CN110399032A - The control method and device of wearable device - Google Patents
The control method and device of wearable device Download PDFInfo
- Publication number
- CN110399032A CN110399032A CN201910616827.8A CN201910616827A CN110399032A CN 110399032 A CN110399032 A CN 110399032A CN 201910616827 A CN201910616827 A CN 201910616827A CN 110399032 A CN110399032 A CN 110399032A
- Authority
- CN
- China
- Prior art keywords
- action
- machine learning
- learning model
- display screen
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of control method of wearable device and devices.Wherein, this method comprises: the state of detection display screen, wherein the state of display screen includes: bright screen or the screen that goes out;Preset machine learning model is selected according to state, wherein machine learning model is obtained according to sample data training, and sample data includes: the motion characteristic data of a variety of sample actions and the type of action of sample action;Based on the action data of sensor acquisition, the type of action of wearing main body is determined by the machine learning model of selection.The present invention solves the movement for determining user's wrist jointly by 3-axis acceleration sensor and gyroscope in the prior art, leads to the technical problem that power consumption is excessive.
Description
Technical field
The present invention relates to wearable device fields, in particular to the control method and device of a kind of wearable device.
Background technique
Currently, the wearable product of the intelligence such as bracelet, wrist-watch is equipped with sensor abundant mostly, including 3-axis acceleration
Sensor and three-axis gyroscope person are in the majority, and wearable product is based on 3-axis acceleration sensor and three-axis gyroscope, to user hand
The movement of wrist is judged, thus the purpose that the time limit controls product based on the movement of user's wrist.
Although using 3-axis acceleration sensor and both sensors of three-axis gyroscope carry out the identification of list action compared with
To be accurate, but the power consumption of gyroscope is relatively high, for the product of 24 hour operation, undoubtedly can relative reduction product continuation of the journey
Time.
For the movement for determining user's wrist jointly by 3-axis acceleration sensor and gyroscope in the prior art, cause
The excessive problem of power consumption, currently no effective solution has been proposed.
Summary of the invention
The embodiment of the invention provides a kind of control method of wearable device and devices, at least to solve to lead in the prior art
The movement that 3-axis acceleration sensor and gyroscope determine user's wrist jointly is crossed, the technical problem that power consumption is excessive is caused.
According to an aspect of an embodiment of the present invention, a kind of control method of object wearing device is provided, object wearing device includes
The sensor of display screen and the action data for acquiring wearing main body, this method comprises: the state of detection display screen, wherein
The state of display screen includes: bright screen or the screen that goes out;Preset machine learning model is selected according to state, wherein machine learning model
It is obtained according to sample data training, sample data includes: the motion characteristic data and the movement of sample action of a variety of sample actions
Type;Based on the action data of sensor acquisition, the type of action of wearing main body is determined by the machine learning model of selection.
Further, object wearing device is wrist object wearing device, and machine learning model includes: for examining to lift wrist movement
The first machine learning model for surveying, for for the second machine learning model detected and for dynamic to wrist is fallen of turning over
The third machine learning model detected, wherein preset machine learning model is selected according to state, comprising: if aobvious
The state of display screen is bright screen, then selects third machine learning model;If the state of display screen is the screen that goes out, the first machine is selected
Learning model and the second machine learning model.
Further, in the action data acquired based on sensor, wearing master is determined by the machine learning model of selection
After the type of action of body, the state of display screen is adjusted according to type of action, wherein the shape of display screen is adjusted according to type of action
If the step of state includes: type of action for lift wrist or turns wrist, the bright screen of display screen is controlled;If type of action is to fall wrist,
Control display screen goes out screen.
Further, sensor is 3-axis acceleration sensor.
Further, action data is pre-processed;Feature extraction is carried out to pretreated movement, obtains movement number
According to characteristic;Based on characteristic, the type of action of wearing main body is determined by the machine learning model of selection.
Further, the action data of fixed duration is intercepted;Low-pass filtering treatment is carried out to the action data of fixed duration,
Obtain pretreated action data.
Further, down-sampling is carried out to action data, obtains characteristic;Or based on action data determine movement
Characteristic value on preset attribute, and determine that characteristic value is characterized data.
According to an aspect of an embodiment of the present invention, a kind of control device of object wearing device is provided, object wearing device includes
The sensor of display screen and the action data for dressing main body, wherein the control device of object wearing device includes: detection module,
For detecting the state of display screen, wherein the state of display screen includes: bright screen or the screen that goes out;Selecting module, for being selected according to state
Select preset machine learning model, wherein machine learning model is obtained according to sample data training, and sample data includes: a variety of
The motion characteristic data of sample action and the type of action of sample action;Determining module, the movement for being acquired based on sensor
Data determine the type of action of wearing main body by the machine learning model of selection.
According to an aspect of an embodiment of the present invention, a kind of storage medium is provided, storage medium includes the program of storage,
Wherein, equipment where controlling storage medium when program is run executes the control method of above-mentioned object wearing device.
According to an aspect of an embodiment of the present invention, a kind of processor is provided, processor is for running program, wherein
Program executes the control method of above-mentioned object wearing device when running.
In embodiments of the present invention, the state of display screen is detected, wherein the state of display screen includes: bright screen or the screen that goes out;Root
Preset machine learning model is selected according to state, wherein machine learning model is obtained according to sample data training, sample data packet
It includes: the motion characteristic data of a variety of sample actions and the type of action of sample action;Based on the action data of sensor acquisition, lead to
The machine learning model for crossing selection determines the type of action of wearing main body.Above scheme, which can be applied to, is equipped with 3-axis acceleration biography
In the bracelet or smartwatch of sensor or the integrated sensor comprising 3-axis acceleration sensor, the movement of sensor detection is utilized
Data without using gyroscope, and then have been reached reduction wearing and set using the movement of the method identification wrist of machine learning
The purpose of standby power consumption, solves and determines user's wrist jointly by 3-axis acceleration sensor and gyroscope in the prior art
Movement, leads to the technical problem that power consumption is excessive, has achieved the effect that the cruise duration for increasing wearable device.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of the control method of object wearing device according to an embodiment of the present invention;
Fig. 2 is a kind of flow chart according to action control wearable device display screen according to an embodiment of the present invention;And
Fig. 3 is the schematic diagram of the control device of object wearing device according to an embodiment of the present invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
Embodiment 1
According to embodiments of the present invention, a kind of embodiment of the control method of object wearing device is provided, it should be noted that In
The step of process of attached drawing illustrates can execute in a computer system such as a set of computer executable instructions, also,
It, in some cases, can be to be different from shown in sequence execution herein although logical order is shown in flow charts
The step of out or describing.
Fig. 1 is the flow chart of the control method of object wearing device according to an embodiment of the present invention, and the object wearing device includes aobvious
The sensor of display screen and the action data for dressing main body, as shown in Figure 1, this method comprises the following steps:
Step S102 detects the state of display screen, wherein the state of display screen includes: bright screen or the screen that goes out.
Specifically, above-mentioned bright screen is for indicating that display screen is lighted, the screen that goes out is for indicating display screen in a dormant state.In order to
Achieve the purpose that economize on electricity, object wearing device is generally in screen state of going out, and bright screen state is only in the preset time being waken up.With
For Intelligent bracelet, the physiology that the display screen of Intelligent bracelet is displayed for current time and the user for wearing bracelet is special
Sign.When user needs to check time or physiological characteristic, the display screen of Intelligent bracelet is waken up, the display screen point of Intelligent bracelet
It is bright, and it is in bright screen state.
Above-mentioned wearable device can be Intelligent bracelet, smartwatch, intelligent glasses, intelligent helmet etc., and following embodiments are logical
It crosses for the wrists object wearing device such as Intelligent bracelet or wrist-watch and is illustrated.
Step S104 selects preset machine learning model according to state, wherein machine learning model is according to sample data
Training obtains, and sample data includes: the motion characteristic data of a variety of sample actions and the type of action of sample action.
In the above scheme, it is preset with the machine learning model for detecting various motion, every kind of machine learning model
Network structure can be identical, such as: decision-tree model, Random Forest model, supporting vector machine model etc..The structure and ginseng of model
Number obtains in the learning process to sample data.Sample data can be the empirical data for artificially collecting or collecting online.
In an alternative embodiment, every kind of movement can correspond to a machine learning model.It is lifted with wrist dynamic
It is illustrated as example, in the training machine learning model, used data may include the feature of a variety of lift wrist movements
Data and the characteristic of non-lift wrist movement act non-lift wrist using the characteristic for lifting wrist movement as positive sample data
Characteristic as negative sample data.
Above-mentioned steps select corresponding machine learning model according to the different conditions of display screen, (to use wearing main body
The user of wearable device) movement detect.The movement of detection can be the movement for being controlled display screen,
That is, above-mentioned steps are in the case where display screen is in different conditions, whether detection wearable device, which generates triggering display screen state, changes
Movement.
For example, may include: to extinguish display screen, adjustment display to the operation of display screen when the screen of display screen is lighted
The brightness of screen.And extinguishing the corresponding movement of display screen can be to fall wrist, the movement for adjusting brightness of display screen can be rotation wrist, because
This, when the bright screen of the state of display screen, selected machine learning model can be to fall wrist detection model and rotation wrist detection
Model.
Step S106 determines wearing main body by the machine learning model of selection based on the action data of sensor acquisition
Type of action.
Specifically, the sensor can be 3-axis acceleration sensor, action data can sense for 3-axis acceleration
The acceleration information that device detects.
In an alternative embodiment, action data can be subjected to feature extraction, is input to selected machine learning
Model, to obtain the result of machine learning model output.The output result of machine learning model is for indicating that the movement refers to
Surely the probability acted can determine type of action according to the output result.
From the foregoing, it will be observed that the state of detection display screen, wherein the state of display screen includes: bright screen or the screen that goes out;It is selected according to state
Select preset machine learning model, wherein machine learning model is obtained according to sample data training, and sample data includes: a variety of
The motion characteristic data of sample action and the type of action of sample action;Based on the action data of sensor acquisition, pass through selection
Machine learning model determine wearing main body type of action.Above scheme can be applied to be equipped with 3-axis acceleration sensor or
In the bracelet or smartwatch of integrated sensor comprising 3-axis acceleration sensor, the action data detected using sensor,
Using the movement of the method identification wrist of machine learning, without using gyroscope, and then reduction wearable device consumption is reached
The purpose of electricity solves and determines the dynamic of user's wrist jointly by 3-axis acceleration sensor and gyroscope in the prior art
Make, lead to the technical problem that power consumption is excessive, has achieved the effect that the cruise duration for increasing wearable device.
Used machine learning model is to sample data by being learnt to obtain when further, due to detection, because
This with carried out by the way of logic judgment detection compared with, can overcome carry out detecting by the way of logic judgment it is existing
Limitation.
As a kind of optional embodiment, object wearing device is wrist object wearing device, and machine learning model includes: for lift
Wrist movement detected the first machine learning model, for for turn over the second machine learning model detected and
For acting the third machine learning model that is detected to falling wrist, wherein preset machine learning model is selected according to state,
If the state for including: display screen is bright screen, third machine learning model is selected;If the state of display screen is the screen that goes out,
Select the first machine learning model and the second machine learning model.
Specifically, above-mentioned three kinds of machine learning models are obtained by three groups of different sample data training, by different type
Movement detected using different machine learning models, have more accurate testing result.
In an alternative embodiment, when display screen be in go out shield state when, need detect can control display screen point
Bright movement, such as lift wrist or turn over, therefore select the first machine learning model and the second machine learning model to movement
Data are detected.
In another kind optionally implements, when display screen is in bright screen state, display screen can be controlled by needing to detect
It goes out bright movement, such as falls wrist movement, therefore third machine learning model is selected to detect action data.
Fig. 2 is a kind of flow chart according to action control wearable device display screen according to an embodiment of the present invention, in conjunction with Fig. 2
It is shown, after carrying out sliding window processing and feature extraction to action data, the whether bright screen of display screen is judged, if display screen is bright
Screen is then carried out falling wrist detection using third machine learning model, if the not bright screen of display screen, uses the first machine learning model
It carries out lift wrist simultaneously with the second machine learning model and to turn wrist to be detected.
As in a kind of optional embodiment, in the action data acquired based on sensor, pass through the machine learning of selection
After model determines the type of action of wearing main body, method further include: the state of display screen is adjusted according to type of action, wherein
If the step of adjusting the state of display screen according to type of action includes: type of action for lift wrist or turn wrist, display screen is controlled
Bright screen;If type of action is to fall wrist, controls display screen and go out screen.
In an alternative embodiment, it by taking user checks the time using bracelet as an example, in order to achieve the purpose that economize on electricity, shows
Display screen is generally in screen state of going out, and when user needs to check bracelet, makes the movement of lift wrist, object wearing device passes through the first machine
Learning model detects the lift wrist movement of user, therefore controls the bright screen of display screen, and then reached user and only lifted wrist, without carrying out
Touch-control bracelet etc. other operation, can bright screen effect.
In another kind optionally implements, still by taking user checks the time using bracelet as an example, the wrist of user is in table
More than face, at this time if user needs to check bracelet, that is, the movement for turning wrist is made, object wearing device passes through the second machine learning model
It detects turning over for user, therefore controls the bright screen of display screen, and then reached user and only turned wrist, without carrying out touch-control bracelet
Deng other operation, can bright screen effect.
In yet a further optional embodiment, also by taking user checks the time using bracelet as an example, when user has checked bracelet
Afterwards, the movement for growing wrist is done, object wearing device detects that the wrist that falls of user acts by third machine learning model, therefore controls aobvious
Display screen is gone out screen, and then has been reached user and only fallen wrist, without carrying out other operations such as touch-control bracelet, the effect for the screen that can go out.
Still with shown in Fig. 2, if detecting movement as lift wrist or turning wrist, the bright screen of display screen is controlled, and aobvious in control
After the bright screen of display screen, detection display screen whether light, if display screen has been lighted, keep the illuminating state of display screen and continue into
Taking action, it is to be detected to make, if display screen is non-lit up, detects new action data again.If detecting that movement is to fall wrist,
Whether control display screen goes out screen, and after control display screen goes out screen, detect display screen and go out screen, and the screen if display screen has gone out is protected
It holds going out for display screen and screen state and continues to act to be detected, the screen if display screen does not go out detects new movement number again
According to.
As a kind of optional embodiment, sensor is 3-axis acceleration sensor.
The machine learning model of selection is passed through based on the action data of sensor acquisition as a kind of optional embodiment
Determine the type of action of wearing main body, comprising: pre-process to action data;Feature is carried out to pretreated movement to mention
It takes, obtains the characteristic of action data;Based on characteristic, the dynamic of wearing main body is determined by the machine learning model of selection
Make type.
Specifically, above-mentioned pre-treatment step is used to denoise action data, to obtain accurate testing result.
Features described above is extracted for obtaining the input of machine learning model based on action data.
As a kind of optional embodiment, action data is pre-processed, comprising: intercept the movement number of fixed duration
According to;Low-pass filtering treatment is carried out to the action data of fixed duration, obtains pretreated action data.
Specifically, above-mentioned low-pass filtering method can be with are as follows: Bessel filter, Chebyshev filter, Butterworth filter
Wave device etc..
In an alternative embodiment, above-mentioned fixed duration can be 1s or 2s, intercept the action data of fixed duration
Afterwards, it is handled using the data of interception as processing unit, treatment process can be, and be filtered using low-pass filter to it
Wave keeps data smoother to remove the trip point and high-frequency noise in data.
As a kind of optional embodiment, feature extraction is carried out to pretreated movement, obtains the feature of action data
Data, comprising: down-sampling is carried out to action data, obtains characteristic;Or belonging to default for movement is determined based on action data
Property on characteristic value, and determine characteristic value be characterized data.
Specifically, the characteristic value on above-mentioned preset attribute may include: movement duration, shock range, movement front and back amplitude
Difference, data distribution dispersion degree etc..
Above scheme provides two kinds of feature extracting methods, it should be noted that the spy of action data in detection process
It is identical to the feature extraction mode of sample action data with sample data to levy extracting mode.
First way is that down-sampling is carried out to action data, which carries out down-sampling for pretreated action data
Afterwards directly as characteristic, to reduce the dimension of feature vector, such as: former sample frequency be 50Hz, can by sampling or
Method for resampling is down to 25Hz.
The second way is to be converted into limited discrete spy to pretreated action data by way of feature extraction
Sign, the type of discrete features may include: movement duration, shock range, movement front and back Magnitude Difference, data distribution dispersion degree
Deng.
Above two characteristic can be used alone, and can also be used in combination, and the series of features of extraction be formed special
It is input to corresponding model after sign vector, the testing result of model output can be obtained.
Embodiment 2
According to embodiments of the present invention, a kind of control device of object wearing device is provided, object wearing device includes display screen and use
In the sensor of the action data of wearing main body, Fig. 3 is the signal of the control device of object wearing device according to an embodiment of the present invention
Figure, the control device of object wearing device include:
Detection module 30, for detecting the state of display screen, wherein the state of display screen includes: bright screen or the screen that goes out.
Selecting module 32, for selecting preset machine learning model according to state, wherein machine learning model is according to sample
Notebook data training obtains, and sample data includes: the motion characteristic data of a variety of sample actions and the type of action of sample action.
Determining module 34, the action data for being acquired based on sensor are worn by the machine learning model determination of selection
Wear the type of action of main body.
As a kind of optionally embodiment, object wearing device is wrist object wearing device, and machine learning model includes: for lift
Wrist movement detected the first machine learning model, for for turn over the second machine learning model detected and
For acting the third machine learning model that is detected to falling wrist, wherein selecting module includes: first choice submodule, is used
If the state in display screen is bright screen, third machine learning model is selected;Second selection submodule, if being used for display screen
State be to go out screen, then select the first machine learning model and the second machine learning model.
As a kind of optionally embodiment, above-mentioned apparatus further include: adjustment module, for being moved what is acquired based on sensor
Make data, after the type of action that wearing main body is determined by the machine learning model of selection, is adjusted and shown according to type of action
The state of screen, wherein adjustment module includes: the first control submodule, if being to lift wrist or turn wrist for type of action, is controlled
The bright screen of display screen;Second control submodule controls display screen and goes out screen if being to fall wrist for type of action.
As one kind, optionally embodiment, sensor are 3-axis acceleration sensor.
It include: pretreatment submodule as a kind of optionally embodiment, determining module, for being located in advance to action data
Reason;Feature deriving means obtain the characteristic of action data for carrying out feature extraction to pretreated movement;It determines
Submodule determines the type of action of wearing main body by the machine learning model of selection for being based on characteristic.
As a kind of optionally embodiment, pretreatment submodule includes: interception unit, for intercepting the movement of fixed duration
Data;Filter unit carries out low-pass filtering treatment for the action data to fixed duration, obtains pretreated movement number
According to.
It include: downsampling unit as a kind of optionally embodiment, feature deriving means, for being carried out down to action data
Sampling, obtains characteristic;Or feature extraction unit, for determining the feature on preset attribute of movement based on action data
Value, and determine that characteristic value is characterized data.
Embodiment 3
According to embodiments of the present invention, a kind of storage medium is provided, the storage medium includes the program of storage, wherein
Equipment where controlling the storage medium in described program operation executes the control method of object wearing device described in embodiment 1.
Embodiment 4
According to embodiments of the present invention, a kind of processor is provided, processor is for running program, wherein described program fortune
The control method of object wearing device described in embodiment 1 is executed when row.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
In the above embodiment of the invention, it all emphasizes particularly on different fields to the description of each embodiment, does not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code
Medium.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of control method of object wearing device, which is characterized in that the object wearing device includes display screen and dresses for acquiring
The sensor of the action data of main body, wherein the control method of the object wearing device includes:
Detect the state of the display screen, wherein the state of the display screen includes: bright screen or the screen that goes out;
Preset machine learning model is selected according to the state, wherein the machine learning model is according to sample data training
It obtains, the sample data includes: the motion characteristic data of a variety of sample actions and the type of action of the sample action;
Based on the action data of sensor acquisition, the wearing main body is determined by the machine learning model of selection
Type of action.
2. the method according to claim 1, wherein the object wearing device is wrist object wearing device, the machine
Learning model includes: for acting the first machine learning model detected, for examining for turning over to lift wrist
The second machine learning model for surveying and for acting the third machine learning model that is detected to falling wrist, wherein according to described
State selects preset machine learning model, comprising:
If the state of the display screen is bright screen, the third machine learning model is selected;
If the state of the display screen is the screen that goes out, first machine learning model and the second machine learning mould are selected
Type.
3. according to the method described in claim 2, it is characterized in that, passing through in the action data acquired based on the sensor
After the machine learning model of selection determines the type of action of the wearing main body, the method also includes: according to described
Type of action adjusts the state of the display screen, wherein the step of adjusting the state of the display screen according to the type of action
Include:
If the type of action is lift wrist or turns wrist, the bright screen of the display screen is controlled;
If the type of action is to fall wrist, controls the display screen and go out screen.
4. the method according to claim 1, wherein the sensor is 3-axis acceleration sensor.
5. method as claimed in any of claims 1 to 4, which is characterized in that based on the dynamic of sensor acquisition
Make data, the type of action of the wearing main body determined by the machine learning model of selection, comprising:
The action data is pre-processed;
Feature extraction is carried out to the pretreated movement, obtains the characteristic of the action data;
Based on the characteristic, the type of action of the wearing main body is determined by the machine learning model of selection.
6. according to the method described in claim 5, it is characterized in that, being pre-processed to the action data, comprising:
Intercept the action data of fixed duration;
Low-pass filtering treatment is carried out to the action data of the fixed duration, obtains pretreated action data.
7. according to the method described in claim 5, it is characterized in that, being obtained to the pretreated movement progress feature extraction
To the characteristic of the action data, comprising:
Down-sampling is carried out to the action data, obtains the characteristic;Or
The characteristic value on preset attribute of the movement is determined based on the action data, and determines that the characteristic value is described
Characteristic.
8. a kind of control device of object wearing device, which is characterized in that the object wearing device includes display screen and for dressing main body
Action data sensor, wherein the control device of the object wearing device includes:
Detection module, for detecting the state of the display screen, wherein the state of the display screen includes: bright screen or the screen that goes out;
Selecting module, for selecting preset machine learning model according to the state, wherein the machine learning model according to
Sample data training obtains, the sample data include: a variety of sample actions motion characteristic data and the sample action
Type of action;
Determining module, the action data for being acquired based on the sensor are determined by the machine learning model of selection
The type of action of the wearing main body.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program
When control the storage medium where equipment perform claim require any one of 1 to 7 described in object wearing device control method.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit require any one of 1 to 7 described in object wearing device control method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910616827.8A CN110399032A (en) | 2019-07-09 | 2019-07-09 | The control method and device of wearable device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910616827.8A CN110399032A (en) | 2019-07-09 | 2019-07-09 | The control method and device of wearable device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110399032A true CN110399032A (en) | 2019-11-01 |
Family
ID=68324022
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910616827.8A Pending CN110399032A (en) | 2019-07-09 | 2019-07-09 | The control method and device of wearable device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110399032A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110990819A (en) * | 2019-12-25 | 2020-04-10 | 浙江每日互动网络科技股份有限公司 | Method and server for acquiring gait feature data of terminal user based on mobile terminal data |
CN111062353A (en) * | 2019-12-25 | 2020-04-24 | 浙江每日互动网络科技股份有限公司 | Method and server for acquiring gait feature data of terminal user based on mobile terminal data |
CN111061376A (en) * | 2019-12-25 | 2020-04-24 | 浙江每日互动网络科技股份有限公司 | Method and server for identifying terminal user change machine based on mobile terminal data |
CN111062352A (en) * | 2019-12-25 | 2020-04-24 | 浙江每日互动网络科技股份有限公司 | Method and server for recognizing gait of terminal user based on mobile terminal data |
CN111126294A (en) * | 2019-12-25 | 2020-05-08 | 浙江每日互动网络科技股份有限公司 | Method and server for recognizing gait of terminal user based on mobile terminal data |
CN111142688A (en) * | 2019-12-25 | 2020-05-12 | 浙江每日互动网络科技股份有限公司 | Method and server for identifying terminal user change machine based on mobile terminal data |
CN117573269A (en) * | 2024-01-15 | 2024-02-20 | 荣耀终端有限公司 | Screen lighting correction method and device for wearable device and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105302308A (en) * | 2015-11-05 | 2016-02-03 | 上海卓易科技股份有限公司 | Intelligent wrist wearing device and automatic screen turn-on method and system therefor |
US9329694B2 (en) * | 2014-06-06 | 2016-05-03 | Google Technology Holdings LLC | Preemptive machine learning-based gesture recognition |
CN106020670A (en) * | 2016-05-24 | 2016-10-12 | 北京搜狗科技发展有限公司 | Screen lightening control method, device and electronic equipment |
CN106293072A (en) * | 2016-08-01 | 2017-01-04 | 广东乐源数字技术有限公司 | A kind of Intelligent bracelet turns the method for wrist bright screen |
CN107155005A (en) * | 2017-04-27 | 2017-09-12 | 上海斐讯数据通信技术有限公司 | A kind of intelligent wrist wearable device bright screen control method and system |
CN107797666A (en) * | 2017-11-21 | 2018-03-13 | 出门问问信息科技有限公司 | Gesture identification method, device and electronic equipment |
-
2019
- 2019-07-09 CN CN201910616827.8A patent/CN110399032A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9329694B2 (en) * | 2014-06-06 | 2016-05-03 | Google Technology Holdings LLC | Preemptive machine learning-based gesture recognition |
CN105302308A (en) * | 2015-11-05 | 2016-02-03 | 上海卓易科技股份有限公司 | Intelligent wrist wearing device and automatic screen turn-on method and system therefor |
CN106020670A (en) * | 2016-05-24 | 2016-10-12 | 北京搜狗科技发展有限公司 | Screen lightening control method, device and electronic equipment |
CN106293072A (en) * | 2016-08-01 | 2017-01-04 | 广东乐源数字技术有限公司 | A kind of Intelligent bracelet turns the method for wrist bright screen |
CN107155005A (en) * | 2017-04-27 | 2017-09-12 | 上海斐讯数据通信技术有限公司 | A kind of intelligent wrist wearable device bright screen control method and system |
CN107797666A (en) * | 2017-11-21 | 2018-03-13 | 出门问问信息科技有限公司 | Gesture identification method, device and electronic equipment |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110990819A (en) * | 2019-12-25 | 2020-04-10 | 浙江每日互动网络科技股份有限公司 | Method and server for acquiring gait feature data of terminal user based on mobile terminal data |
CN111062353A (en) * | 2019-12-25 | 2020-04-24 | 浙江每日互动网络科技股份有限公司 | Method and server for acquiring gait feature data of terminal user based on mobile terminal data |
CN111061376A (en) * | 2019-12-25 | 2020-04-24 | 浙江每日互动网络科技股份有限公司 | Method and server for identifying terminal user change machine based on mobile terminal data |
CN111062352A (en) * | 2019-12-25 | 2020-04-24 | 浙江每日互动网络科技股份有限公司 | Method and server for recognizing gait of terminal user based on mobile terminal data |
CN111126294A (en) * | 2019-12-25 | 2020-05-08 | 浙江每日互动网络科技股份有限公司 | Method and server for recognizing gait of terminal user based on mobile terminal data |
CN111142688A (en) * | 2019-12-25 | 2020-05-12 | 浙江每日互动网络科技股份有限公司 | Method and server for identifying terminal user change machine based on mobile terminal data |
CN110990819B (en) * | 2019-12-25 | 2023-04-21 | 每日互动股份有限公司 | Method and server for acquiring gait feature data of terminal user based on mobile terminal data |
CN111062353B (en) * | 2019-12-25 | 2023-04-28 | 每日互动股份有限公司 | Method and server for acquiring gait feature data of terminal user based on mobile terminal data |
CN117573269A (en) * | 2024-01-15 | 2024-02-20 | 荣耀终端有限公司 | Screen lighting correction method and device for wearable device and storage medium |
CN117573269B (en) * | 2024-01-15 | 2024-06-04 | 荣耀终端有限公司 | Screen lighting correction method and device for wearable device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110399032A (en) | The control method and device of wearable device | |
CN107886061B (en) | Human body behavior recognition method and system based on multi-mode deep Boltzmann machine | |
CN103793075B (en) | Recognition method applied to intelligent wrist watch | |
CN105205436B (en) | A kind of gesture recognition system based on forearm bioelectricity multisensor | |
CN111382714B (en) | Image detection method, device, terminal and storage medium | |
CN105302308A (en) | Intelligent wrist wearing device and automatic screen turn-on method and system therefor | |
US10969864B2 (en) | Method, apparatus and device for detecting fatigue state | |
CN110728241A (en) | Driver fatigue detection method based on deep learning multi-feature fusion | |
CN110349147A (en) | Training method, the lesion recognition methods of fundus flavimaculatus area, device and the equipment of model | |
CN106599914A (en) | Multi-sensor fused wristed falling detection method and device | |
CN107085367B (en) | Method for lightening screen of smart watch by raising hand | |
CN106919958A (en) | A kind of human finger action identification method based on intelligent watch | |
CN110123313A (en) | A kind of self-training brain machine interface system and related training method | |
CN107277222A (en) | User behavior state judging method based on mobile phone built-in sensors | |
CN106293045A (en) | Display control method, display control unit and subscriber equipment | |
CN109034060B (en) | Wearing state detection method and device | |
CN109770900A (en) | Brain-computer interface based on convolutional neural networks instructs delivery method, system, device | |
CN105373712A (en) | Mobile terminal unlocking system and mobile terminal unlocking method based on neural network | |
CN106292871A (en) | A kind of Intelligent bracelet realizing turning wrist bright screen | |
CN105877701A (en) | Method and device for analyzing sleep period in real time and intelligent wearable equipment | |
CN109805923A (en) | Wearable device, signal processing method and device | |
CN114081513A (en) | Electromyographic signal-based abnormal driving behavior detection method and system | |
CN106506823A (en) | For the intelligent wearable device of control terminal equipment, system, method and apparatus | |
CN110584675B (en) | Information triggering method and device and wearable device | |
CN108354591A (en) | A kind of operating personnel's degree of safety method of discrimination and equipment |
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 |
Application publication date: 20191101 |
|
RJ01 | Rejection of invention patent application after publication |