CN106598222A - Scene mode switching method and system - Google Patents

Scene mode switching method and system Download PDF

Info

Publication number
CN106598222A
CN106598222A CN201611019977.3A CN201611019977A CN106598222A CN 106598222 A CN106598222 A CN 106598222A CN 201611019977 A CN201611019977 A CN 201611019977A CN 106598222 A CN106598222 A CN 106598222A
Authority
CN
China
Prior art keywords
classification
kinestate
identification module
grader
exercise 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
Application number
CN201611019977.3A
Other languages
Chinese (zh)
Inventor
邓星
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Feixun Data Communication Technology Co Ltd
Original Assignee
Shanghai Feixun Data Communication Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Feixun Data Communication Technology Co Ltd filed Critical Shanghai Feixun Data Communication Technology Co Ltd
Priority to CN201611019977.3A priority Critical patent/CN106598222A/en
Publication of CN106598222A publication Critical patent/CN106598222A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2203/00Indexing scheme relating to G06F3/00 - G06F3/048
    • G06F2203/01Indexing scheme relating to G06F3/01
    • G06F2203/011Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention provides a scene mode switching method. The method comprises the steps of obtaining motion data of a user; obtaining a motion state of a current user by using a classification identification module according to the motion data; obtaining an occurrence frequency of each motion state; and if the continuous occurrence frequency of the same motion state reaches a preset threshold, switching to a scene mode corresponding to the motion state. By adopting the method, the motion state of the current user can be obtained through the classification identification module according to the obtained motion data, and when the continuous occurrence frequency of the same motion state reaches the threshold, the operation of switching to the scene mode corresponding to the motion state which continuously occurs is performed, so that the scene mode can be switched according to the motion state of the user, and the scene mode switching is more accurate; the scene mode switching is performed only when the motion state occurs for multiple times continuously, so that incorrect switching caused by errors is avoided; and the motion state switching of an intelligent wearable terminal is automatically finished, so that the accuracy of acquiring the motion data of the user is improved and the user experience is enhanced.

Description

A kind of changing method and system of scene mode
Technical field
The present invention relates to electronic information technical field, more particularly to a kind of changing method and system of scene mode.
Background technology
With the development and the progress of society of science and technology, various smart machines such as mobile phone, panel computer, intelligent watch etc. Equipment is increasingly popularized.Smart machine has become the important component part of people's life, carries amusement, communication, online etc. Task.Wherein, Intelligent worn device is possessing part computing function, can connect mobile phone and the portable accessory form of each Terminal Type Exist, its product form is included with wrist as the watch classes that support, including the product such as wrist-watch, wrist strap, bracelet, or is worn on Other positions, such as intelligent belt, tape etc..By Intelligent worn device, user can record exercise in daily life, There is the real time data such as diet and location information sleep, part, and these data are synchronous with mobile phone, flat board, play and pass through The effect of data-guiding healthy living.
The existing smart motion wrist-watch kinestate to be detected includes walking, runs, swims, riding.With Increasing using scene, in different application scenarios, needs the data of measurement different, continuous general with smart motion wrist-watch And and function gradual perfection, it would be desirable to a kind of more intelligent experience mode.
Therefore, Intelligent worn device how is enable to automatically switch to corresponding scene and mould according to the kinestate of user Formula, becomes the problem of this area urgent need to resolve.
The content of the invention
It is an object of the invention to provide the changing method and system of a kind of scene mode, can be according to the kinestate of user Automatically switch to corresponding scene and pattern.
The purpose of the present invention is achieved through the following technical solutions:
A kind of changing method of scene mode, including:
Obtain the exercise data of user;
According to the exercise data, using Classification and Identification module the kinestate of active user is obtained;
Obtain the occurrence number of each kinestate;
If the continuous occurrence number of same kinestate reaches default threshold value, the field being switched to corresponding to the kinestate Scape pattern.
Preferably, the Classification and Identification module includes support vector machine;It is described currently to be used according to the motion capture The step of kinestate at family, specifically includes:
According to the exercise data for obtaining, using support vector machine the kinestate of active user is obtained.
Preferably, the support vector machine are specifically included:Ground floor grader, second layer grader, third layer grader; The step of use support vector machine obtain the kinestate of active user specifically includes:
Obtain the kinestate of active user using ground floor grader, second layer grader, third layer grader successively.
Preferably, wherein, the classification foundation of the ground floor grader at least includes the first motion index, the second layer The classification foundation of grader at least includes the second motion index, and the classification foundation of the third layer grader is at least including the 3rd fortune Dynamic index.
Preferably, after the step of scene mode being switched to corresponding to the kinestate described, methods described enters one Step includes:
Exercise data under Classification and Identification module collection current scene pattern, and the exercise data is stored in into Classification and Identification In module, and the data base in Classification and Identification module is updated.
The present invention discloses a kind of switched system of scene mode, including:
Acquisition module, for obtaining the exercise data of user;
Classification and Identification module, for according to the exercise data, obtaining the kinestate of active user;
Statistical module, for obtaining the occurrence number of each kinestate;
Handover module, if reaching default threshold value for the continuous occurrence number of same kinestate, is switched to the motion Scene mode corresponding to state.
Preferably, the Classification and Identification module includes support vector machine;The Classification and Identification module specifically for:
According to the exercise data for obtaining, using support vector machine the kinestate of active user is obtained.
Preferably, the support vector machine are specifically included:Ground floor grader, second layer grader, third layer grader; The Classification and Identification module specifically for:
Obtain the kinestate of active user using ground floor grader, second layer grader, third layer grader successively.
Preferably, wherein, the classification foundation of the ground floor grader at least includes the first motion index, the second layer The classification foundation of grader at least includes the second motion index, and the classification foundation of the third layer grader is at least including the 3rd fortune Dynamic index.
Preferably, the system is further included:Update module, under Classification and Identification module collection current scene pattern Exercise data, and the exercise data is stored in Classification and Identification module, and the data base in Classification and Identification module is carried out Update.
The changing method of the scene mode of the present invention is due to including:Obtain the exercise data of user;According to the motion number According to using the kinestate of Classification and Identification module acquisition active user;Obtain the occurrence number of each kinestate;If same fortune The continuous occurrence number of dynamic state reaches default threshold value, then the scene mode being switched to corresponding to the kinestate.Using this Mode, it is possible to according to the exercise data for obtaining, the kinestate of active user is obtained by Classification and Identification module, and work as same When the number of times that kinestate continuously occurs reaches threshold value, the scene mould corresponding to the kinestate of the continuous appearance is just switched to Formula, so not only can be according to the kinestate of user come handoff scenario pattern and more accurate, only when continuous several times go out Can just switch now, it is to avoid the caused mistake switching because of error, be automatically performed the switching of intelligence wearing motion state of terminal, The accuracy of user exercise data acquisition is improved, while improving Consumer's Experience.
Description of the drawings
Fig. 1 is the flow chart of the changing method of the scene mode of the embodiment of the present invention;
Fig. 2 is the flow chart of the method that the kinestate of the embodiment of the present invention is obtained;
Fig. 3 is the flow chart of the support vector machine switching and the method for updating of the embodiment of the present invention;
Fig. 4 is the schematic diagram of the switched system of the scene mode of the embodiment of the present invention.
Specific embodiment
Although operations to be described as flow chart the process of order, many of which operation can by concurrently, Concomitantly or while implement.The order of operations can be rearranged.Processing when its operations are completed to be terminated, It is also possible to have the additional step being not included in accompanying drawing.Process can correspond to method, function, code, subroutine, son Program etc..
Computer equipment includes user equipment and the network equipment.Wherein, user equipment or client include but is not limited to electricity Brain, smart mobile phone, PDA etc.;The network equipment includes but is not limited to single network server, the service of multiple webservers composition Device group or the cloud being made up of a large amount of computers or the webserver based on cloud computing.Computer equipment can isolated operation realizing The present invention, also can access network and by with network in other computer equipments interactive operation realizing the present invention.Calculate Network residing for machine equipment includes but is not limited to the Internet, wide area network, Metropolitan Area Network (MAN), LAN, VPN etc..
May have been used term " first ", " second " etc. here to describe unit, but these units should not When limited by these terms, it is used for the purpose of making a distinction a unit and another unit using these terms.Here institute The term "and/or" for using includes any and all combination of one of them or more listed associated items.When one Unit is referred to as " connection " or during " coupled " to another unit, and it can be connected or coupled to another unit, or There may be temporary location.
Term used herein above is not intended to limit exemplary embodiment just for the sake of description specific embodiment.Unless Context clearly refers else, and singulative " one " otherwise used herein above, " one " also attempt to include plural number.Should also When being understood by, term " including " used herein above and/or "comprising" specify stated feature, integer, step, operation, The presence of unit and/or component, and do not preclude the presence or addition of one or more other features, integer, step, operation, unit, Component and/or its combination.
Below in conjunction with the accompanying drawings the invention will be further described with preferred embodiment.
Embodiment one
As shown in figure 1, a kind of changing method of scene mode disclosed in the present embodiment, including:
S101, the exercise data for obtaining user;
S102, according to the exercise data, obtain the kinestate of active user using Classification and Identification module;
S103, the occurrence number for obtaining each kinestate;
If S104, the continuous occurrence number of same kinestate reach default threshold value, the kinestate institute is switched to right The scene mode answered.
The changing method of the scene mode of the present invention is due to including:Obtain the exercise data of user;According to the motion number According to using the kinestate of Classification and Identification module acquisition active user;Obtain the occurrence number of each kinestate;If same fortune The continuous occurrence number of dynamic state reaches default threshold value, then the scene mode being switched to corresponding to the kinestate.Using this Mode, it is possible to according to the exercise data for obtaining, the kinestate of active user is obtained by Classification and Identification module, and work as same When the number of times that kinestate continuously occurs reaches threshold value, the scene mould corresponding to the kinestate of the continuous appearance is just switched to Formula, so not only can be according to the kinestate of user come handoff scenario pattern and more accurate, only when continuous several times go out Can just switch now, it is to avoid the caused mistake switching because of error, be automatically performed the switching of intelligence wearing motion state of terminal, The accuracy of user exercise data acquisition is improved, while improving Consumer's Experience.
In the present embodiment, for example, currently once, after obtaining the exercise data of user, according to exercise data, Classification and Identification mould It is walking that block obtains the kinestate of current user;Second, after obtaining the exercise data of user, according to exercise data, point Class identification module obtains the kinestate of current user to run;For the third time, after obtaining the exercise data of user, according to motion Data, Classification and Identification module obtains the kinestate of current user to run;4th time, after obtaining the exercise data of user, According to exercise data, Classification and Identification module obtains the kinestate of current user to run;So recorded in this period Running continuously occur in that three times, if default threshold value is three times, then Intelligent worn device can just cut scene mode Running modes are changed to, so as to record the parameters such as velocity, running step number, running heart rate, and by these reference records, are stored Local, it is also possible to as the data foundation for determining whether running state later.And if other kinestates reach threshold value, Also corresponding scene mode can be switched to, such as, if riding condition, switches to ride mode, if swimming state, Stay and be switched to swimming pattern, etc..
According to one of example, the Classification and Identification module includes support vector machine;It is described according to the exercise data The step of kinestate for obtaining active user, specifically includes:
According to the exercise data for obtaining, using support vector machine the kinestate of active user is obtained.
Support vector machine (Support Vector Machine, SVM) are that Corinna Cortes and Vapnik are equal to What nineteen ninety-five proposed first, it shows many distinctive advantages in small sample, the identification of non-linear and high dimensional pattern is solved, and During the other machines problem concerning study such as Function Fitting can be promoted the use of.In machine learning, (SVM is also supported support vector machine Vector network) it is the supervised learning model relevant with related learning algorithm, can be with analytical data, recognition mode, for classifying And regression analyses.In machine learning, support vector machine (SVM goes back support vector network) are relevant with related learning algorithm Supervised learning model, can be with analytical data, recognition mode, for classification and regression analyses.One group of training sample is given, each It is labeled as belonging to two classes, a SVM training algorithm establishes a model, it is a class or other classes to distribute new example so as to Become non-probability binary linearity classification.The example of one SVM model, such as point in space, mapping so that the different class Other example be by obvious gap division as wide as possible expression.New embodiment is then mapped to identical space In, and prediction falls to belonging in the clearance side classification based on them.
Using support vector machine (SVM) as Classification and Identification model, its nonlinear pattern recognition problem in multi-C vector On have very big advantage.The foundation of identification model needs substantial amounts of initial data to be trained it, these data it is preliminary Acquisition is completed when manufacturer internal is tested.Kinestate i (i=0 walkings, 1 runs, and 2 ride, 3 swimming) is for example manually set, and The data such as heart rate under this state, GPS location, movement velocity, acceleration and temperature are gathered as the correspondence under corresponding state Sample Si.Using this four classes sample data as the training data of SVM so as to set up basis supporting vector machine model.
According to other in which example, the support vector machine are specifically included:Ground floor grader, second layer grader, Third layer grader;The step of use support vector machine obtain the kinestate of active user specifically includes:
Obtain the kinestate of active user using ground floor grader, second layer grader, third layer grader successively.
Specifically, wherein, the classification foundation of the ground floor grader at least includes the first motion index, the second layer The classification foundation of grader at least includes the second motion index, and the classification foundation of the third layer grader is at least including the 3rd fortune Dynamic index.
When user is under different kinestates, its own state is discrepant.Such as in walking and running shape Under condition, heart rate, movement velocity are variant;Running and movement velocity under riding condition, the acceleration change of wrist-watch is different; Movement velocity, temperature under running and swimming situation etc. also has difference.Heart rate, GPS location, movement velocity, acceleration and temperature This five classes data is spent as a vector, then the spatial distribution position of the corresponding vector of different motion state is different, and Identical state, its vector space is distributed in the one piece of region more concentrated, different one regions of kinestate correspondence.It is based on These space vectors are carried out classifying and dividing using support vector machine so as to complete one group of sensing data to meeting the tendency of by this point The judgement of dynamic state.Support vector machine are a kind of algorithms of two classification, therefore by the way of multistratum classification, one are selected every time Sensor parameters, can significantly represent the difference between two classifications.
Therefore, classified by means of which, it is possible to more accurately kinestate is classified.So, this In embodiment, the first motion index can be heart rate, can so distinguish walking and run, ride, swimming;Second motion Index can be speed and temperature etc., can so distinguish swimming and ride, run;3rd motion index can be speed With acceleration etc., can so distinguish running and ride;In this manner it is possible to different kinestates are thus distinguished, so as to Obtain final kinestate.
According to other in which example, the step of the scene mode being switched to corresponding to the kinestate described after, Methods described is further included:
Exercise data under Classification and Identification module collection current scene pattern, and the exercise data is stored in into Classification and Identification In module, and the data base in Classification and Identification module is updated.
Thus in parameters such as record velocity, running step number, running hearts rate, and by these reference records, store Local, it is also possible to as the data foundation for determining whether running state later.
In the present embodiment, understand from technical elements in order to more detailed, the typical application scenarios of the embodiment of the present invention are retouched State as follows:
A, user's ambulatory status
B, system monitoring sensing data judges current as ambulatory status
C, user enters running state
D, system monitoring sensing data, it is running state to judge identification by classification
E, when continuous several times are judged as running state, system automatically switches to running function pattern
The handoff scenario of other kinestates is similar with above-mentioned scene.
As shown in Fig. 2 when user is under different kinestates, its own state is discrepant.Such as in step Under row and running situation, heart rate, movement velocity are variant;Running and movement velocity under riding condition, the acceleration of wrist-watch becomes Change is different;Movement velocity, temperature under running and swimming situation etc. also has difference.Heart rate, GPS location, movement velocity, Acceleration and temperature this five classes data are used as a vector, then the spatial distribution position of the corresponding vector of different motion state is Different, and identical state, its vector space is distributed in the one piece of region more concentrated, different kinestates correspondences one Region.Based on this point, using support vector machine these space vectors are carried out with classifying and dividing so as to complete one group of sensor The judgement of data correspondence kinestate.Support vector machine are a kind of algorithms of two classification, therefore by the way of multistratum classification, often One sensor parameters of secondary selection, can significantly represent the difference between two classifications.
As shown in figure 3, the foundation of pattern recognition model and renewal:Using support vector machine (SVM) as Classification and Identification mould Type, it has very big advantage in the nonlinear pattern recognition problem of multi-C vector.The foundation of identification model needs substantial amounts of original Being trained to it, the preliminary acquisition of these data is completed beginning data when manufacturer internal is tested.It is manually set motion shape State i (i=0 walkings, 1 runs, and 2 ride, 3 swimming), and gather heart rate, GPS location, movement velocity, acceleration under this state The data such as degree and temperature are used as the corresponding sample Si under corresponding state.Using this four classes sample data as SVM training data from And set up the supporting vector machine model on basis.
In user's operational phase, when user is under certain motor pattern, system acquisition sensing data, and utilize this A little sample datas are updated to model, so that pattern recognition model is more localized, the kinestate of user of fitting, from And improve its judgment accuracy.
The automatic switching procedure of kinestate:In use, system can sampling sensor at a certain time interval Data, when system continuous several times judge that user kinestate changes according to sensing data, then switch wrist-watch current State enters corresponding kinestate.
As shown in figure 4, according to one of example of the invention, the present embodiment discloses a kind of switched system of scene mode, Including:
Acquisition module 401, for obtaining the exercise data of user;
Classification and Identification module 402, for according to the exercise data, obtaining the kinestate of active user;
Statistical module 403, for obtaining the occurrence number of each kinestate;
Handover module 404, if reaching default threshold value for the continuous occurrence number of same kinestate, is switched to the fortune Scene mode corresponding to dynamic state.
Adopt in this way, it is possible to according to the exercise data for obtaining, obtain active user's by Classification and Identification module Kinestate, and when the number of times that same kinestate continuously occurs reaches threshold value, just switch to the motion shape of the continuous appearance Scene mode corresponding to state, so not only can be according to the kinestate of user come handoff scenario pattern and more accurate, Can just switch only when continuous several times occur, it is to avoid the caused mistake switching because of error, be automatically performed intelligence wearing eventually The switching of end motion state, improves the accuracy of user exercise data acquisition, while improving Consumer's Experience.
In the present embodiment, for example, currently once, after obtaining the exercise data of user, according to exercise data, Classification and Identification mould It is walking that block obtains the kinestate of current user;Second, after obtaining the exercise data of user, according to exercise data, point Class identification module obtains the kinestate of current user to run;For the third time, after obtaining the exercise data of user, according to motion Data, Classification and Identification module obtains the kinestate of current user to run;4th time, after obtaining the exercise data of user, According to exercise data, Classification and Identification module obtains the kinestate of current user to run;So recorded in this period Running continuously occur in that three times, if default threshold value is three times, then Intelligent worn device can just cut scene mode Running modes are changed to, so as to record the parameters such as velocity, running step number, running heart rate, and by these reference records, are stored Local, it is also possible to as the data foundation for determining whether running state later.
According to one of example, the Classification and Identification module includes support vector machine;The Classification and Identification module is concrete For:
According to the exercise data for obtaining, using support vector machine the kinestate of active user is obtained.
Using support vector machine (SVM) as Classification and Identification model, its nonlinear pattern recognition problem in multi-C vector On have very big advantage.The foundation of identification model needs substantial amounts of initial data to be trained it, these data it is preliminary Acquisition is completed when manufacturer internal is tested.Kinestate i (i=0 walkings, 1 runs, and 2 ride, 3 swimming) is for example manually set, and The data such as heart rate under this state, GPS location, movement velocity, acceleration and temperature are gathered as the correspondence under corresponding state Sample Si.Using this four classes sample data as the training data of SVM so as to set up basis supporting vector machine model.
According to other in which example, the support vector machine are specifically included:Ground floor grader, second layer grader, Third layer grader;The Classification and Identification module specifically for:
Obtain the kinestate of active user using ground floor grader, second layer grader, third layer grader successively.
Specifically, wherein, the classification foundation of the ground floor grader at least includes the first motion index, the second layer The classification foundation of grader at least includes the second motion index, and the classification foundation of the third layer grader is at least including the 3rd fortune Dynamic index.
When user is under different kinestates, its own state is discrepant.Such as in walking and running shape Under condition, heart rate, movement velocity are variant;Running and movement velocity under riding condition, the acceleration change of wrist-watch is different; Movement velocity, temperature under running and swimming situation etc. also has difference.Heart rate, GPS location, movement velocity, acceleration and temperature This five classes data is spent as a vector, then the spatial distribution position of the corresponding vector of different motion state is different, and Identical state, its vector space is distributed in the one piece of region more concentrated, different one regions of kinestate correspondence.It is based on These space vectors are carried out classifying and dividing using support vector machine so as to complete one group of sensing data to meeting the tendency of by this point The judgement of dynamic state.Support vector machine are a kind of algorithms of two classification, therefore by the way of multistratum classification, one are selected every time Sensor parameters, can significantly represent the difference between two classifications.
Therefore, classified by means of which, it is possible to more accurately kinestate is classified.So, this In embodiment, the first motion index can be heart rate, can so distinguish walking and run, ride, swimming;Second motion Index can be speed and temperature etc., can so distinguish swimming and ride, run;3rd motion index can be speed With acceleration etc., can so distinguish running and ride;In this manner it is possible to different kinestates are thus distinguished, so as to Obtain final kinestate.
According to other in which example, the system is further included:Update module, works as the collection of Classification and Identification module Exercise data under front scene mode, and the exercise data is stored in Classification and Identification module, and by Classification and Identification module Data base be updated.Thus in record velocity, running step number, the parameter such as running heart rate, and by these parameters Record, is stored in local, it is also possible to as the data foundation for determining whether running state later.
Above content is to combine specific preferred implementation further description made for the present invention, it is impossible to assert The present invention be embodied as be confined to these explanations.For general technical staff of the technical field of the invention, On the premise of without departing from present inventive concept, some simple deduction or replace can also be made, should all be considered as belonging to the present invention's Protection domain.

Claims (10)

1. a kind of changing method of scene mode, it is characterised in that include:
Obtain the exercise data of user;
According to the exercise data, using Classification and Identification module the kinestate of active user is obtained;
Obtain the occurrence number of each kinestate;
If the continuous occurrence number of same kinestate reaches default threshold value, the scene mould being switched to corresponding to the kinestate Formula.
2. changing method according to claim 1, it is characterised in that the Classification and Identification module includes support vector machine; The step of kinestate according to the motion capture active user, specifically includes:
According to the exercise data for obtaining, using support vector machine the kinestate of active user is obtained.
3. changing method according to claim 2, it is characterised in that the support vector machine are specifically included:Ground floor point Class device, second layer grader, third layer grader;The step of use support vector machine obtain the kinestate of active user Specifically include:
Obtain the kinestate of active user using ground floor grader, second layer grader, third layer grader successively.
4. changing method according to claim 3, it is characterised in that wherein, the classification foundation of the ground floor grader At least include the first motion index, the classification foundation of the second layer grader at least includes the second motion index, the described 3rd The classification foundation of layer grader at least includes the 3rd motion index.
5. changing method according to claim 1, it is characterised in that in the field being switched to corresponding to the kinestate After the step of scape pattern, methods described is further included:
Exercise data under Classification and Identification module collection current scene pattern, and the exercise data is stored in into Classification and Identification module In, and the data base in Classification and Identification module is updated.
6. a kind of switched system of scene mode, it is characterised in that include:
Acquisition module, for obtaining the exercise data of user;
Classification and Identification module, for according to the exercise data, obtaining the kinestate of active user;
Statistical module, for obtaining the occurrence number of each kinestate;
Handover module, if reaching default threshold value for the continuous occurrence number of same kinestate, is switched to the kinestate Corresponding scene mode.
7. switched system according to claim 6, it is characterised in that the Classification and Identification module includes support vector machine; The Classification and Identification module specifically for:
According to the exercise data for obtaining, using support vector machine the kinestate of active user is obtained.
8. switched system according to claim 7, it is characterised in that the support vector machine are specifically included:Ground floor point Class device, second layer grader, third layer grader;The Classification and Identification module specifically for:
Obtain the kinestate of active user using ground floor grader, second layer grader, third layer grader successively.
9. switched system according to claim 8, it is characterised in that wherein, the classification foundation of the ground floor grader At least include the first motion index, the classification foundation of the second layer grader at least includes the second motion index, the described 3rd The classification foundation of layer grader at least includes the 3rd motion index.
10. switched system according to claim 6, it is characterised in that the system is further included:Update module, uses The exercise data under current scene pattern is gathered in Classification and Identification module, and the exercise data is stored in into Classification and Identification module In, and the data base in Classification and Identification module is updated.
CN201611019977.3A 2016-11-14 2016-11-14 Scene mode switching method and system Pending CN106598222A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611019977.3A CN106598222A (en) 2016-11-14 2016-11-14 Scene mode switching method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611019977.3A CN106598222A (en) 2016-11-14 2016-11-14 Scene mode switching method and system

Publications (1)

Publication Number Publication Date
CN106598222A true CN106598222A (en) 2017-04-26

Family

ID=58591696

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611019977.3A Pending CN106598222A (en) 2016-11-14 2016-11-14 Scene mode switching method and system

Country Status (1)

Country Link
CN (1) CN106598222A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107888765A (en) * 2017-10-31 2018-04-06 维沃移动通信有限公司 A kind of method of handoff scenario pattern, mobile terminal
CN108514421A (en) * 2018-03-30 2018-09-11 福建幸福家园投资管理有限公司 The method for promoting mixed reality and routine health monitoring
CN109238306A (en) * 2018-08-30 2019-01-18 Oppo广东移动通信有限公司 Step counting data verification method, device, storage medium and terminal based on wearable device
WO2021081768A1 (en) * 2019-10-29 2021-05-06 深圳市欢太科技有限公司 Interface switching method and apparatus, wearable electronic device and storage medium
CN113960911A (en) * 2021-11-02 2022-01-21 珠海读书郎软件科技有限公司 System and method for automatically generating and switching watch dial of sports watch

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101894252A (en) * 2010-03-29 2010-11-24 天津大学 Walking movement classification method based on triaxial acceleration transducer signals
CN102447775A (en) * 2010-10-09 2012-05-09 上海博路信息技术有限公司 Automatic switching method for environment-related mobile phone modes
CN102670207A (en) * 2012-05-15 2012-09-19 北京大学 Gait analysis method based on plantar pressure
CN102772211A (en) * 2012-08-08 2012-11-14 中山大学 Human movement state detection system and detection method
CN104301534A (en) * 2014-10-09 2015-01-21 广东小天才科技有限公司 Method and device for intelligently adjusting scene mode of mobile terminal
CN104323780A (en) * 2014-10-30 2015-02-04 上海交通大学 Support vector machine-based pedestrian gait classifying system and method
CN104490401A (en) * 2015-01-15 2015-04-08 张�杰 Method for intelligent terminal for automatically recognizing human behaviors based on acceleration data
CN104598880A (en) * 2015-03-06 2015-05-06 中山大学 Behavior identification method based on fuzzy support vector machine
CN105511609A (en) * 2015-11-30 2016-04-20 联想(北京)有限公司 Information processing method and electronic equipment

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101894252A (en) * 2010-03-29 2010-11-24 天津大学 Walking movement classification method based on triaxial acceleration transducer signals
CN102447775A (en) * 2010-10-09 2012-05-09 上海博路信息技术有限公司 Automatic switching method for environment-related mobile phone modes
CN102670207A (en) * 2012-05-15 2012-09-19 北京大学 Gait analysis method based on plantar pressure
CN102772211A (en) * 2012-08-08 2012-11-14 中山大学 Human movement state detection system and detection method
CN104301534A (en) * 2014-10-09 2015-01-21 广东小天才科技有限公司 Method and device for intelligently adjusting scene mode of mobile terminal
CN104323780A (en) * 2014-10-30 2015-02-04 上海交通大学 Support vector machine-based pedestrian gait classifying system and method
CN104490401A (en) * 2015-01-15 2015-04-08 张�杰 Method for intelligent terminal for automatically recognizing human behaviors based on acceleration data
CN104598880A (en) * 2015-03-06 2015-05-06 中山大学 Behavior identification method based on fuzzy support vector machine
CN105511609A (en) * 2015-11-30 2016-04-20 联想(北京)有限公司 Information processing method and electronic equipment

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107888765A (en) * 2017-10-31 2018-04-06 维沃移动通信有限公司 A kind of method of handoff scenario pattern, mobile terminal
CN108514421A (en) * 2018-03-30 2018-09-11 福建幸福家园投资管理有限公司 The method for promoting mixed reality and routine health monitoring
CN109238306A (en) * 2018-08-30 2019-01-18 Oppo广东移动通信有限公司 Step counting data verification method, device, storage medium and terminal based on wearable device
WO2021081768A1 (en) * 2019-10-29 2021-05-06 深圳市欢太科技有限公司 Interface switching method and apparatus, wearable electronic device and storage medium
CN113960911A (en) * 2021-11-02 2022-01-21 珠海读书郎软件科技有限公司 System and method for automatically generating and switching watch dial of sports watch
CN113960911B (en) * 2021-11-02 2022-09-20 珠海读书郎软件科技有限公司 System and method for automatically generating and switching watch dial of sports watch

Similar Documents

Publication Publication Date Title
CN106598222A (en) Scene mode switching method and system
CA2924691C (en) User activity tracking system and device
CN103996068B (en) Statistical method and device for passenger flow distribution
CN103026780B (en) For controlling the method and apparatus called of sensor
US20140129560A1 (en) Context labels for data clusters
CN107997767A (en) For identifying the method and its electronic equipment of User Activity
CN108363750B (en) Clothing recommendation method and related products
CN107526429A (en) Wearable device control method, wearable device control device and wearable device
CN109945855A (en) The acquisition of fine grained location data
CN104427547B (en) Business and network associate method of testing, apparatus and system
CN106202427A (en) Application processing method and device
CN109858528A (en) Recommender system training method, device, computer equipment and storage medium
CN112965592A (en) Equipment interaction method, device and system
CN116778411A (en) People flow prediction method and device, electronic equipment and nonvolatile storage medium
CN110276380A (en) A kind of real time kinematics online direction system based on depth model frame
CN106030442B (en) Interactive equipment selection method and device
CN109033995A (en) Identify the method, apparatus and intelligence wearable device of user behavior
CN114223139B (en) Interface switching method and device, wearable electronic equipment and storage medium
CN106994238A (en) Data processing method and the electronic equipment for performing the data processing method
CN107832848A (en) application management method, device, storage medium and electronic equipment
CN106445110A (en) State updating method and apparatus
CN106384014A (en) Artificial intelligent data processing system and method based on motion sensor and GPS positioning
CN105652673A (en) Control method, device and electronic apparatus
CN109640272A (en) A kind of localization method and mobile terminal
CN114491410A (en) Motion mode identification method and system, intelligent wearable device and storage medium

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: 20170426

WD01 Invention patent application deemed withdrawn after publication