CN105807903A - Control method and device of intelligent equipment - Google Patents
Control method and device of intelligent equipment Download PDFInfo
- Publication number
- CN105807903A CN105807903A CN201410849562.3A CN201410849562A CN105807903A CN 105807903 A CN105807903 A CN 105807903A CN 201410849562 A CN201410849562 A CN 201410849562A CN 105807903 A CN105807903 A CN 105807903A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- remote control
- gesture motion
- control unit
- 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
Landscapes
- User Interface Of Digital Computer (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention is suitable for the technical field of control, and provides a control method and device of intelligent equipment. The control method comprises the following steps: collecting the motion data of a remote control device through a sensor, wherein the motion data is generated in a way that a user holds the remote control device by hands to make a gesture action; carrying out characteristic value extraction on the motion data to obtain the characteristic value of the motion data; matching the characteristic value of the motion data with the characteristic value in a preset database, and determining target intelligent equipment to which the gesture motion points; and establishing communication connection between the remote control device and the target intelligent equipment to cause the user to control the target intelligent equipment through the remote control device. The same remote control device is used, the intelligent equipment which needs to be subjected to remote control at present is determined through distinguishing different gesture actions so as to realize the cooperative control of multiple pieces of intelligent equipment, and the cooperative control efficiency of multiple pieces of equipment is greatly improved.
Description
Technical field
The invention belongs to control technical field, particularly relate to control method and the device of a kind of smart machine.
Background technology
The application scenarios of Smart Home may relate to light fixture Based Intelligent Control, security protection Based Intelligent Control, door and window Based Intelligent Control, household instrument Based Intelligent Control and home appliance Based Intelligent Control, etc., above-mentioned application scenarios needs the electrical equipment of multiple different application classifications is controlled.
Among current intelligent home control system, the control to distinct device is that the remote controller each used by each equipment is realized.Along with the degree of home intelligence is more and more higher, the required remote controller used also gets more and more, every equipment all requires over a remote controller and operates, what thus cause is in the control process of Smart Home, need the difference according to controlling equipment to be replaced as frequently as remote controller, reduce control efficiency.
Summary of the invention
The purpose of the embodiment of the present invention is in that to provide control method and the device of a kind of smart machine, it is intended to solve the problem that in the process at present many equipment being controlled, control efficiency is low.
The embodiment of the present invention is achieved in that the control method of a kind of smart machine, including:
S1, gather remote control unit exercise data, described exercise data is made gesture motion by the hand-held described remote control unit of user and is produced；
S2, described exercise data is carried out characteristics extraction, obtain the eigenvalue of described exercise data；
S3, the eigenvalue of described exercise data is mated with the eigenvalue in presetting database, it is determined that the Intelligent target equipment pointed by described gesture motion；
S4, set up the communication connection of described remote control unit and described Intelligent target equipment, so that user controls described Intelligent target equipment by described remote control unit.
The another object of the embodiment of the present invention is in that to provide the control device of a kind of smart machine, including:
First collecting unit, for gathering the exercise data of remote control unit, described exercise data is made gesture motion by the hand-held described remote control unit of user and is produced；
Extraction unit, for described exercise data is carried out characteristics extraction, obtains the eigenvalue of described exercise data；
Matching unit, for mating the eigenvalue of described exercise data with the eigenvalue in presetting database, it is determined that the Intelligent target equipment pointed by described gesture motion；
Control unit, for setting up the communication connection of described remote control unit and described Intelligent target equipment, so that user controls described Intelligent target equipment by described remote control unit.
The embodiment of the present invention utilizes same remote control unit, the smart machine being currently needed for remote control by distinguishing different gesture motion to determine, thus realizing the Collaborative Control to multiple stage smart machine, greatly increases the Collaborative Control efficiency of many equipment.
Accompanying drawing explanation
Fig. 1 is the flowchart of the control method of the smart machine that the embodiment of the present invention provides；
Fig. 2 is the flowchart of the control method of the smart machine that another embodiment of the present invention provides；
Fig. 3 be the embodiment of the present invention provide smart machine control method S106 implement flow chart；
Fig. 4 be the embodiment of the present invention provide smart machine control method S103 implement flow chart；
Fig. 5 is the presetting database schematic diagram that this embodiment provides；
Fig. 6 be the embodiment of the present invention provide smart machine control device structured flowchart.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein is only in order to explain the present invention, is not intended to limit the present invention.
What Fig. 1 illustrated the control method of the smart machine that the embodiment of the present invention provides realizes flow process, and details are as follows:
In S101, by the exercise data of sensor acquisition remote control unit, described exercise data is made gesture motion by the hand-held described remote control unit of user and is produced.
Described remote control unit, may be located among the terminal units such as remote controller, mobile phone, flat board, it is by WiFi, infrared, bluetooth or other short-distance wireless communication modes, communication connection can be set up with the multiple devices in the same area space, exercise data is sent, to realize the control to these equipment to these equipment.Such as, control all electrical equipments in intelligent domestic system, including intelligent television, intelligent refrigerator, intelligent washing machine, etc..
Described sensor, includes but not limited to be integrated among remote control unit, or is integrated in the acceleration transducer among the terminal unit of remote control unit place, gyroscope, geomagnetic sensor and temperature sensor, etc..
The hand-held terminal unit being integrated with remote control unit of user makes gesture motion, to send the selection instruction to smart machine, it is controlled for selecting one in multiple stage smart machine, in this process, remote control unit and sensor are in kinestate, and when user is performed gesture motion by sensor, exercise data produced by remote control unit is acquired.
In S102, described exercise data is carried out characteristics extraction, obtain the eigenvalue of described exercise data.
Exercise data is carried out characteristics extraction, main extracts exercise data energy on X-axis, Y-axis and three directions of Z axis, dominant frequency, dominant frequency size, average, variance and at relative coefficient between coordinate axes between two.Features described above value extracting method is as follows:
(1) energy: can calculate exercise data energy in X-axis, Y-axis and Z-direction respectively, the computing formula of energy isIt should be noted that when calculating exercise data energy on Z axis, it is necessary to deduct energy produced by gravity (being approximately 9.8 joules).
(2) dominant frequency (Dominantfrequency) and size (magnitude) thereof:
Wherein, dominant frequency is for carry out fast Fourier transform (FastFourierTransform, FFT), the coordinate on coordinate axes of the maximum in its FFT result to exercise data, and this maximum is then the size of dominant frequency.
(3) average: the computing formula of average is
(4) variance: the computing formula of variance is
The extracting method of features described above value (1) to (4) is all for the extracting method in X-axis, wherein, N is total number of exercise data, x (n) represents the data corresponding in X-axis at nth strong point, Y-axis and on Z axis, the extracting method of eigenvalue can be by that analogy.
(5) relative coefficient: include exercise data relative coefficient in X-axis and Y-axis, the relative coefficient in Y-axis and Z axis, and the relative coefficient in X-axis and Z axis.The computing formula of exercise data relative coefficient in X-axis and Y-axis is
The extracting method of features described above value (5) is for the extracting method of X-axis and the relative coefficient of Y-axis, wherein, N is total number of exercise data, x (n) represents the data corresponding in X-axis at nth strong point, relative coefficient in Y-axis and Z axis, and the extracting method of the relative coefficient on X-axis and Z axis can be by that analogy.
Table 1 illustrates the different characteristic value of storage in presetting database and the numbering of correspondence thereof.
Table 1
| Numbering | Implication |
| 0 | Average in X-axis |
| 1 | Average in Y-axis |
| 2 | Average on Z axis |
| 3 | Variance in X-axis |
| 4 | Variance in Y-axis |
| 5 | Variance on Z axis |
| 6 | X, the relative coefficient between Y-axis |
| 7 | Y, the relative coefficient between Z axis |
| 8 | Z, the relative coefficient between X-axis |
| 9 | Energy in X-axis |
| 10 | Energy in Y-axis |
| 11 | Energy on Z axis |
| 12 | Dominant frequency in X-axis |
| 13 | Dominant frequency in Y-axis |
| 14 | Dominant frequency on Z axis |
| 15 | Dominant frequency size in X-axis |
| 16 | Dominant frequency size in Y-axis |
| 17 | Dominant frequency size on Z axis |
In S103, the eigenvalue of described exercise data is mated with the eigenvalue in presetting database, it is determined that the Intelligent target equipment pointed by described gesture motion.
In the present embodiment, described presetting database has stored exercise data characteristic of correspondence value produced by various gesture motion, store different smart machine associated by gesture motion simultaneously, by the eigenvalue calculated in S102 is mated with the eigenvalue in presetting database, can interpolate that out this exercise data by which kind of gesture motion is produced, and judge the smart machine pointed by this gesture motion further.
Such as, the association of rectangle gesture motion is intelligent television, if match in presetting database this action data corresponding be rectangle gesture motion, then what can determine that this gesture motion points to is intelligent television；In like manner, it is possible to the oval gesture motion association intelligent refrigerator of definition, triangle gesture action association intelligent washing machine in presetting database.
If through S103, exercise data is not carried out successful match, then illustrate not define this gesture motion in presetting database, it is clear that also just cannot inquire about and obtain corresponding Intelligent target equipment, now, return the result that it fails to match.
In S104, set up the communication connection of described remote control unit and described Intelligent target equipment, control described Intelligent target equipment by described remote control unit.
Once it is determined that corresponding Intelligent target equipment, then set up the communication connection of remote control unit and this Intelligent target equipment, now, the control instruction sent by beepbox only can mail to this Intelligent target equipment, realizes, with this, the purpose that one smart machine of appointment is controlled in multiple stage smart machine.When needs control another smart machine, it is only necessary to again make the gesture motion being associated with another smart machine, it is possible to realize the control to another smart machine by same remote control unit.
Pass through said method, it is possible to use same remote control unit, the smart machine being currently needed for remote control by distinguishing different gesture motion to determine, thus realizing the Collaborative Control to multiple stage smart machine, greatly increase the Collaborative Control efficiency of many equipment.
As one embodiment of the present of invention, it can also be each a set of gesture motion of user's special setting, such as, user A performs rectangle gesture motion, corresponding Intelligent target equipment is intelligent television, and user B performs rectangle gesture motion, corresponding Intelligent target equipment is intelligent refrigerator, this needs before identifying gesture motion, first pass through the gesture motion data of user's handheld remote control device to judge the identity of user, then the gesture motion that user performs is put into and carried out gesture coupling in the data base that this user is corresponding.As in figure 2 it is shown, before S101, described method also includes:
In S105, gather the gesture motion data of the hand-held described remote control unit of user.
In S106, based on described gesture motion data and described presetting database, identify the identity of user.
In the present embodiment, presetting database also stored for the relation table of user identity characteristic of correspondence Value Data, by different user action difference in handheld remote control device process, or, further, by different user action difference in picking up remote control unit process, relation table according to user identity characteristic of correspondence Value Data judges the user identity of the user of gesture remote control device, then completes user's control to smart machine further according to the mapping table between the gesture of user and smart machine.Specifically, as it is shown on figure 3, S106 comprises the following steps:
In S301, calculate eigenvalue and the similarity of the eigenvalue of each user identity class of storage in described presetting database of described exercise data respectively.
In S302, determine, according to result of calculation, the user identity class that described similarity is the highest.
User identity in S303, according to the user of the highest described hand-held described remote control unit of user identity class identification of described similarity.
In the present embodiment, pass through cluster analysis, presetting database also stores in advance different user identity class characteristic of correspondence values, described user identity class, can divide according to the ages of user, such as, child, young, old, etc., each user identity class suffers from characteristic of correspondence value, such as, user picks up in remote control unit process, difference due to the age, rising and falling of remote control unit highly has difference, or the speed of rising and falling of remote control unit also has difference, in the present embodiment, utilize Bayes classifier to calculate eigenvalue and the similarity of the eigenvalue of the user identity class of storage in presetting database of these componental movement data.The principle of classification of Bayes classifier is the prior probability by certain object, utilizes Bayesian formula to calculate its posterior probability, and namely this object belongs to the probability of a certain class, selects the class with maximum a posteriori probability as the class belonging to this object.In theory, Bayes classifier be a conditional probability model p (C | F1,...,Fn), there is some independent class variable C, condition depends on some characteristic variables, passes through formula The eigenvalue picking up the user identity class set up in eigenvalue and the presetting database of the exercise data produced in remote control unit process according to active user can be compared by system, maximum by what calculate, the user identity class corresponding to result that namely similarity is the highest extracts, with further reversal of identification current handheld remote control unit is who member in the middle of family, thus reaching to identify the purpose of user identity.Such as, the user identity class that in matching result, similarity is the highest is child, then obviously, the now child being particularly likely that in family of handheld remote control device.
By embodiment illustrated in fig. 3, with age bracket, user identity divided, cluster, it is possible to efficiently differentiate out kinsfolk, facilitate the self-defined gesture motion of each kinsfolk, according to self being accustomed to the control to smart machine.
It should be noted that, in presetting database, to the storage of the eigenvalue of user identity class with to improve be carry out user behavior solidifying the process with abstract, by modeling, concrete user behavior feature is changed into data structure one by one, and in subsequent use process, by data model is constantly solidified and maintenance, this data model can be more and more perfect, then also can be more and more accurate to the recognition result of user identity.
As one embodiment of the present of invention, before S105, in order to ensure the correctness of the aspect ratio pair of gesture motion data, it is necessary to first gesture motion data are carried out pretreatment, the preprocessing process of gesture motion data is included successively:
(1) denoising, removes the noise datas such as shake.Denoising process is:
Being primarily based on is Qwest's sampling thheorem, and the gesture motion data collected are carried out signal sampling.Described is Qwest's sampling thheorem, and namely when 2 times of highest frequency during sample frequency is more than signal, the digital signal that sampling obtains intactly remains the information in primary signal.Therefore, in the present embodiment, the signal in order to ensure sampling is undistorted, it is possible to 4～5 times of the number of winning the confidence upper frequency limit as sample frequency.After signal sampling completes, by there being limit for length unit impulse response (FiniteImpulseResponse, FIR) digital signal that sampling is obtained by wave filter processes, and wherein vibrating, bigger data filtering falls, more true to ensure the gesture motion data obtained.
(2) data filtering, filters out the data not meeting characteristics extraction requirement in gesture motion data, including the data of: incomplete data, the data of mistake and repetition.
(3) gesture motion data are logically carried out integrated by data integration, for instance, according to gathering the sensor of data, by same type or to have the gesture motion data of similar feature logically integrated for the mode such as form that gathers of data.
(4) the gesture motion data after integrated are carried out stipulations according to preset rules by hough transformation, enable the data after stipulations to present in the way of set, while presenting with aggregate manner, also remain the integrity of initial data.
After completing the pretreatment to gesture motion data, it is necessary to these part gesture motion data are carried out data segmentation, meaningless or not representative data waveform is split away from complete action waveforms.Specifically, described described gesture motion data are carried out pretreatment after, described method also includes:
The gesture motion data that pretreatment obtains are removed user and picks up the exercise data produced in described remote control unit process.
That is, user is before hand-held remote controller makes gesture motion, is actually also made that the action picking up remote controller, then need this partial act waveform partition to go out.The handling process of data segmentation is as follows:
The exercise data that pretreatment is obtained carries out the conversion of time-domain and frequency-domain respectively, the time-domain signal and the frequency-region signal that respectively conversion are obtained are analyzed again, and it is partitioned into corresponding action waveforms according to analyzing result, user picks up the action of remote controller, the change of time-domain signal is from static to vibration, the change of frequency-region signal is that this is according to this Variation Features, and the exercise data produced when user is picked up remote controller is split away to frequently by sparse.
As one embodiment of the present of invention, presetting database stores the mapping table between user identity, the relation table of user identity characteristic of correspondence Value Data and gesture and the smart machine of user, after determining user identity, as shown in Figure 4, S103 particularly as follows:
In S401, described presetting database extracts described user identity characteristic of correspondence Value Data.
In S402, the eigenvalue of described exercise data is mated with described user identity characteristic of correspondence Value Data, it is determined that the Intelligent target equipment pointed by described gesture motion.
As shown in Figure 5, in presetting database, define different user identity, the eigenvalue of gesture motion to different intelligent equipment is stored respectively under each user identity, after determining user identity, extracting this user identity characteristic of correspondence Value Data to mate, the made gesture motion of user to determine current handheld remote control unit is desirable to for controlling which smart machine.
The embodiment of the present invention can be used among each application scenarios that many smart machines control under background, gesture motion is carried out by hand-held same remote control unit, sensor acquisition on remote control unit is to the exercise data of this gesture motion, and Intelligent Recognition to go out this exercise data be the defined control instruction for pointing to certain concrete smart machine of certain user, thus going to control this smart machine to the operational order of remote control unit according to this user further, reach the Collaborative Control of many smart machines.Among Smart Home application scenarios, different kinsfolks can use the gesture motion oneself defined to control all of smart machine in family, change multiple remote controller to control the present situation of multiple smart machine, realize the personalized control to smart machine, improve the Collaborative Control efficiency of many equipment.
Fig. 6 illustrates the structured flowchart controlling device of the smart machine that the embodiment of the present invention provides, and this device may be located in the remote control unit being integrated in terminal unit, for running the control method of smart machine mentioned above.For the ease of illustrating, illustrate only part related to the present embodiment.
With reference to Fig. 6, this device includes:
First collecting unit 61, by the exercise data of sensor acquisition remote control unit, described exercise data is made gesture motion by the hand-held described remote control unit of user and is produced.
Described remote control unit, may be located among the terminal units such as remote controller, mobile phone, flat board, it is by WiFi, infrared, bluetooth or other short-distance wireless communication modes, communication connection can be set up with the multiple devices in the same area space, exercise data is sent, to realize the control to these equipment to these equipment.Such as, control all electrical equipments in intelligent domestic system, including intelligent television, intelligent refrigerator, intelligent washing machine, etc..
Described sensor, includes but not limited to be integrated among remote control unit, or is integrated in the acceleration transducer among the terminal unit of remote control unit place, gyroscope, geomagnetic sensor and temperature sensor, etc..
The hand-held terminal unit being integrated with remote control unit of user makes gesture motion, to send the selection instruction to smart machine, it is controlled for selecting one in multiple stage smart machine, in this process, remote control unit and sensor are in kinestate, and when user is performed gesture motion by sensor, exercise data produced by remote control unit is acquired.
Extraction unit 62, carries out characteristics extraction to described exercise data, obtains the eigenvalue of described exercise data.
Exercise data is carried out characteristics extraction, main extracts exercise data energy on X-axis, Y-axis and three directions of Z axis, dominant frequency, dominant frequency size, average, variance and at relative coefficient between coordinate axes between two.Features described above value extracting method is as follows:
(1) energy: can calculate exercise data energy in X-axis, Y-axis and Z-direction respectively, the computing formula of energy isIt should be noted that when calculating exercise data energy on Z axis, it is necessary to deduct energy produced by gravity (being approximately 9.8 joules).
(2) dominant frequency (Dominantfrequency) and size (magnitude) thereof:
Wherein, dominant frequency is for carry out fast Fourier transform (FastFourierTransform, FFT), the coordinate on coordinate axes of the maximum in its FFT result to exercise data, and this maximum is then the size of dominant frequency.
(3) average: the computing formula of average is
(4) variance: the computing formula of variance is
The extracting method of features described above value (1) to (4) is all for the extracting method in X-axis, wherein, N is total number of exercise data, x (n) represents the data corresponding in X-axis at nth strong point, Y-axis and on Z axis, the extracting method of eigenvalue can be by that analogy.
(5) relative coefficient: include exercise data relative coefficient in X-axis and Y-axis, the relative coefficient in Y-axis and Z axis, and the relative coefficient in X-axis and Z axis.The computing formula of exercise data relative coefficient in X-axis and Y-axis is
The extracting method of features described above value (5) is for the extracting method of X-axis and the relative coefficient of Y-axis, wherein, N is total number of exercise data, x (n) represents the data corresponding in X-axis at nth strong point, relative coefficient in Y-axis and Z axis, and the extracting method of the relative coefficient on X-axis and Z axis can be by that analogy.
Matching unit 63, mates the eigenvalue of described exercise data with the eigenvalue in presetting database, it is determined that the Intelligent target equipment pointed by described gesture motion.
In the present embodiment, described presetting database has stored exercise data characteristic of correspondence value produced by various gesture motion, store different smart machine associated by gesture motion simultaneously, by the eigenvalue calculated in extraction unit 62 is mated with the eigenvalue in presetting database, can interpolate that out this exercise data by which kind of gesture motion is produced, and judge the smart machine pointed by this gesture motion further.
Such as, the association of rectangle gesture motion is intelligent television, if match in presetting database this action data corresponding be rectangle gesture motion, then what can determine that this gesture motion points to is intelligent television；In like manner, it is possible to the oval gesture motion association intelligent refrigerator of definition, triangle gesture action association intelligent washing machine in presetting database.
Control unit 64, sets up the communication connection of described remote control unit and described Intelligent target equipment, so that user controls described Intelligent target equipment by described remote control unit.
Once it is determined that corresponding Intelligent target equipment, then set up the communication connection of remote control unit and this Intelligent target equipment, now, the control instruction sent by beepbox only can mail to this Intelligent target equipment, realizes, with this, the purpose that one smart machine of appointment is controlled in multiple stage smart machine.When needs control another smart machine, it is only necessary to again make the gesture motion being associated with another smart machine, it is possible to realize the control to another smart machine by same remote control unit.
Alternatively, it can also be each a set of gesture motion of user's special setting, such as, user A performs rectangle gesture motion, and corresponding Intelligent target equipment is intelligent television, and user B performs rectangle gesture motion, corresponding Intelligent target equipment is intelligent refrigerator, this needs, identifying before gesture motion, to first pass through the gesture motion data of user's handheld remote control device to judge the identity of user, then the gesture motion that user performs is put into and carry out gesture coupling in the data base that this user is corresponding.Then described device also includes:
Second collecting unit, gathers the gesture motion data of the hand-held described remote control unit of user.
Identity recognizing unit, based on described gesture motion data and described presetting database, identifies the identity of user.
Alternatively, described device also includes:
Described gesture motion data are carried out pretreatment by pretreatment unit, and described pretreatment includes successively: data de-noising, data filtering, data integration and hough transformation.
Wherein, pretreatment includes:
(1) denoising, removes the noise datas such as shake.Denoising process is:
Being primarily based on is Qwest's sampling thheorem, and the gesture motion data collected are carried out signal sampling.Described is Qwest's sampling thheorem, and namely when 2 times of highest frequency during sample frequency is more than signal, the digital signal that sampling obtains intactly remains the information in primary signal.Therefore, in the present embodiment, the signal in order to ensure sampling is undistorted, it is possible to 4～5 times of the number of winning the confidence upper frequency limit as sample frequency.After signal sampling completes, by there being limit for length unit impulse response (FiniteImpulseResponse, FIR) digital signal that sampling is obtained by wave filter processes, and wherein vibrating, bigger data filtering falls, more true to ensure the gesture motion data obtained.
(2) data filtering, filters out the data not meeting characteristics extraction requirement in gesture motion data, including the data of: incomplete data, the data of mistake and repetition.
(3) gesture motion data are logically carried out integrated by data integration, for instance, according to gathering the sensor of data, by same type or to have the gesture motion data of similar feature logically integrated for the mode such as form that gathers of data.
(4) the gesture motion data after integrated are carried out stipulations according to preset rules by hough transformation, enable the data after stipulations to present in the way of set, while presenting with aggregate manner, also remain the integrity of initial data.
Removal unit, removes user in the gesture motion data that pretreatment obtains and picks up the exercise data produced in described remote control unit process.
That is, user is before hand-held remote controller makes gesture motion, is actually also made that the action picking up remote controller, then need this partial act waveform partition to go out.The handling process of data segmentation is as follows:
The exercise data that pretreatment is obtained carries out the conversion of time-domain and frequency-domain respectively, the time-domain signal and the frequency-region signal that respectively conversion are obtained are analyzed again, and it is partitioned into corresponding action waveforms according to analyzing result, user picks up the action of remote controller, the change of time-domain signal is from static to vibration, the change of frequency-region signal is that this is according to this Variation Features, and the exercise data produced when user is picked up remote controller is split away to frequently by sparse.
Alternatively, described eigenvalue include following at least one:
Described exercise data energy on X-axis, Y-axis and three directions of Z axis, dominant frequency, dominant frequency size, average, variance and at relative coefficient between coordinate axes between two.
Alternatively, described presetting database includes the mapping table between user identity, the relation table of user identity characteristic of correspondence Value Data and gesture and the smart machine of user, and described matching unit 53 includes:
Extract subelement, described presetting database extracts described user identity characteristic of correspondence Value Data.
Coupling subelement, mates the eigenvalue of described exercise data with described user identity characteristic of correspondence Value Data, it is determined that the Intelligent target equipment pointed by described gesture motion.
Alternatively, described identity recognizing unit includes:
Computation subunit, calculates eigenvalue and the similarity of the eigenvalue of each user identity class of storage in described presetting database of described gesture motion data respectively；
Determine subelement, determine, according to result of calculation, the user identity class that described similarity is the highest；
Identify subelement, the user identity according to the user of the highest described hand-held described remote control unit of user identity class identification of described similarity.
In the present embodiment, pass through cluster analysis, presetting database also stores in advance different user identity class characteristic of correspondence values, described user identity class, can divide according to the ages of user, such as, child, young, old, etc., each user identity class suffers from characteristic of correspondence value, such as, user picks up in remote control unit process, difference due to the age, rising and falling of remote control unit highly has difference, or the speed of rising and falling of remote control unit also has difference, in the present embodiment, utilize Bayes classifier to calculate eigenvalue and the similarity of the eigenvalue of the user identity class of storage in presetting database of these componental movement data.The principle of classification of Bayes classifier is the prior probability by certain object, utilizes Bayesian formula to calculate its posterior probability, and namely this object belongs to the probability of a certain class, selects the class with maximum a posteriori probability as the class belonging to this object.In theory, Bayes classifier be a conditional probability model p (C | F1,...,Fn), there is some independent class variable C, condition depends on some characteristic variables, passes through formula The eigenvalue picking up the user identity class set up in eigenvalue and the presetting database of the exercise data produced in remote control unit process according to active user can be compared by system, maximum by what calculate, the user identity class corresponding to result that namely similarity is the highest extracts, with further reversal of identification current handheld remote control unit is who member in the middle of family, thus reaching to identify the purpose of user identity.Such as, the user identity class that in matching result, similarity is the highest is child, then obviously, the now child being particularly likely that in family of handheld remote control device.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all any amendment, equivalent replacement and improvement etc. made within the spirit and principles in the present invention, should be included within protection scope of the present invention.
Claims (11)
1. the control method of a smart machine, it is characterised in that including:
S1, gather remote control unit exercise data, described exercise data is made gesture motion by the hand-held described remote control unit of user and is produced；
S2, described exercise data is carried out characteristics extraction, obtain the eigenvalue of described exercise data；
S3, the eigenvalue of described exercise data is mated with the eigenvalue in presetting database, it is determined that the Intelligent target equipment pointed by described gesture motion；
S4, set up the communication connection of described remote control unit and described Intelligent target equipment, so that user controls described Intelligent target equipment by described remote control unit.
2. the method for claim 1, it is characterised in that further comprise the steps of: before described S1
A1, gather the hand-held described remote control unit of user gesture motion data；
A2, based on described gesture motion data and described presetting database, identify the identity of user.
3. method as claimed in claim 2, it is characterised in that after described step A1, include before A2:
B1, described gesture motion data being carried out pretreatment, described pretreatment includes successively: data de-noising, data filtering, data integration and hough transformation；
B2, in the gesture motion data that pretreatment obtains remove user pick up in described remote control unit process produce exercise data.
4. the method for claim 1, it is characterised in that described eigenvalue include following at least one:
Described exercise data energy on X-axis, Y-axis and three directions of Z axis, dominant frequency, dominant frequency size, average, variance and at relative coefficient between coordinate axes between two.
5. method as claimed in claim 2 or claim 3, it is characterised in that described presetting database includes the mapping table between user identity, the relation table of user identity characteristic of correspondence Value Data and gesture and the smart machine of user, and described step S3 specifically includes:
S31, in described presetting database, extract described user identity characteristic of correspondence Value Data；
S32, the eigenvalue of described exercise data is mated with described user identity characteristic of correspondence Value Data, it is determined that the Intelligent target equipment pointed by described gesture motion.
6. method as claimed in claim 2, it is characterised in that described step A2 specifically includes:
A21, the eigenvalue calculating described gesture motion data respectively and the similarity of the eigenvalue of each user identity class of storage in described presetting database；
A22, determine, according to result of calculation, the user identity class that described similarity is the highest；
A23, user identity according to the user of the highest described hand-held described remote control unit of user identity class identification of described similarity.
7. the control device of a smart machine, it is characterised in that including:
First collecting unit, for gathering the exercise data of remote control unit, described exercise data is made gesture motion by the hand-held described remote control unit of user and is produced；
Extraction unit, for described exercise data is carried out characteristics extraction, obtains the eigenvalue of described exercise data；
Matching unit, for mating the eigenvalue of described exercise data with the eigenvalue in presetting database, it is determined that the Intelligent target equipment pointed by described gesture motion；
Control unit, for setting up the communication connection of described remote control unit and described Intelligent target equipment, so that user controls described Intelligent target equipment by described remote control unit.
8. device as claimed in claim 7, it is characterised in that described device also includes:
Second collecting unit, for gathering the gesture motion data of the hand-held described remote control unit of user；
Identity recognizing unit, for based on described gesture motion data and described presetting database, identifying the identity of user.
9. device as claimed in claim 8, it is characterised in that described device also includes:
Pretreatment unit, for described gesture motion data are carried out pretreatment, described pretreatment includes successively: data de-noising, data filtering, data integration and hough transformation；
Removal unit, picks up, for removing user in the gesture motion data that pretreatment obtains, the exercise data produced in described remote control unit process.
10. device as claimed in claim 8 or 9, it is characterised in that described presetting database includes the mapping table between user identity, the relation table of user identity characteristic of correspondence Value Data and gesture and the smart machine of user, and described matching unit includes:
Extract subelement, for extracting described user identity characteristic of correspondence Value Data in described presetting database；
Coupling subelement, for mating the eigenvalue of described exercise data with described user identity characteristic of correspondence Value Data, it is determined that the Intelligent target equipment pointed by described gesture motion.
11. device as claimed in claim 8, it is characterised in that described identity recognizing unit includes:
Computation subunit, for calculating eigenvalue and the similarity of the eigenvalue of each user identity class of storage in described presetting database of described gesture motion data respectively；
Determine subelement, for determining, according to result of calculation, the user identity class that described similarity is the highest；
Identify subelement, for the user identity of the user of the described user identity class identification hand-held described remote control unit the highest according to described similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410849562.3A CN105807903A (en) | 2014-12-30 | 2014-12-30 | Control method and device of intelligent equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410849562.3A CN105807903A (en) | 2014-12-30 | 2014-12-30 | Control method and device of intelligent equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105807903A true CN105807903A (en) | 2016-07-27 |
Family
ID=56421033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410849562.3A Pending CN105807903A (en) | 2014-12-30 | 2014-12-30 | Control method and device of intelligent equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105807903A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106648094A (en) * | 2016-12-20 | 2017-05-10 | 同方计算机有限公司 | Mobile-device identity and position identifying system and method |
| CN106647398A (en) * | 2016-12-23 | 2017-05-10 | 广东美的制冷设备有限公司 | Remote controller, operation control method and device |
| CN107678287A (en) * | 2017-09-18 | 2018-02-09 | 广东美的制冷设备有限公司 | Apparatus control method, device and computer-readable recording medium |
| WO2018082006A1 (en) * | 2016-11-04 | 2018-05-11 | 深圳市奥星澳科技有限公司 | Control method, control apparatus, and control system |
| CN108510984A (en) * | 2017-02-24 | 2018-09-07 | 九阳股份有限公司 | A kind of voice cooperative control method of intelligent appliance equipment |
| CN110230865A (en) * | 2019-06-06 | 2019-09-13 | 河南科技大学 | It is a kind of that the personnel of BN are merged in room state identification method based on information |
| CN110941187A (en) * | 2018-09-21 | 2020-03-31 | 珠海格力电器股份有限公司 | Household appliance control method and device |
| CN113038449A (en) * | 2021-02-01 | 2021-06-25 | 深圳创维－Rgb电子有限公司 | Device pairing method, device, storage medium and device |
| CN113031775A (en) * | 2021-03-24 | 2021-06-25 | Oppo广东移动通信有限公司 | Gesture data acquisition method and device, terminal and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101777250A (en) * | 2010-01-25 | 2010-07-14 | 中国科学技术大学 | General remote control device and method for household appliances |
| CN102184014A (en) * | 2011-05-12 | 2011-09-14 | 浙江大学 | Intelligent appliance interaction control method and device based on mobile equipment orientation |
| CN103248933A (en) * | 2013-04-03 | 2013-08-14 | 深圳Tcl新技术有限公司 | Interactive method and remote control device based on user identity for interaction |
| CN103809735A (en) * | 2012-11-12 | 2014-05-21 | 腾讯科技（深圳）有限公司 | Gesture recognition method and gesture recognition device |
| CN103890696A (en) * | 2011-10-12 | 2014-06-25 | 高通股份有限公司 | Authenticated gesture recognition |
| CN104102183A (en) * | 2013-04-13 | 2014-10-15 | 王斌 | Intelligent household gesture control method and apparatus |
-
2014
- 2014-12-30 CN CN201410849562.3A patent/CN105807903A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101777250A (en) * | 2010-01-25 | 2010-07-14 | 中国科学技术大学 | General remote control device and method for household appliances |
| CN102184014A (en) * | 2011-05-12 | 2011-09-14 | 浙江大学 | Intelligent appliance interaction control method and device based on mobile equipment orientation |
| CN103890696A (en) * | 2011-10-12 | 2014-06-25 | 高通股份有限公司 | Authenticated gesture recognition |
| CN103809735A (en) * | 2012-11-12 | 2014-05-21 | 腾讯科技（深圳）有限公司 | Gesture recognition method and gesture recognition device |
| CN103248933A (en) * | 2013-04-03 | 2013-08-14 | 深圳Tcl新技术有限公司 | Interactive method and remote control device based on user identity for interaction |
| CN104102183A (en) * | 2013-04-13 | 2014-10-15 | 王斌 | Intelligent household gesture control method and apparatus |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018082006A1 (en) * | 2016-11-04 | 2018-05-11 | 深圳市奥星澳科技有限公司 | Control method, control apparatus, and control system |
| CN106648094B (en) * | 2016-12-20 | 2019-10-01 | 同方计算机有限公司 | A kind of mobile equipment identity and position-recognizing system and method |
| CN106648094A (en) * | 2016-12-20 | 2017-05-10 | 同方计算机有限公司 | Mobile-device identity and position identifying system and method |
| CN106647398A (en) * | 2016-12-23 | 2017-05-10 | 广东美的制冷设备有限公司 | Remote controller, operation control method and device |
| CN108510984B (en) * | 2017-02-24 | 2020-10-27 | 九阳股份有限公司 | Voice cooperative control method of intelligent household electrical appliance |
| CN108510984A (en) * | 2017-02-24 | 2018-09-07 | 九阳股份有限公司 | A kind of voice cooperative control method of intelligent appliance equipment |
| WO2019051898A1 (en) * | 2017-09-18 | 2019-03-21 | 广东美的制冷设备有限公司 | Device control method and apparatus, and computer readable storage medium |
| CN107678287A (en) * | 2017-09-18 | 2018-02-09 | 广东美的制冷设备有限公司 | Apparatus control method, device and computer-readable recording medium |
| CN110941187A (en) * | 2018-09-21 | 2020-03-31 | 珠海格力电器股份有限公司 | Household appliance control method and device |
| CN110230865A (en) * | 2019-06-06 | 2019-09-13 | 河南科技大学 | It is a kind of that the personnel of BN are merged in room state identification method based on information |
| CN113038449A (en) * | 2021-02-01 | 2021-06-25 | 深圳创维－Rgb电子有限公司 | Device pairing method, device, storage medium and device |
| CN113038449B (en) * | 2021-02-01 | 2022-11-25 | 深圳创维－Rgb电子有限公司 | Device pairing method, device, storage medium and device |
| CN113031775A (en) * | 2021-03-24 | 2021-06-25 | Oppo广东移动通信有限公司 | Gesture data acquisition method and device, terminal and storage medium |
| WO2022199312A1 (en) * | 2021-03-24 | 2022-09-29 | Oppo广东移动通信有限公司 | Gesture data acquisition method and apparatus, terminal, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105807903A (en) | Control method and device of intelligent equipment | |
| Gu et al. | Paws: Passive human activity recognition based on wifi ambient signals | |
| AU2016200905B2 (en) | A system and method for identifying and analyzing personal context of a user | |
| US10061389B2 (en) | Gesture recognition system and gesture recognition method | |
| CN103529762B (en) | A kind of intelligent home furnishing control method based on sensor technology and system | |
| CN108924736B (en) | PCA-Kalman-based passive indoor personnel state detection method | |
| CN103546789B (en) | A kind of TV programme suggesting method, system and intelligent terminal | |
| CN110288978A (en) | A kind of speech recognition modeling training method and device | |
| CN104780217B (en) | Detect method, system and the client of user job efficiency | |
| CN108986801A (en) | A kind of man-machine interaction method, device and human-computer interaction terminal | |
| CN106237604A (en) | Wearable device and the method utilizing its monitoring kinestate | |
| CN105246024B (en) | The method and system of terminal device pairing connection | |
| CN105353881A (en) | Gesture recognition method and system based on RFID (radio frequency identification devices) | |
| US20160202766A1 (en) | Gesture recognition method, gesture recognition system, terminal device and wearable device | |
| CN104731307A (en) | Somatic action identifying method and man-machine interaction device | |
| CN105208513B (en) | The method and system of terminal device pairing connection confirmation | |
| CN103517118B (en) | The action identification method of a kind of remote controller and system | |
| CN105892301A (en) | Smart home control method and device | |
| CN109901539A (en) | A kind of man-machine interactive system and its control method applied to smart home | |
| Maekawa et al. | WristSense: wrist-worn sensor device with camera for daily activity recognition | |
| CN105786189A (en) | Finger independent action recognition method and system based on MMG signal | |
| CN106778476A (en) | Human posture recognition method and human body attitude identifying device | |
| CN105807640A (en) | Terminal control method and terminal control system | |
| CN110866468A (en) | Gesture recognition system and method based on passive RFID | |
| CN109766798A (en) | Gesture data processing method, server and awareness apparatus based on experience small echo |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160727 |