method of interval training | |
| CN110909621A (en) | Body-building guidance system based on vision | |
| CN110180154A (en) | A kind of intermittent Training Administration System and method based on wearable device | |
| CN110517751A (en) | A kind of athletic rehabilitation management system | |
| CN109243573A (en) | A kind of comprehensive sports education exercise device | |
| CN116135267A (en) | Healthy sports equipment intelligent control system with man-machine interaction function | |
| CN110180155A (en) | A kind of the intensity remote supervision system and method for interval training | |
| CN115607936A (en) | Swimming training intelligent supervision control system and method based on artificial intelligence |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190830 |