CN108404394A - The computational methods and system, wearable device of a kind of running distance for wearable device - Google Patents
The computational methods and system, wearable device of a kind of running distance for wearable device Download PDFInfo
- Publication number
- CN108404394A CN108404394A CN201810133055.8A CN201810133055A CN108404394A CN 108404394 A CN108404394 A CN 108404394A CN 201810133055 A CN201810133055 A CN 201810133055A CN 108404394 A CN108404394 A CN 108404394A
- Authority
- CN
- China
- Prior art keywords
- data
- swing arm
- sample
- wearable device
- sample data
- 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
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0062—Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B22/00—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements
- A63B22/02—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements with movable endless bands, e.g. treadmills
-
- 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
-
- 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
- A63B2071/0663—Position or arrangement of display arranged on the user worn on the wrist, e.g. wrist bands
-
- 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
- A63B2220/10—Positions
- A63B2220/12—Absolute positions, e.g. by using GPS
-
- 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
- A63B2220/20—Distances or displacements
-
- 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
- A63B2220/20—Distances or displacements
- A63B2220/22—Stride length
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physical Education & Sports Medicine (AREA)
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Cardiology (AREA)
- Vascular Medicine (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention provides a kind of computational methods and system, wearable device of the running distance for wearable device, including：When the signal strength of GPS is less than predetermined threshold value, the swing arm amplitude of each swing arm in testing time section is obtained；According to the swing arm amplitude and user movement characteristic model of each swing arm, the corresponding stride of each swing arm is obtained；According to the corresponding stride of each swing arm in testing time section, running distance is obtained；The present invention can improve the computational accuracy for the running distance that indoor running or GPS can not be under service condition.
Description
Technical field
The present invention relates to wearable device field, the computational methods of espespecially a kind of running distance for wearable device and
System, wearable device.
Background technology
Under treadmill pattern, the step number of user is estimated by the number of arms swing indoors for current bracelet wrist-watch,
Then stride being calculated according to the body data of itself, such as age, height input by user etc. again, step number is multiplied by stride, from
And estimate the distance of indoor running.In above-mentioned computational methods, the stride run every time is substantially fixed.But in practical mistake
The running posture of Cheng Zhong, user can change with the different phase of running, and usual running posture is different, and stride is not yet
Together, it generally jogs at the beginning, swing arm amplitude is smaller, is preheated, and then accelerates, hurries up, and swing arm amplitude becomes larger, swing arm frequency
It becomes faster, at the end of soon, and gradually slows down, jog.In general, swing arm amplitude is bigger, running step is bigger, but according to above-mentioned meter
Calculation method can lead to not the distance of actually running for accurately measuring user.
Invention content
The object of the present invention is to provide a kind of computational methods of the running distance for wearable device, wearable device,
The computational accuracy for the running distance that indoor running or GPS can not be under service condition can be improved.
Technical solution provided by the invention is as follows：
A kind of computational methods of running distance for wearable device, including：Step S200 is low when the signal strength of GPS
When predetermined threshold value, the swing arm amplitude of each swing arm in testing time section is obtained；Step S300 is according to the pendulum of each swing arm
Arm amplitude and user movement characteristic model obtain the corresponding stride of each swing arm；Step S400 is according to every in testing time section
The corresponding stride of secondary swing arm obtains running distance.
In the above-mentioned technical solutions, by calculating the corresponding stride of each swing arm, can improve indoor running or GPS without
The computational accuracy of running distance under method service condition.
Further, further include：Step S100 obtains the movement number of user when the signal strength of GPS reaches predetermined threshold value
According to as sample data；The sample data is sent to server by step S110；Step S120 receives the server and sends
User movement characteristic model, and update the user movement characteristic model of wearable device.
In the above-mentioned technical solutions, exercise data when can be used using GPS, such as outdoor running data, through server structure
It builds user movement characteristic model and issues wearable device；It is unavailable in GPS, for example, indoor running, wearable device
Using the model, the computational accuracy of stride can be improved, to improve the computational accuracy of running distance.
Further, the step S100 is specifically included：Step S101 leads to when the signal strength of GPS reaches predetermined threshold value
Cross the original sampling data of the original sampling data and cadence of the sensor acquisition swing arm amplitude of wearable device；Step S102 is logical
The built-in GPS for crossing wearable device obtains the original sampling data of movement velocity；Step S103 is original to the swing arm amplitude
Sampled data, the original sampling data of the cadence, the movement velocity original sampling data handled, it is same to obtain the time
Swing arm amplitude sample data, cadence sample data and the movement velocity sample data of step；Step S104 is according to the movement velocity
Sample data and cadence sample data obtain corresponding stride sample data；Step S105 is by the stride sample data, swing arm
Amplitude sample data and the data of cadence sample data composition are as the sample data；By the stride sample of each time synchronization
Originally a, sample of the combination of swing arm amplitude sample and cadence sample as the sample data.
In the above-mentioned technical solutions, the data that the data and built-in GPS obtained by the sensor of wearable device obtain,
Combination constitutes sample data, provides the foundation for the follow-up motion feature model for obtaining user.
Further, the step S200 further includes that step S210 is obtained when the signal strength of GPS is less than predetermined threshold value
The swing arm amplitude and corresponding cadence of each swing arm in testing time section；The step S300 further includes that step S310 will be each
A swing arm amplitude and its corresponding cadence substitute into user movement characteristic model, obtain corresponding stride.
In the above-mentioned technical solutions, unavailable in GPS, constructed by exercise data when can be used according to GPS
User movement characteristic model, the computational accuracy of stride can be improved, to improve running distance computational accuracy.
The present invention also provides a kind of wearable devices, including：Data acquisition module is less than for the signal strength as GPS
When predetermined threshold value, the swing arm amplitude of each swing arm in testing time section is obtained；Distance calculation module, with the data acquisition module
Electrical connection obtains the corresponding step of each swing arm for the swing arm amplitude and user movement characteristic model according to each swing arm
Width；And according to the corresponding stride of each swing arm in testing time section, obtain running distance.
In the above-mentioned technical solutions, by calculating the corresponding stride of each swing arm, can improve indoor running or GPS without
The computational accuracy of running distance under method service condition.
Further, the data acquisition module is further used for when the signal strength of GPS reaches predetermined threshold value, obtains
The exercise data of user, as sample data；Further include data transmission blocks, is electrically connected, is used for the data acquisition module
The sample data is sent to server；Model receiving module, the user movement feature sent for receiving the server
Model, and update the user movement characteristic model of wearable device.
In the above-mentioned technical solutions, exercise data when can be used using GPS, such as outdoor running data, structure user's fortune
Dynamic characteristic model, it is unavailable in GPS, for example indoor running can improve the computational accuracy of stride using the model,
To improve the computational accuracy of running distance.
Further, the data acquisition module is further used for, when the signal strength of GPS reaches predetermined threshold value, passing through
The sensor of wearable device obtains the original sampling data of the original sampling data and cadence of swing arm amplitude；And by can
The built-in GPS of wearable device obtains the original sampling data of movement velocity；And the crude sampling number to the swing arm amplitude
It is handled according to, the original sampling data of the original sampling data of the cadence, the movement velocity, obtains the pendulum of time synchronization
Arm amplitude sample data, cadence sample data and movement velocity sample data；And according to the movement velocity sample data and
Cadence sample data obtains corresponding stride sample data；And by the stride sample data, swing arm amplitude sample data
Data with cadence sample data composition are as the sample data；By the stride sample of each time synchronization, swing arm amplitude
A sample of the combination of sample and cadence sample as the sample data.
In the above-mentioned technical solutions, the data that the data and built-in GPS obtained by the sensor of wearable device obtain,
Combination constitutes sample data, provides the foundation for the follow-up motion feature model for obtaining user.
Further, the data acquisition module is further used for, when the signal strength of GPS is less than predetermined threshold value, obtaining
The swing arm amplitude and corresponding cadence of each swing arm in testing time section；The distance calculation module, being further used for will be each
A swing arm amplitude and its corresponding cadence substitute into user movement characteristic model, obtain corresponding stride.
In the above-mentioned technical solutions, it uses unavailable in GPS, utilizes exercise data when can be used according to GPS
Constructed user movement characteristic model, can improve the computational accuracy of stride, to improve the computational accuracy of running distance..
The present invention also provides a kind of computing system of the running distance for wearable device, including above-mentioned wearable set
It is standby, further include server；The server includes：Data reception module, for receiving the sample data from wearable device；
Model construction module is electrically connected with the data reception module, for according to the sample data, passing through supervision type machine learning
Algorithm obtains the user movement characteristic model；Model sending module is electrically connected with the model construction module, and being used for will be described
User movement characteristic model is sent to wearable device.
In the above-mentioned technical solutions, provide a kind of system, by server carry out model construction, contribute to GPS not
The computational accuracy of running distance is promoted when available.
Further, the model construction module is further used for when the sample data updates, according to newer sample
User movement characteristic model described in data update.
In the above-mentioned technical solutions, multiple sample data is obtained by repeatedly running, and uses multiple sample data
Training, can make user's motion feature model more acurrate.
The computational methods and system of a kind of running distance for wearable device provided through the invention wearable are set
It is standby, following advantageous effect can be brought：The present invention can improve the running distance that indoor running or GPS can not be under service conditions
Computational accuracy.
Description of the drawings
Below by a manner of clearly understandable, preferred embodiment is described with reference to the drawings, wearable device is used for one kind
The computational methods of running distance and above-mentioned characteristic, technical characteristic, advantage and its realization method of system, wearable device give
It further illustrates.
Fig. 1 is a kind of flow of one embodiment of the computational methods of running distance for wearable device of the present invention
Figure；
Fig. 2 a are a kind of another embodiments of the computational methods of running distance for wearable device of the present invention
The flow chart that sample data obtains；
Fig. 2 is a kind of stream of another embodiment of the computational methods of running distance for wearable device of the present invention
Cheng Tu；
Fig. 3 is a kind of structural schematic diagram of one embodiment of wearable device of the present invention；
Fig. 4 is a kind of structural schematic diagram of another embodiment of wearable device of the present invention；
Fig. 5 is a kind of structure of one embodiment of the computing system of running distance for wearable device of the present invention
Schematic diagram.
Drawing reference numeral explanation：
100. wearable device, 110. data acquisition modules, 120. distance calculation modules, 130. data transmission blocks,
140. model receiving module, 200. servers, 210. data reception modules, 220. model construction modules, 230. models send mould
Block.
Specific implementation mode
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, control is illustrated below
The specific implementation mode of the present invention.It should be evident that drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, other are can also be obtained according to these attached drawings
Attached drawing, and obtain other embodiments.
To make simplified form, part related to the present invention is only schematically shown in each figure, they are not represented
Its practical structures as product.In addition, so that simplified form is easy to understand, there is identical structure or function in some figures
Component only symbolically depicts one of those, or has only marked one of those.Herein, "one" is not only indicated
" only this ", can also indicate the situation of " more than one ".
In one embodiment of the invention, as shown in Figure 1, a kind of calculating side of running distance for wearable device
Method, including：
Step S200 obtains the swing arm of swing arm every time in testing time section when the signal strength of GPS is less than predetermined threshold value
Amplitude；
Step S300 obtains each swing arm and corresponds to according to the swing arm amplitude and user movement characteristic model of each swing arm
Stride；
Step S400 obtains running distance according to the corresponding stride of each swing arm in testing time section.
Specifically, wearable device, refers to wearable smart motion equipment, such as bracelet wrist-watch.
When the signal strength of GPS reaches predetermined threshold value, GPS signal can be used for positioning, and wearable device can be by interior
The GPS set immediately arrives at the running distance of user.When the signal strength of GPS is less than predetermined threshold value, such as indoor running, due to
GPS signal is poor, it is difficult to position, running distance is calculated by the following method：Pass through the sensor on wearable device
Measure the swing arm amplitude of each swing arm in testing time section；According to the swing arm amplitude and user movement characteristic model of each swing arm,
Obtain the corresponding stride of each swing arm；The corresponding stride of each swing arm being calculated in testing time section is added up, i.e.,
Obtain the running distance of testing time section.
Testing time section refers to the time span once run, from the time for starting to run to running end.User movement
Characteristic model describes the relationship of stride and swing arm amplitude, for example, stride is multiplied by a coefficient, the coefficient equal to swing arm amplitude
According to personal feature data, for example the height of user, age, weight obtain.The user movement characteristic model is stored in and can wear
It wears in equipment.
In another embodiment of the present invention, as shown in Fig. 2 a, Fig. 2, a kind of running distance for wearable device
Computational methods, including：
Step S100 obtains the exercise data of user, as sample number when the signal strength of GPS reaches predetermined threshold value
According to；
The sample data is sent to server by step S110；
Step S120 receives the user movement characteristic model that the server is sent, and updates user's fortune of wearable device
Dynamic characteristic model；
Step S210 obtains the swing arm of swing arm every time in testing time section when the signal strength of GPS is less than predetermined threshold value
Amplitude and corresponding cadence；
Each swing arm amplitude and its corresponding cadence are substituted into user movement characteristic model by step S310, are corresponded to
Stride；
Step S400 obtains running distance according to the corresponding stride of each swing arm in testing time section；
The step S100 is specifically included：
Step S101 obtains swing arm when the signal strength of GPS reaches predetermined threshold value, by the sensor of wearable device
The original sampling data of amplitude and the original sampling data of cadence；
Step S102 obtains the original sampling data of movement velocity by the built-in GPS of wearable device；
Step S103 is to the original sampling data of the swing arm amplitude, the original sampling data of the cadence, the movement
The original sampling data of speed is handled, and swing arm amplitude sample data, cadence sample data and the movement of time synchronization are obtained
Speed sample data；
Step S104 obtains corresponding stride sample number according to the movement velocity sample data and cadence sample data
According to；
The data that step S105 forms the stride sample data, swing arm amplitude sample data and cadence sample data are made
For the sample data；Using the combination of the stride sample of each time synchronization, swing arm amplitude sample and cadence sample as institute
State a sample of sample data.
Specifically, relatively previous embodiment, embodiment adds step S100- steps S105, step S110- steps
S120, step S210 are instead of step S200, with step S310 instead of step S300.
When the signal strength of GPS reaches predetermined threshold value, GPS signal can be used for positioning, and wearable device passes through built-in
GPS can obtain more movable informations.As shown in Figure 2 a, the sample data detailed process for obtaining user is as follows：
When the signal strength of GPS reaches predetermined threshold value, the pendulum of this movement is obtained by the sensor of wearable device
The original sampling data of arm amplitude and the original sampling data of cadence；The original sampling data of movement velocity is obtained by GPS；It will
Swing arm amplitude, cadence, movement velocity original sampling data in time synchronization onwards come.For example, the sample frequency of cadence is 3
Beat/min, the sample frequency of swing arm amplitude is 3 beats/min, and movement velocity is 0.5 beat/min, because These parameters are using different
What device was sampled, while the data sampled are additionally operable to different purposes, so their sample frequency may be different；It needs
These original sampling datas are handled, synchronization onwards are come on the time, could be used for the user movement characteristic model of next step
Modeling；For example, by 1 beat/min of the processing frequency data that obtain that treated, processing frequency is more than for sample frequency, at 1 point
Initial data in clock can be more than needs, may be used the mode that 1 minute interior data adduction is averaging calculating one
A new data replaces the initial data in 1 minute, can also only choose wherein 1 data to replace the original number in 1 minute
According to there are many modes of selection, for example, there is 3.3,5.0,4.5 etc. 3 data in 1 minute, can choose in this 3 data
Value 4.5, or choose the data 5.0 etc. in centre position；Processing frequency is less than for sample frequency, the side of repetition may be used
Formula has 2 data 65,70 by Data-parallel language, such as in 0.5 beat/min, 4 minutes of sample frequency, to Data duplication, to reach 4
There are 4 data 65,65,70,70 in minute；In the above manner, processing data are aligned in time, time synchronization is obtained
Swing arm amplitude sample data, cadence sample data and movement velocity sample data；According to movement velocity sample data and cadence sample
Notebook data obtains corresponding stride sample data；By stride sample data, swing arm amplitude sample data and cadence sample data group
At sample data of the data as user movement characteristic model, each sample of sample data is by stride sample, swing arm width
Sample and cadence sample composition are spent, they are synchronous in time.
By the sample data of acquisition, server is reported, is exercised supervision type machine learning algorithm by server, obtains user
Motion feature model.By receiving the user movement characteristic model from server, which is applied to GPS by wearable device
Signal strength be less than the scene of predetermined threshold value, such as the calculating of the running distance of indoor running：
When the signal strength of GPS is less than predetermined threshold value, this indoor running is obtained by the sensor of wearable device
The swing arm amplitude and corresponding cadence of each swing arm in testing time section, testing time section are this indoor running time
The swing arm amplitude of length, each swing arm in the testing time section constitutes swing arm amplitude data；According to the sampling frequency of swing arm amplitude
Rate, handles the cadence data, and the two is aligned in time, goes to intercept according to each swing arm amplitude corresponding time
Corresponding cadence；Each swing arm amplitude and its corresponding cadence are substituted into the user movement characteristic model that front basis obtains,
Obtain corresponding stride；The corresponding stride of each swing arm in testing time section is added up, this indoor running is obtained
Running distance.
In addition to obtaining the original sampling data of swing arm amplitude, the original sampling data of cadence sample data, movement velocity, also
The original sampling data that heart rate can be obtained handles data above, time synchronization, obtains sample data.By the sample
Data report server, by supervision type machine learning algorithm, obtain user movement characteristic model, obtain more characterization movements
The information of data can make model more accurate.
User movement characteristic model, can also be with the update of sample data, the synchronous update for carrying out model.It is new when obtaining
Sample data when, report server, server to be updated model, by the training of multiple sample data, model can
With more precisely, more meet user's personal feature.Wearable device calculates stride, Ke Yiti with newest user movement characteristic model
The accuracy of height running distance.
To sum up, the exercise data obtained when the signal strength of GPS is reached predetermined threshold value by the present embodiment, reports server,
It is exercised supervision type machine learning algorithm by server, obtains user movement characteristic model；By receiving the use from server
The model is less than the scene of predetermined threshold value, such as room by family motion feature model, wearable device applied to the signal strength of GPS
Interior running can promote the computational accuracy of stride, to improve indoor running running distance computational accuracy.
In another embodiment of the present invention, as shown in figure 3, a kind of wearable device 100, including：
Data acquisition module 110, it is every in testing time section for when the signal strength of GPS is less than predetermined threshold value, obtaining
The swing arm amplitude of secondary swing arm；
Distance calculation module 120 is electrically connected with the data acquisition module 110, for the pendulum according to each swing arm
Arm amplitude and user movement characteristic model obtain the corresponding stride of each swing arm；And according to each pendulum in testing time section
The corresponding stride of arm obtains running distance.
Specifically, wearable device, refers to wearable smart motion equipment, such as bracelet wrist-watch.
When the signal strength of GPS reaches predetermined threshold value, GPS signal can be used for positioning, and wearable device can be by interior
The GPS set immediately arrives at the running distance of user.When the signal strength of GPS is less than predetermined threshold value, such as indoor running, due to
GPS signal is poor, it is difficult to position, running distance is calculated by the following method：Pass through the sensor on wearable device
Measure the swing arm amplitude of each swing arm in testing time section；According to the swing arm amplitude and user movement characteristic model of each swing arm,
Obtain the corresponding stride of each swing arm；The corresponding stride of each swing arm being calculated in testing time section is added up, i.e.,
Obtain the running distance of testing time section.
Testing time section refers to the time span once run, from the time for starting to run to running end.User movement
Characteristic model describes the relationship of stride and swing arm amplitude, for example, stride is multiplied by a coefficient, the coefficient equal to swing arm amplitude
According to personal feature data, for example the height of user, age, weight obtain.The user movement characteristic model is stored in and can wear
It wears in equipment.
In another embodiment of the present invention, as shown in figure 4, a kind of wearable device 100, including：
Data acquisition module 110, for when the signal strength of GPS reaches predetermined threshold value, obtaining the exercise data of user,
As sample data；
Data transmission blocks are electrically connected with the data acquisition module, for the sample data to be sent to server；
Model receiving module, the user movement characteristic model sent for receiving the server；
The data acquisition module 110 is further used for, when the signal strength of GPS is less than predetermined threshold value, being tested
The swing arm amplitude and corresponding cadence of each swing arm in period；
Distance calculation module 120 is electrically connected with the data acquisition module 110, for by each swing arm amplitude and its
Corresponding cadence substitutes into user movement characteristic model, obtains corresponding stride；And according to each swing arm in testing time section
Corresponding stride obtains running distance；
The data acquisition module 110 is further used for when the signal strength of GPS reaches predetermined threshold value, by that can wear
Wear the original sampling data of the original sampling data and cadence of the sensor acquisition swing arm amplitude of equipment；And by wearable
The built-in GPS of equipment obtains the original sampling data of movement velocity；And the original sampling data to the swing arm amplitude, institute
The original sampling data of the original sampling data, the movement velocity of stating cadence is handled, and the swing arm width of time synchronization is obtained
Spend sample data, cadence sample data and movement velocity sample data；And according to the movement velocity sample data and cadence
Sample data obtains corresponding stride sample data；And by the stride sample data, swing arm amplitude sample data and step
The data of frequency sample data composition are as the sample data；By the stride sample of each time synchronization, swing arm amplitude sample
A sample of the combination as the sample data with cadence sample.
Specifically, relatively previous embodiment, embodiment adds data transmission blocks and model receiving module, logarithms
Function enhancing has been done according to acquisition module, distance calculation module.
When the signal strength of GPS reaches predetermined threshold value, GPS signal can be used for positioning, and wearable device passes through built-in
GPS can obtain more movable informations.As shown in Figure 2 a, the sample data detailed process for obtaining user is as follows：
When the signal strength of GPS reaches predetermined threshold value, this outdoor sport is obtained by the sensor of wearable device
When swing arm amplitude original sampling data and cadence original sampling data；The crude sampling of movement velocity is obtained by GPS
Data；By the original sampling data of swing arm amplitude, cadence, movement velocity, synchronization onwards are come in time.For example, the sampling frequency of cadence
Rate is 3 beats/min, and the sample frequency of swing arm amplitude is 3 beats/min, and movement velocity is 0.5 beat/min, because These parameters are using not
What same device was sampled, while the data sampled are additionally operable to different purposes, so their sample frequency may be different；
It needs to handle these original sampling datas, synchronization onwards are come on the time, could be used for the user movement character modules of next step
The modeling of type；For example, by 1 beat/min of the processing frequency data that obtain that treated, preset processing is more than frequently for sample frequency
Rate, the initial data in 1 minute can be more than needs, and the side for being averaging 1 minute interior data adduction may be used
Formula calculates a new data to replace the initial data in 1 minute, can also only choose wherein 1 data to replace 1 minute
Interior initial data, there are many modes of selection, for example, there is 3.3,5.0,4.5 etc. 3 data in 1 minute, can choose this 3
The intermediate value 4.5 of a data, or choose the data 5.0 etc. in centre position；Processing frequency is less than for sample frequency, can be adopted
With the mode repeated by Data-parallel language, for example there are 2 data 65,70 in 0.5 beat/min, 4 minutes of sample frequency, to Data duplication,
There are 4 data 65,65,70,70 to reach in 4 minutes；In the above manner, processing data are aligned in time, obtain
Swing arm amplitude sample data, cadence sample data and the movement velocity sample data of time synchronization；According to movement velocity sample number
According to cadence sample data, obtain corresponding stride sample data；By stride sample data, swing arm amplitude sample data and cadence
Sample data of the data of sample data composition as user movement characteristic model, each sample of sample data is by stride sample
Originally, swing arm amplitude sample and cadence sample composition, they are synchronous in time.
By the sample data of acquisition, server is reported, is exercised supervision type machine learning algorithm by server, obtains user
Motion feature model.By receiving the user movement characteristic model from server, which is applied to GPS by wearable device
Signal strength be less than the scene of predetermined threshold value, such as the calculating of the running distance of indoor running：
When the signal strength of GPS is less than predetermined threshold value, this indoor running is obtained by the sensor of wearable device
The swing arm amplitude and corresponding cadence of each swing arm in testing time section, testing time section are this indoor running time
The swing arm amplitude of length, each swing arm in the testing time section constitutes swing arm amplitude data；According to the sampling frequency of swing arm amplitude
Rate, handles the cadence data, and the two is aligned in time, goes to intercept according to each swing arm amplitude corresponding time
Corresponding cadence；Each swing arm amplitude and its corresponding cadence are substituted into the user movement characteristic model that front basis obtains,
Obtain corresponding stride；The corresponding stride of each swing arm in testing time section is added up, this indoor running is obtained
Running distance.
In addition to obtaining the original sampling data of swing arm amplitude, the original sampling data of cadence sample data, movement velocity, also
The original sampling data that heart rate can be obtained handles data above, time synchronization, obtains sample data.By the sample
Data report server, by supervision type machine learning algorithm, obtain user movement characteristic model, obtain more characterization movements
The information of data can make model more accurate.
User movement characteristic model, can also be with the update of sample data, the synchronous update for carrying out model.It is new when obtaining
Sample data when, report server, server to be updated model, by the training of multiple sample data, model can
With more precisely, more meet user's personal feature.Wearable device calculates stride, Ke Yiti with newest user movement characteristic model
The accuracy of height running distance.
To sum up, the exercise data obtained when the signal strength of GPS is reached predetermined threshold value by the present embodiment, reports server,
It is exercised supervision type machine learning algorithm by server, obtains user movement characteristic model；By receiving the use from server
The model is less than the scene of predetermined threshold value, such as room by family motion feature model, wearable device applied to the signal strength of GPS
Interior running can promote the computational accuracy of stride, to improve indoor running running distance computational accuracy.
In another embodiment of the present invention, as shown in figure 5, a kind of calculating of running distance for wearable device
Wearable device 100 in system, including any of the above-described embodiment further includes server 200；
The server 200 includes：
Data reception module 210, for receiving the sample data from wearable device；
Model construction module 220 is electrically connected with the data reception module 210, for according to the sample data, passing through
Supervision type machine learning algorithm obtains the user movement characteristic model；
Model sending module 230 is electrically connected with the model construction module 220, is used for the user movement character modules
Type is sent to wearable device 100.
Specifically, providing a kind of computing system, which includes wearable device and server.It is carried out by server
Model construction contributes to the computational accuracy that running distance is promoted when GPS is unavailable.
Model construction module obtains user movement feature according to the sample data received, by supervision type machine learning algorithm
Model.
Supervision type machine learning is instructed by existing training sample (i.e. given data and its corresponding output)
Practice, to obtain an optimal models, this model is recycled to export corresponding result to new data sample.Supervision type machine
There are many kinds of learning algorithms, and one kind is given below：
According to linear fit model, the fitting function of stride is obtained；And according to the sample data, using under gradient
Drop method obtains the value of each parameter in the fitting function of the stride；And the fitting function of the value of each parameter will be substituted into
As the user movement characteristic model；
The fitting function of the stride is：
hθ(x)=θTX=θ0x0+θ1x1 ……………………………(1)
Wherein, x=[x0,x1]T, x0For swing arm amplitude, x1For cadence；θ0,θ1For parameter, θ=[θ0,θ1]T；
The value of each parameter in the fitting function of the stride is obtained, is adopted using gradient descent method according to sample data
Function is as follows：
Wherein, i indicates i-th of sample in sample data, and m is the total sample number in sample data；hθ(xi) it is i-th
The corresponding prediction stride of sample, yiIndicate the practical stride in i-th of sample；When J (θ) minimums, the corresponding θ values of J (θ) are quasi-
Close the value of each parameter in function.
In another embodiment of the present invention, as shown in figure 5, a kind of calculating of running distance for wearable device
Wearable device 100 in system, including any of the above-described embodiment further includes server 200；
The server 200 includes：
Data reception module 210, for receiving the sample data from wearable device；
Model construction module 220 is electrically connected with the data reception module 210, for according to the sample data, passing through
Supervision type machine learning algorithm obtains the user movement characteristic model；
Model sending module 230 is electrically connected with the model construction module 220, is used for the user movement character modules
Type is sent to wearable device 100；
The model construction module 230 is further used for when the sample data updates, according to newer sample data
Update the user movement characteristic model.
Specifically, relatively previous embodiment, the present embodiment supports the update of user movement characteristic model.
The swing arm amplitude of running has relationship with movement velocity, user movement state etc., for example, jog some day with it is another
It is hurried up, and the sampled data affirmative of obtained swing arm amplitude is different, so the model obtained with data of once running can compare
It is more unilateral, so in order to keep the output of model more acurrate, machine learning is carried out to obtain mass data by repeatedly running, it can be with
Keep user's motion feature model more acurrate.
When obtaining new sample data every time, wearable device reports server.Server to family motion feature model into
Row update, by the training of multiple sample data, model can more precisely, more meet user's personal feature.Wearable device
Stride is calculated with newest user movement characteristic model, the accuracy of running distance can be improved.
It should be noted that above-described embodiment can be freely combined as needed.The above is only the preferred of the present invention
Embodiment, it is noted that for those skilled in the art, in the premise for not departing from the principle of the invention
Under, several improvements and modifications can also be made, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of computational methods of running distance for wearable device, which is characterized in that including：
Step S200 obtains the swing arm amplitude of each swing arm in testing time section when the signal strength of GPS is less than predetermined threshold value；
Step S300 obtains the corresponding step of each swing arm according to the swing arm amplitude and user movement characteristic model of each swing arm
Width；
Step S400 obtains running distance according to the corresponding stride of each swing arm in testing time section.
2. the computational methods of the running distance according to claim 1 for wearable device, which is characterized in that obtain institute
The user movement characteristic model stated in step 300 includes：
Step S100 obtains the exercise data of user, as sample data when the signal strength of GPS reaches predetermined threshold value；
The sample data is sent to server by step S110；
Step S120 receives the user movement characteristic model that the server is sent, and the user movement for updating wearable device is special
Levy model.
3. the computational methods of the running distance according to claim 2 for wearable device, which is characterized in that the step
Rapid S100 is specifically included：
Step S101 obtains swing arm amplitude when the signal strength of GPS reaches predetermined threshold value, by the sensor of wearable device
Original sampling data and cadence original sampling data；
Step S102 obtains the original sampling data of movement velocity by the built-in GPS of wearable device；
Step S103 is to the original sampling data of the swing arm amplitude, the original sampling data of the cadence, the movement velocity
Original sampling data handled, obtain swing arm amplitude sample data, cadence sample data and the movement velocity of time synchronization
Sample data；
Step S104 obtains corresponding stride sample data according to the movement velocity sample data and cadence sample data；
The data that step S105 forms the stride sample data, swing arm amplitude sample data and cadence sample data are as institute
State sample data；Using the combination of the stride sample of each time synchronization, swing arm amplitude sample and cadence sample as the sample
One sample of notebook data.
4. the computational methods of the running distance according to claim 3 for wearable device, it is characterised in that：
The step S200 further includes that step S210 is obtained when the signal strength of GPS is less than predetermined threshold value in testing time section
The swing arm amplitude and corresponding cadence of each swing arm；
The step S300 further includes that each swing arm amplitude and its corresponding cadence are substituted into user movement spy by step S310
Model is levied, corresponding stride is obtained.
5. a kind of wearable device, which is characterized in that including：
Data acquisition module, for when the signal strength of GPS is less than predetermined threshold value, obtaining each swing arm in testing time section
Swing arm amplitude；
Distance calculation module is electrically connected with the data acquisition module, for the swing arm amplitude and use according to each swing arm
Family motion feature model obtains the corresponding stride of each swing arm；And it is corresponding according to each swing arm in testing time section
Stride obtains running distance.
6. wearable device according to claim 5, it is characterised in that：
The data acquisition module is further used for obtaining the movement number of user when the signal strength of GPS reaches predetermined threshold value
According to as sample data；
Further include：
Data transmission blocks are electrically connected with the data acquisition module, for the sample data to be sent to server；
Model receiving module, the user movement characteristic model sent for receiving the server, and update wearable device
User movement characteristic model.
7. wearable device according to claim 6, it is characterised in that：
The data acquisition module is further used for, when the signal strength of GPS reaches predetermined threshold value, passing through wearable device
Sensor obtains the original sampling data of the original sampling data and cadence of swing arm amplitude；And by wearable device
Set the original sampling data that GPS obtains movement velocity；And the original sampling data to the swing arm amplitude, the step
The original sampling data of frequency, the movement velocity original sampling data handled, obtain the swing arm amplitude sample of time synchronization
Notebook data, cadence sample data and movement velocity sample data；And according to the movement velocity sample data and cadence sample
Data obtain corresponding stride sample data；And by the stride sample data, swing arm amplitude sample data and cadence sample
The data of notebook data composition are as the sample data；By the stride sample, swing arm amplitude sample and step of each time synchronization
A sample of the combination of frequency sample as the sample data.
8. wearable device according to claim 7, it is characterised in that：
The data acquisition module is further used for, when the signal strength of GPS is less than predetermined threshold value, obtaining in testing time section
The swing arm amplitude and corresponding cadence of each swing arm；
The distance calculation module is further used for each swing arm amplitude and its corresponding cadence substituting into user movement spy
Model is levied, corresponding stride is obtained.
9. a kind of computing system of running distance for wearable device, which is characterized in that including any institutes of claim 5-8
The wearable device stated further includes server；
The server includes：
Data reception module, for receiving the sample data from wearable device；
Model construction module is electrically connected with the data reception module, for according to the sample data, passing through supervision type machine
Learning algorithm obtains user movement characteristic model；
Model sending module is electrically connected with the model construction module, can for the user movement characteristic model to be sent to
Wearable device.
10. the computing system according to claim 9 for the running distance for wearable device, it is characterised in that：
The model construction module is further used for when the sample data updates, and updates institute according to newer sample data
State user movement characteristic model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810133055.8A CN108404394A (en) | 2018-02-09 | 2018-02-09 | The computational methods and system, wearable device of a kind of running distance for wearable device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810133055.8A CN108404394A (en) | 2018-02-09 | 2018-02-09 | The computational methods and system, wearable device of a kind of running distance for wearable device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108404394A true CN108404394A (en) | 2018-08-17 |
Family
ID=63128273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810133055.8A Pending CN108404394A (en) | 2018-02-09 | 2018-02-09 | The computational methods and system, wearable device of a kind of running distance for wearable device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108404394A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109635408A (en) * | 2018-12-05 | 2019-04-16 | 广东乐心医疗电子股份有限公司 | Distance calculation method and terminal equipment |
| CN110595502A (en) * | 2019-10-23 | 2019-12-20 | 成都乐动信息技术有限公司 | Running distance estimation method and device |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10293039A (en) * | 1996-09-11 | 1998-11-04 | Seiko Instr Inc | Portable gps receiver |
| US6145389A (en) * | 1996-11-12 | 2000-11-14 | Ebeling; W. H. Carl | Pedometer effective for both walking and running |
| JP2001027545A (en) * | 1999-05-07 | 2001-01-30 | Seiko Instruments Inc | Portable range finder, portable distance/speed meter, and distance/speed measuring method |
| JP2002162250A (en) * | 1996-09-11 | 2002-06-07 | Seiko Instruments Inc | Portable gps receiver |
| TW200708319A (en) * | 2005-08-23 | 2007-03-01 | You-Yu Chen | Arm-swinging type exercise quantity sensing apparatus |
| CN103752006A (en) * | 2009-04-26 | 2014-04-30 | 耐克国际有限公司 | GPS features and functionality in an athletic watch system |
| CN104215238A (en) * | 2014-08-21 | 2014-12-17 | 北京空间飞行器总体设计部 | Indoor positioning method of intelligent mobile phone |
| CN104287703A (en) * | 2013-06-03 | 2015-01-21 | 飞比特公司 | Use of gyroscopes in personal fitness tracking devices |
| CN105403228A (en) * | 2015-12-18 | 2016-03-16 | 北京朗动科技有限公司 | Determination method and device of movement distance |
| CN106174849A (en) * | 2016-08-31 | 2016-12-07 | 潘捌贡 | A kind of intelligence meter step running shoes based on GPS location technology |
| CN106384014A (en) * | 2016-09-29 | 2017-02-08 | 董昱 | Artificial intelligent data processing system and method based on motion sensor and GPS positioning |
| CN106525066A (en) * | 2016-10-17 | 2017-03-22 | 深圳众思科技有限公司 | Step-counting data processing method and step counter |
| CN106813676A (en) * | 2017-02-21 | 2017-06-09 | 北京邮电大学 | One kind meter step, localization method and device |
| CN107462260A (en) * | 2017-08-22 | 2017-12-12 | 上海斐讯数据通信技术有限公司 | A kind of trace generator method, apparatus and wearable device |
| CN107504979A (en) * | 2017-07-31 | 2017-12-22 | 上海斐讯数据通信技术有限公司 | Move distance computational methods and device and wearable device |
| CN107515004A (en) * | 2017-07-27 | 2017-12-26 | 上海斐讯数据通信技术有限公司 | Step size computation device and method |
| CN107631736A (en) * | 2017-09-13 | 2018-01-26 | 广东远峰电子科技股份有限公司 | A kind of stride evaluation method and device |
-
2018
- 2018-02-09 CN CN201810133055.8A patent/CN108404394A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10293039A (en) * | 1996-09-11 | 1998-11-04 | Seiko Instr Inc | Portable gps receiver |
| JP2002162250A (en) * | 1996-09-11 | 2002-06-07 | Seiko Instruments Inc | Portable gps receiver |
| US6145389A (en) * | 1996-11-12 | 2000-11-14 | Ebeling; W. H. Carl | Pedometer effective for both walking and running |
| JP2001027545A (en) * | 1999-05-07 | 2001-01-30 | Seiko Instruments Inc | Portable range finder, portable distance/speed meter, and distance/speed measuring method |
| TW200708319A (en) * | 2005-08-23 | 2007-03-01 | You-Yu Chen | Arm-swinging type exercise quantity sensing apparatus |
| CN103752006A (en) * | 2009-04-26 | 2014-04-30 | 耐克国际有限公司 | GPS features and functionality in an athletic watch system |
| CN104287703A (en) * | 2013-06-03 | 2015-01-21 | 飞比特公司 | Use of gyroscopes in personal fitness tracking devices |
| CN104215238A (en) * | 2014-08-21 | 2014-12-17 | 北京空间飞行器总体设计部 | Indoor positioning method of intelligent mobile phone |
| CN105403228A (en) * | 2015-12-18 | 2016-03-16 | 北京朗动科技有限公司 | Determination method and device of movement distance |
| CN106174849A (en) * | 2016-08-31 | 2016-12-07 | 潘捌贡 | A kind of intelligence meter step running shoes based on GPS location technology |
| CN106384014A (en) * | 2016-09-29 | 2017-02-08 | 董昱 | Artificial intelligent data processing system and method based on motion sensor and GPS positioning |
| CN106525066A (en) * | 2016-10-17 | 2017-03-22 | 深圳众思科技有限公司 | Step-counting data processing method and step counter |
| CN106813676A (en) * | 2017-02-21 | 2017-06-09 | 北京邮电大学 | One kind meter step, localization method and device |
| CN107515004A (en) * | 2017-07-27 | 2017-12-26 | 上海斐讯数据通信技术有限公司 | Step size computation device and method |
| CN107504979A (en) * | 2017-07-31 | 2017-12-22 | 上海斐讯数据通信技术有限公司 | Move distance computational methods and device and wearable device |
| CN107462260A (en) * | 2017-08-22 | 2017-12-12 | 上海斐讯数据通信技术有限公司 | A kind of trace generator method, apparatus and wearable device |
| CN107631736A (en) * | 2017-09-13 | 2018-01-26 | 广东远峰电子科技股份有限公司 | A kind of stride evaluation method and device |
Non-Patent Citations (1)
| Title |
|---|
| 陈平等: "基于WLAN与手机APP的大学生日常跑步锻炼监测管理系统的设计与应用研究", 《体育科技文献通报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109635408A (en) * | 2018-12-05 | 2019-04-16 | 广东乐心医疗电子股份有限公司 | Distance calculation method and terminal equipment |
| CN109635408B (en) * | 2018-12-05 | 2023-05-09 | 广东乐心医疗电子股份有限公司 | Distance calculation method and terminal equipment |
| CN110595502A (en) * | 2019-10-23 | 2019-12-20 | 成都乐动信息技术有限公司 | Running distance estimation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220296962A1 (en) | Methods and apparatus for power expenditure and technique determination during bipedal motion | |
| Wang et al. | Inertial sensor-based analysis of equestrian sports between beginner and professional riders under different horse gaits | |
| Guignard et al. | Behavioral dynamics in swimming: The appropriate use of inertial measurement units | |
| CN105311816A (en) | Notification device, exercise analysis system, notification method, and exercise support device | |
| EP2988099A1 (en) | Estimating local motion of physical exercise | |
| EP3163464B1 (en) | Energy consumption measuring method and energy consumption measuring system | |
| RU2107328C1 (en) | Method for tracing and displaying of position and orientation of user in three-dimensional space and device which implements said method | |
| DE112016002255T5 (en) | Data processing device, data processing method and program | |
| CN109102859A (en) | A kind of motion control method and system | |
| CN108404394A (en) | The computational methods and system, wearable device of a kind of running distance for wearable device | |
| CN107194193A (en) | A kind of ankle pump motion monitoring method and device | |
| CN107389052A (en) | A kind of ankle pump motion monitoring system and terminal device | |
| KR20160047153A (en) | Method and apparatus for managing exercise | |
| KR20170127550A (en) | A method for determining the type of human movement activity and a device for implementing the same | |
| JP6421475B2 (en) | Data analysis apparatus, data analysis method, and data analysis program | |
| JPWO2020071149A1 (en) | Information processing device | |
| JP2013188294A (en) | Exercise information generation system, exercise information generation program and exercise information generation method | |
| CN109646902A (en) | A kind of body building metering method based on identification equipment | |
| CN113869594A (en) | User physical performance score prediction method and device, electronic device and storage medium | |
| JP2015109946A (en) | Exercise quantity calculation method, exercise quantity calculation device, and portable apparatus | |
| JP2013188293A (en) | Exercise information display system, exercise information display program and exercise information display method | |
| CN106031824A (en) | A wearable device applicable for different motion types | |
| CN111598134B (en) | Test analysis method for gymnastics movement data monitoring | |
| CN111354435B (en) | Monitoring method based on running exercise data | |
| WO2018179664A1 (en) | Information processing device, information processing method, and program |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180817 |
|
| WD01 | Invention patent application deemed withdrawn after publication |