CN107844073A - Control method of electronic device, device, system, storage medium and processor - Google Patents
Control method of electronic device, device, system, storage medium and processor Download PDFInfo
- Publication number
- CN107844073A CN107844073A CN201710834272.5A CN201710834272A CN107844073A CN 107844073 A CN107844073 A CN 107844073A CN 201710834272 A CN201710834272 A CN 201710834272A CN 107844073 A CN107844073 A CN 107844073A
- Authority
- CN
- China
- Prior art keywords
- electronic equipment
- target
- control device
- network model
- parameter
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Air Conditioning Control Device (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention provides a kind of electronic equipment control method, device, system, storage medium and processor, wherein, this method includes:Control device obtains the current signature parameter that electronic equipment detects;Control device obtains target control signal corresponding with current signature parameter by target nerve network model, wherein, target nerve network model is used for the corresponding relation of indicative character parameter and control signal, target control signal is run for control electronics under target operation state, and target operation state is to make the running status that operational efficiency of the electronic equipment under the running environment being presently in is higher than default efficiency and energy loss is less than default loss;Control device sends target control signal to electronic equipment.Using above-mentioned technical proposal, solves the problems, such as the power consumption for reducing electronic equipment in correlation technique to the low control efficiency for causing powder consumption of electronic equipment too high, improving electronic equipment of control efficiency of electronic equipment.
Description
Technical field
The present invention relates to the communications field, is situated between in particular to a kind of electronic equipment control method, device, system, storage
Matter and processor.
Background technology
With expanding economy and science and technology progress, people in daily life the application to electronic equipment increasingly frequency
It is numerous, at the same time, requirement of the people to electronic equipment also more and more higher.Along with people's constantly carrying to energy conservation and environmental awareness
Rise, the requirement for reaching energy-conserving and environment-protective that the electronic equipment desirably used can be more intelligent.But electronic equipment is not conformed to
The operation and control of reason, the power consumption of electronic equipment can be caused too high, be unable to reach energy-saving and emission-reduction, the purpose of environmental protection.
For in correlation technique to control efficiency low the problem of causing powder consumption of electronic equipment too high of electronic equipment, at present also
Do not efficiently solve scheme.
The content of the invention
The embodiments of the invention provide a kind of electronic equipment control method, device, system, storage medium and processor, with
At least solve the problems, such as low to the control efficiency of electronic equipment in correlation technique to cause powder consumption of electronic equipment too high.
According to one embodiment of present invention, there is provided the control method of a kind of electronic equipment, including:Control device obtains
The current signature parameter that electronic equipment detects, wherein, the current signature parameter is used to indicate the current institute of the electronic equipment
The running environment at place;The control device obtains target corresponding with the current signature parameter by target nerve network model
Control signal, wherein, the target nerve network model is used for the corresponding relation of indicative character parameter and control signal, the mesh
Mark control signal is used to control the electronic equipment to run under target operation state, and the target operation state is to make the electricity
Operational efficiency of the sub- equipment under the running environment being presently in is higher than default efficiency and energy loss is less than default loss
Running status;The control device sends the target control signal to the electronic equipment.
Alternatively, the control device is obtained corresponding with the current signature parameter by the target nerve network model
The target control signal include:The control device is obtained and the current signature by the target nerve network model
Object run corresponding to parameter identifies, wherein, the target nerve network model is used for indicative character parameter and operation mark
Corresponding relation, operation mark are used for unique mark control signal;The control device identifies according to the object run and determines institute
State target control signal.
Alternatively, obtained and the current signature parameter pair by the target nerve network model in the control device
Before the target control signal answered, methods described also includes:The control device obtains sample data, wherein, the sample
Notebook data is the data for being labelled with characteristic parameter and the corresponding relation of control signal;The control device is from the sample data
Middle acquisition training sample;The control device is trained by the training sample to initial neural network model, obtains institute
Target nerve network model is stated, wherein, the initial neural network model is special according to the data of characteristic parameter and control signal
The network model that point is pre-configured with.
Alternatively, the control device is trained by the training sample to the initial neural network model, is obtained
Include to the target nerve network model:The target input parameter and target of the control device acquisition training sample are defeated
Go out parameter, and using the initial neural network model as Current Situation of Neural Network model;Following steps are repeated, until described
Error caused by the output parameter of Current Situation of Neural Network model is less than default error amount, obtains the target nerve network mould
Type:The target input parameter is inputted Current Situation of Neural Network model by the control device, obtains current output parameter;It is described
Control device determines working as the Current Situation of Neural Network model according to the current output parameter and the target output parameter
Preceding error;The control device judges whether the error current is less than preset error value;Judging that the error current is big
In or equal in the case of the preset error value, the control device adjusts the model ginseng of the Current Situation of Neural Network model
Number, obtains new Current Situation of Neural Network model.
Alternatively, the initial neural network model is trained by the training sample in the control device,
After obtaining the target nerve network model, methods described also includes:The control device obtains from the sample data
Test sample;The control device repeats using the target nerve network model as neural network model to be tested
Following steps, until determining that the neural network model to be tested is the target nerve network model:The control device
The neural network model to be tested is tested by the test sample, obtains test error;The control device
Judge whether the test error is less than default test error;Judging that it is described pre- that the test error is more than or equal to
If test error in the case of, the control device enters again through the training sample to the initial neural network model
Row training, obtains new neural network model to be tested;Judging the test error less than the default test mistake
In the case of difference, the control device determines that the neural network model to be tested is the target nerve network model.
Alternatively, the control device obtains the training sample from the sample data and from the sample data
The middle acquisition test sample includes:The control device enters according to the characteristic parameter of the sample data to the sample data
Row sequence;The control device extracts described in the conduct of the first data according to default interval from the sample data after sequence
Training sample;The control device obtains the second data in the sample data as the test sample, wherein, described the
Two data are the total data in addition to the training sample in the sample data.
Alternatively, the control device obtains the sample data and included:The control device obtains a variety of environmental forms
Corresponding characteristic parameter;The operational efficiency that the control device determines to make the electronic equipment under every kind of environmental form is higher than pre-
If efficiency and energy loss are less than the operational factor of the electronic equipment of default loss;The control device is joined to the feature
Corresponding relation between several and described operational factor is labeled, and obtains initial data;The control device is joined from the feature
Weight is obtained in number and is more than input parameter of the parameter of default weight as the sample data, wherein, the weight is used to refer to
Show influence degree of the parameter to the running status of electronic equipment, weight is bigger to represent that influence degree is bigger;The control device obtains
Output parameter of the control signal as the sample data corresponding to the operational factor is taken, wherein, the control signal is used for
The electronic equipment is controlled to be run under the running status indicated by the operational factor;The control device is from the original number
According to corresponding relation in extract the corresponding relation of the input parameter and the output parameter, obtain the sample data.
Alternatively, characteristic parameter includes at least one of:Indoor temperature, outdoor temperature, indoor humidity, outside humidity,
User profile in regional information, Weather information, current environment;Control signal includes at least one of:Compressor is controlled to turn
The signal of speed, the signal of the outer rotation speed of fan of control, the signal for controlling electronic expansion valve opening, control inner blower rotating speed signal,
Control the signal in wind deflector direction.
According to another embodiment of the invention, there is provided the control method of a kind of electronic equipment, including:Electronic equipment is examined
The current signature parameter of the electronic equipment is surveyed, wherein, the current signature parameter is used to indicate the current institute of the electronic equipment
The running environment at place;The electronic equipment sends the current signature parameter to control device, wherein, the control device is used
In obtaining corresponding with current signature parameter target control signal by target nerve network model and set to the electronics
Preparation send the target control signal, and the target nerve network model is used for indicative character parameter pass corresponding with control signal
System, the target control signal are used to control the electronic equipment to run under target operation state, the target operation state
To make, operational efficiency of the electronic equipment under the running environment being presently in is higher than default efficiency and energy loss is low
In the running status of default loss;The electronic equipment receives the target control signal that the control device returns;It is described
Electronic equipment responds the target control signal and adjusts the running status of the electronic equipment to the target operation state.
Alternatively, object run mark is carried in the target control signal, wherein, the object run, which identifies, to be used for
Target control signal described in unique mark, the electronic equipment respond the target control signal by the operation of the electronic equipment
State, which is adjusted to the target operation state, to be included:The electronic equipment adjusts the running status of the electronic equipment to described
The target operation state of object run mark instruction.
Alternatively, the running status of the electronic equipment is adjusted to the object run to identify and indicated by the electronic equipment
The target operation state include:The electronic equipment determines the target operation state according to object run mark,
Wherein, the corresponding relation of operation mark and running status is stored with the electronic equipment;The electronic equipment is by the electronics
The running status of equipment is adjusted to the target operation state.
According to another embodiment of the invention, there is provided the control device of a kind of electronic equipment, applied to control device,
Including:First acquisition module, the current signature parameter detected for obtaining electronic equipment, wherein, the current signature parameter
The running environment being presently in for indicating the electronic equipment;Second acquisition module, for passing through target nerve network model
Target control signal corresponding with the current signature parameter is obtained, wherein, the target nerve network model is used to indicate spy
The corresponding relation of parameter and control signal is levied, the target control signal is used to control the electronic equipment in target operation state
Lower operation, the target operation state are that the operational efficiency for making the electronic equipment under the running environment being presently in is high
In default efficiency and energy loss is less than the default running status being lost;First sending module, for being sent out to the electronic equipment
Send the target control signal.
According to another embodiment of the invention, there is provided the control device of a kind of electronic equipment, applied to electronic equipment,
Including:Detection module, for detecting the current signature parameter of the electronic equipment, wherein, the current signature parameter is used to refer to
Show the running environment that the electronic equipment is presently in;Second sending module, for the current signature parameter to be sent to control
Control equipment, wherein, the control device is used for corresponding with the current signature parameter by the acquisition of target nerve network model
Target control signal simultaneously sends the target control signal to the electronic equipment, and the target nerve network model is used to indicate
The corresponding relation of characteristic parameter and control signal, the target control signal are used to control the electronic equipment in object run shape
Run under state, the target operation state is the operational efficiency for making the electronic equipment under the running environment being presently in
Higher than default efficiency and energy loss is less than the default running status being lost;Receiving module, returned for receiving the control device
The target control signal returned;Adjusting module, for responding the target control signal by the operation shape of the electronic equipment
State is adjusted to the target operation state.
According to another embodiment of the invention, there is provided the control system of a kind of electronic equipment, including:Control device and
Electronic equipment, wherein, the control device, the current signature parameter detected for obtaining electronic equipment, wherein, it is described current
Characteristic parameter is used to indicate the running environment that the electronic equipment is presently in;By target nerve network model obtain with it is described
Target control signal corresponding to current signature parameter, wherein, the target nerve network model is used for indicative character parameter and control
The corresponding relation of signal processed, the target control signal are used to control the electronic equipment to run under target operation state, institute
It is to make operational efficiency of the electronic equipment under the running environment being presently in higher than default effect to state target operation state
Rate and energy loss are less than the running status of default loss;The target control signal is sent to the electronic equipment;The electricity
Sub- equipment, for detecting the current signature parameter of the electronic equipment;The current signature parameter is sent to control and set
It is standby;Receive the target control signal that the control device returns;The target control signal is responded by the electronic equipment
Running status adjust to the target operation state.
According to still another embodiment of the invention, a kind of storage medium is additionally provided, the storage medium includes storage
Program, wherein, the method described in any of the above-described is performed when described program is run.
According to still another embodiment of the invention, a kind of processor is additionally provided, the processor is used for operation program, its
In, the method described in any of the above-described is performed when described program is run.
By the present invention, control device obtains the current signature parameter that electronic equipment detects, wherein, current signature parameter
The running environment being presently in for indicating electronic equipment;Control device is obtained by target nerve network model and current signature
Target control signal corresponding to parameter, wherein, it is corresponding with control signal that target nerve network model is used for indicative character parameter
Relation, target control signal are run for control electronics under target operation state, and target operation state is to set electronics
The standby operational efficiency under the running environment being presently in is higher than default efficiency and energy loss is less than the operation shape for presetting loss
State;Control device sends target control signal to electronic equipment, it can be seen that, electronics is obtained using such scheme control device and set
The standby current signature parameter detected, is obtained by target nerve network model and enables to electronic equipment in the fortune being presently in
Operational efficiency under row environment is higher than default efficiency and energy loss is less than the default target operation state being lost, and passes through target
Control signal control electronics adjust running status to the target operation state, with the running status energy of control electronics
The environment that the adaptation of enough intelligence is presently in so that the operation of electronic equipment disclosure satisfy that user to energy-saving and emission-reduction environmental protection
Demand, this improves the control efficiency of electronic equipment, the power consumption of electronic equipment is reduced, so as to solve in correlation technique
To control efficiency low the problem of causing powder consumption of electronic equipment too high of electronic equipment.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, forms the part of the application, this hair
Bright schematic description and description is used to explain the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the hardware block diagram of the mobile terminal of the control method of a kind of electronic equipment of the embodiment of the present invention;
Fig. 2 is the flow chart of the control method of a kind of electronic equipment according to embodiments of the present invention;
Fig. 3 is the schematic diagram according to a kind of initial neural network model of optional embodiment of the invention;
Fig. 4 is the signal according to a kind of BP neural network of initial neural network model of optional embodiment of the invention
Figure;
Fig. 5 is the CNN convolutional neural networks according to a kind of initial neural network model of optional embodiment of the invention
Schematic diagram;
Fig. 6 is showing according to the residual error neutral net of initial neural network model of embodiment of the invention optional a kind of
It is intended to one;
Fig. 7 is showing according to the residual error neutral net of initial neural network model of embodiment of the invention optional a kind of
It is intended to two;
Fig. 8 is the flow chart of the control method of another electronic equipment according to embodiments of the present invention;
Fig. 9 is the structured flowchart of the control device of a kind of electronic equipment according to embodiments of the present invention;
Figure 10 is the structured flowchart of the control device of another electronic equipment according to embodiments of the present invention;
Figure 11 is the schematic diagram according to the control system of a kind of electronic equipment of optional embodiment of the invention.
Embodiment
Describe the present invention in detail below with reference to accompanying drawing and in conjunction with the embodiments.It should be noted that do not conflicting
In the case of, the feature in embodiment and embodiment in the application can be mutually combined.
It should be noted that term " first " in description and claims of this specification and above-mentioned accompanying drawing, "
Two " etc. be for distinguishing similar object, without for describing specific order or precedence.
Embodiment 1
The embodiment of the method that the embodiment of the present application 1 is provided can be in mobile terminal, terminal or similar fortune
Calculate and performed in device.Exemplified by running on mobile terminals, Fig. 1 is the control method of a kind of electronic equipment of the embodiment of the present invention
Mobile terminal hardware block diagram, as shown in figure 1, mobile terminal 10 can include one or more (one is only shown in figure
It is individual) (processor 102 can include but is not limited to Micro-processor MCV or PLD FPGA etc. processing to processor 102
Device), the memory 104 for data storage and the transmitting device 106 for communication function.Ordinary skill people
It is appreciated that the structure shown in Fig. 1 is only to illustrate, it does not cause to limit member to the structure of above-mentioned electronic installation.It is for example, mobile
Terminal 10 may also include more either less components than shown in Fig. 1 or have the configuration different from shown in Fig. 1.
Memory 104 can be used for the software program and module of storage application software, such as the electronics in the embodiment of the present invention
Programmed instruction/module corresponding to the control method of equipment, processor 102 are stored in the software journey in memory 104 by operation
Sequence and module, so as to perform various function application and data processing, that is, realize above-mentioned method.Memory 104 may include
High speed random access memory, may also include nonvolatile memory, as one or more magnetic storage device, flash memory or its
His non-volatile solid state memory.In some instances, memory 104 can further comprise remotely setting relative to processor 102
The memory put, these remote memories can pass through network connection to mobile terminal 10.The example of above-mentioned network is included but not
It is limited to internet, intranet, LAN, mobile radio communication and combinations thereof.
Transmitting device 106 is used to data are received or sent via a network.Above-mentioned network instantiation may include
The wireless network that the communication providerses of mobile terminal 10 provide.In an example, transmitting device 106 includes a Network adaptation
Device (Network Interface Controller, NIC), its can be connected by base station with other network equipments so as to it is mutual
Networking is communicated.In an example, transmitting device 106 can be radio frequency (Radio Frequency, RF) module, and it is used
In wirelessly being communicated with internet.
The control method of a kind of electronic equipment is provided in the present embodiment, and Fig. 2 is one kind according to embodiments of the present invention
The flow chart of the control method of electronic equipment, as shown in Fig. 2 the flow comprises the following steps:
Step S202, control device obtain the current signature parameter that electronic equipment detects, wherein, current signature parameter is used
In the running environment that instruction electronic equipment is presently in;
Step S204, control device obtain target control corresponding with current signature parameter by target nerve network model
Signal, wherein, target nerve network model is used for the corresponding relation of indicative character parameter and control signal, and target control signal is used
Run in control electronics under target operation state, target operation state is to make electronic equipment in the operation ring being presently in
Operational efficiency under border is higher than default efficiency and energy loss is less than the default running status being lost;
Step S206, control device send target control signal to electronic equipment.
Alternatively, the control method of above-mentioned electronic equipment can be, but not limited to be applied to by control device control electronics
Scene in.Such as:By the scene of control device control air-conditioning equipment.
Alternatively, the control method of above-mentioned electronic equipment can be, but not limited to be applied to control device, such as:The control is set
It is standby to can be, but not limited to include:Wireless communication module, router (such as Intelligent routing), server (such as cloud server),
Intelligent terminal (mobile phone, tablet personal computer, Intelligent worn device etc.), electronic equipment mainboard.
Alternatively, in the present embodiment, above-mentioned electronic equipment can be, but not limited to include:Intelligent home device, such as:It is empty
Tune, air purifier, fan, intelligent kitchen tools, intelligent sofa, intelligent table, Intelligent seat etc..
Alternatively, in the present embodiment, above-mentioned default efficiency and default loss can be, but not limited to be that basis sets electronics
Set for the low requirement of efficiency high energy consumption.Such as:By taking the control to air-conditioning equipment as an example, preset efficiency and default loss can
With but be not limited to the energy valid value and power consumption values set on the premise of it disclosure satisfy that user to the requirement of environment temperature so that it is empty
Adjust the efficiency and energy consumption relative equilibrium of equipment.
Alternatively, in the present embodiment, ambient parameter can be, but not limited to include:Indoor temperature, outdoor temperature, interior are wet
User profile in degree, outside humidity, regional information, Weather information, current environment etc..It should be noted that ambient parameter
For indicating the environment where electronic equipment, above-mentioned ambient parameter is a kind of example, and the ambient parameter of the present embodiment is not limited to
Above-mentioned ambient parameter.
Alternatively, in the present embodiment, the user profile in current environment can be, but not limited to include:User's sex, use
Family age, number of users, user's clothing information (thickness of wearing the clothes, clothing species etc.), user health information etc..Need to illustrate
, the user profile in current environment is used to indicating the information for the user being under a certain environment, in above-mentioned current environment
User profile is a kind of example, and the ambient parameter of the present embodiment is not limited to above-mentioned ambient parameter.
Alternatively, in the present embodiment, the control to electronic equipment running status can be, but not limited to be to electronic equipment
The control of middle load, the running status of load or the operational factor of control load etc. can be controlled.
By above-mentioned steps, control device obtains the current signature parameter that electronic equipment detects, passes through target nerve net
Network model, which obtains, enables to operational efficiency of the electronic equipment under the running environment being presently in be higher than default efficiency and energy
Loss less than default loss target operation state, and by target control signal control electronics by running status adjust to
The target operation state, the environment that is presently in of adaptation of intelligence is capable of with the running status of control electronics so that electronics
The operation of equipment disclosure satisfy that demand of the user to energy-saving and emission-reduction environmental protection, this improves the control efficiency of electronic equipment,
The power consumption of electronic equipment is reduced, low to the control efficiency of electronic equipment in correlation technique causes electronic equipment work(so as to solve
Consume the problem of too high.
Alternatively, in above-mentioned steps S204, control device can be, but not limited to obtain in the following manner:Control device
Object run corresponding with current signature parameter is obtained by target nerve network model to identify, wherein, target nerve network mould
Type is used for the corresponding relation of indicative character parameter and operation mark, and operation mark is used for unique mark control signal;According to target
Operation mark determines target control signal.
Alternatively, before above-mentioned steps S204, control device can be, but not limited to train to obtain mesh in the following manner
Mark neural network model:Control device obtains sample data, wherein, sample data is to be labelled with characteristic parameter and control signal
Corresponding relation data;Control device obtains training sample from sample data;Control device is by training sample to initial
Neural network model is trained, and obtains target nerve network model, wherein, initial neural network model is according to characteristic parameter
The network model being pre-configured with the data characteristicses of control signal.
Alternatively, control device can be, but not limited to train initial neural network model in the following manner, obtain target
Neural network model:Control device obtains the target input parameter and target output parameter of training sample, and by initial nerve net
Network model is as Current Situation of Neural Network model;Following steps are repeated, until the output parameter of Current Situation of Neural Network model produces
Raw error is less than default error amount, obtains target nerve network model:Control device inputs target input parameter current
Neural network model, obtain current output parameter;Control device determines according to current output parameter and target output parameter
The error current of Current Situation of Neural Network model;Control device judges whether error current is less than preset error value;Judging to work as
In the case that preceding error is more than or equal to preset error value, control device adjusts the model parameter of Current Situation of Neural Network model,
Obtain new Current Situation of Neural Network model.
In an optional embodiment, so that control device controls air-conditioning equipment as an example, control device is according to different
Characteristic parameter (such as:Design temperature, environment temperature, the shell temperature etc. of user) data characteristic that is influenceed on operation of air conditioner and its
The rule contained, the basic structure of network, the input of network, output node number, network hidden layer number, hidden node can be primarily determined that
Number, network initial weight etc., obtain initial neural network model.Fig. 3 is according to a kind of first of optional embodiment of the invention
The schematic diagram of beginning neural network model, as shown in figure 3, initial neural network model is provided with multiple input parameter (input parameters
1- input parameter n), input parameter is input to initial neural network model and obtains output parameter as energy-saving operation of air conditioner mark.
The network structure of initial neural network model can be, but not limited to include following three kinds of network structures:
Structure one, BP neural network
The structure design of BP networks mainly solves the problems, such as to set several hidden layers and several hidden nodes.Hidden layer and hidden node are really
Surely can constantly be adjusted in network training.One hidden layer is first set during design, improves net by adjusting the number of hidden nodes
Network performance;When Hidden nodes are excessive, excessive fitting occur, increase hidden layer is considered further that, hidden node is reduced, to improve internetworking
Energy.Fig. 4 is according to a kind of schematic diagram of the BP neural network of initial neural network model of embodiment of the invention optional, such as
Shown in Fig. 4, initial neural network model is provided with multiple input parameters (input parameter 1- input parameter n), and multiple hidden sections
Point (hidden node 1- hidden node m), wherein, each hidden node can be individual layer or the node of multilayer, initial neural network model
Output parameter for energy-saving operation of air conditioner mark (can be adjusted as needed during practical application input layer, hidden layer, output node layer
Number and hidden layers numbers).
Structure two, 4.2CNN convolutional neural networks
Multilayer convolutional network be exactly constantly extracted from the feature of low dimensional merge the feature for obtaining more higher-dimension so as to
To be classified or inter-related task.In this optional embodiment, Fig. 5 is according to a kind of first of optional embodiment of the invention
The schematic diagram of the CNN convolutional neural networks of beginning neural network model, obtained as shown in figure 5, initial data can be continuous acquisition,
Intuitively it is and time correlation.A certain amount of rule of data one can be combined, be regarded as the number as image
According to form, Existential Space serial relation between row and row, column and row, these relationship affects " label " of final data, also
It is energy-saving run mark.So as to carry out feature extraction to input data by convolutional neural networks, air-conditioning is accurately detected
According to running most power saving under which kind of energy saver mode.(network structure can adjust according to actual conditions during practical application).
Structure three, residual error neutral net
When debugging CNN networks, deepening the method for the network number of plies and change convolution kernel size can not cause network to show
Get a promotion.Front and rear data can preferably be connected by adding residual block, strengthen feature representation ability, so it can strengthen convolution
The learning ability of network.In this optional embodiment, Fig. 6 is a kind of initial nerve according to optional embodiment of the invention
The schematic diagram one of the residual error neutral net of network model, as shown in fig. 6, the input of certain section of neutral net is x, desired output H
(x) after input x, is passed to output as initial configuration, the target of study is just changed into F (x)=H (x)-x.
In this optional embodiment, Fig. 7 is a kind of initial neutral net mould according to optional embodiment of the invention
The schematic diagram two of the residual error neutral net of type, as shown in fig. 7, network structure can adjust according to actual conditions during practical application.
Alternatively, in this optional embodiment, after the completion of network design, training sample data can be used, network is entered
Row training.Training method can be adjusted according to the problem of discovery in the network structure of reality and training.Herein only for originally may be used
The one of which method in embodiment is selected to be illustrated below:
Input data x is imported, the reality output a of network is calculated according to activation primitive, the weights of initialization and biasing
(x), i.e., a (x)=1/ (1+e-z), wherein Z=Wk*x+bl.
Judge whether the desired output y (x) and reality output a (x) of network meet output accuracy requirement i.e.:
‖y(x)-a(x)‖<∈, ∈ are target minimal error
Terminate to train if required precision is met, update the weights Wk of network according in the following manner if being unsatisfactory for, partially
Put bl:
C (w, b) is error energy function (by taking standard variance function as an example), and n is the total quantity of training sample, summation be
Carried out on total training sample x
Update each layer weights:
Update each layer biasing:
Wherein:
Wk is initial weight,For the partial derivative of error energy function pair weights.
Bl is initial bias,For the partial derivative of error energy function pair biasing.
Value can be obtained by chain type Rule for derivation.
Untill the output error of network is less than ∈, so as to obtain target nerve network model.
Alternatively, can also be to obtained target nerve network mould after being trained to initial neural network model
Type is tested, to improve the precision of target nerve network model, so as to improve the control efficiency of electronic equipment.Such as:Control
Equipment obtains test sample from sample data;Using target nerve network model as neural network model to be tested, repeat
Following steps are performed, until determining that neural network model to be tested is target nerve network model:Treated by test sample
The neural network model of test is tested, and obtains test error;Judge whether test error is less than default test error;
In the case of judging that test error is more than or equal to default test error, again through training sample to initial nerve net
Network model is trained, and obtains new neural network model to be tested;Judging test error less than default test mistake
In the case of difference, it is target nerve network model to determine neural network model to be tested.
,, can be with after the completion of network training so that control device controls air-conditioning equipment as an example in an optional embodiment
Test sample positive test network is used again.When test error is unsatisfactory for requiring, then repeatedly above step, re -training network;
If test error meets to require, network training test is completed.
Alternatively, control device can be, but not limited to obtain training sample and test sample in the following manner:Control
Equipment is ranked up according to the characteristic parameter of sample data to sample data;It is spaced according to default from the sample data after sequence
The first data of middle extraction are as training sample;The second data in sample data are obtained as test sample, wherein, the second data
For the total data in sample data in addition to training sample.
In an optional embodiment, so that control device controls air-conditioning equipment as an example, all sample datas are listed,
Sample data is classified according to the data collected and marked, from different classes of sample, data are uniformly extracted, as training
Sample;After extracting training sample, remaining data can be used as test sample.
Alternatively, control device can be, but not limited to obtain sample data in the following manner:Control device obtains a variety of
Characteristic parameter corresponding to environmental form;It is determined that make under every kind of environmental form electronic equipment operational efficiency be higher than default efficiency and
Operational factor of the energy loss less than the electronic equipment of default loss;Corresponding relation between characteristic parameter and operational factor is entered
Rower is noted, and obtains initial data;Weight is obtained from characteristic parameter and is more than input of the parameter of default weight as sample data
Parameter, wherein, weight is used to indicate influence degree of the parameter to the running status of electronic equipment, the bigger expression influence degree of weight
It is bigger;Output parameter of the control signal as sample data corresponding to operational factor is obtained, wherein, control signal is used to control electricity
Sub- equipment is run under the running status indicated by operational factor;From the corresponding relation of initial data extract input parameter with it is defeated
Go out the corresponding relation of parameter, obtain sample data.
In an optional embodiment, so that control device controls air-conditioning equipment as an example, first, air-conditioning is collected in difference
Under running environment, during different set temperature, the low pattern of efficiency high energy consumption is simultaneously marked in detail.Specific collection mode include but
It is not limited to operational factor of the air-conditioning under laboratory simulation environment, air-conditioning when actual user uses is collected by technology of Internet of things
The modes such as operational factor.
By the analysis to initial data and with reference to expertise, the sensor being had a great influence to air conditioning operating mode is chosen
Data identify different energy-saving runs as output quantity as input parameter.Wherein, input parameter includes but is not limited to interior
Outer environment temperature, air-conditioning design temperature, body surface temperature etc..Input parameter is not only single parameter, is included by certain yet
The input parameter matrix of rule composition.
Because each parameter may have different physical significance and dimension, standardization can also be made to input parameter, so
Carry out unified conversion process again afterwards.In present embodiment, data processing method includes but is not limited to data are normalized
Etc. the Nonlinear Processing such as linear process and logarithmic transformation, square root transformation, cubic root conversion.
Alternatively, characteristic parameter can be, but not limited to include at least one of:Indoor temperature, outdoor temperature, interior are wet
User profile in degree, outside humidity, regional information, Weather information, current environment;Control signal can be, but not limited to include with
It is at least one lower:Control the signal of compressor rotary speed, the signal of the outer rotation speed of fan of control, the letter of control electronic expansion valve opening
Number, the signal of control inner blower rotating speed, the signal in control wind deflector direction.
The control method of another electronic equipment is additionally provided in the present embodiment, and Fig. 8 is according to embodiments of the present invention
The flow chart of the control method of another electronic equipment, as shown in figure 8, the flow comprises the following steps:
Step S802, electronic equipment detect the current signature parameter of electronic equipment, wherein, current signature parameter is used to indicate
The running environment that electronic equipment is presently in;
Step S804, electronic equipment send current signature parameter to control device, wherein, control device is used to pass through mesh
Neural network model is marked to obtain target control signal corresponding with current signature parameter and send target control letter to electronic equipment
Number, target nerve network model is used for the corresponding relation of indicative character parameter and control signal, and target control signal is used to control
Electronic equipment is run under target operation state, and target operation state is to make electronic equipment under the running environment being presently in
Operational efficiency is higher than default efficiency and energy loss is less than the default running status being lost;
Step S806, the target control signal that electronic equipment receiving control apparatus returns;
Step S808, electronic equipment response target control signal adjust the running status of electronic equipment to object run shape
State.
Alternatively, the control method of above-mentioned electronic equipment can be, but not limited to be applied to by control device control electronics
Scene in.Such as:By the scene of control device control air-conditioning equipment.
Alternatively, above-mentioned control device can be, but not limited to include:Wireless communication module, router (such as intelligent road
By), server (such as cloud server), intelligent terminal (mobile phone, tablet personal computer, Intelligent worn device etc.), electronics
Equipment mainboard.
Alternatively, in the present embodiment, above-mentioned electronic equipment can be, but not limited to include:Intelligent home device, such as:It is empty
Tune, air purifier, fan, intelligent kitchen tools, intelligent sofa, intelligent table, Intelligent seat etc..
Alternatively, in the present embodiment, above-mentioned default efficiency and default loss can be, but not limited to be that basis sets electronics
Set for the low requirement of efficiency high energy consumption.Such as:By taking the control to air-conditioning equipment as an example, preset efficiency and default loss can
With but be not limited to the energy valid value and power consumption values set on the premise of it disclosure satisfy that user to the requirement of environment temperature so that it is empty
Adjust the efficiency and energy consumption relative equilibrium of equipment.
Alternatively, in the present embodiment, ambient parameter can be, but not limited to include:Indoor temperature, outdoor temperature, interior are wet
User profile in degree, outside humidity, regional information, Weather information, current environment etc..It should be noted that ambient parameter
For indicating the environment where electronic equipment, above-mentioned ambient parameter is a kind of example, and the ambient parameter of the present embodiment is not limited to
Above-mentioned ambient parameter.
Alternatively, in the present embodiment, the user profile in current environment can be, but not limited to include:User's sex, use
Family age, number of users, user's clothing information (thickness of wearing the clothes, clothing species etc.), user health information etc..Need to illustrate
, the user profile in current environment is used to indicating the information for the user being under a certain environment, in above-mentioned current environment
User profile is a kind of example, and the ambient parameter of the present embodiment is not limited to above-mentioned ambient parameter.
Alternatively, in the present embodiment, the control to electronic equipment running status can be, but not limited to be to electronic equipment
The control of middle load, the running status of load or the operational factor of control load etc. can be controlled.
By above-mentioned steps, control device obtains the current signature parameter that electronic equipment detects, passes through target nerve net
Network model, which obtains, enables to operational efficiency of the electronic equipment under the running environment being presently in be higher than default efficiency and energy
Loss less than default loss target operation state, and by target control signal control electronics by running status adjust to
The target operation state, the environment that is presently in of adaptation of intelligence is capable of with the running status of control electronics so that electronics
The operation of equipment disclosure satisfy that demand of the user to energy-saving and emission-reduction environmental protection, this improves the control efficiency of electronic equipment,
The power consumption of electronic equipment is reduced, low to the control efficiency of electronic equipment in correlation technique causes electronic equipment work(so as to solve
Consume the problem of too high.
Alternatively, object run mark is carried in target control signal, wherein, object run is identified for unique mark
Target control signal, in above-mentioned steps S808, the running status of the electronic equipment can be adjusted to target and transported by electronic equipment
The target operation state of line identifier instruction.
Alternatively, operation mark and the corresponding relation of running status, electronic equipment can be previously stored with electronic equipment
It can be identified to identify in the corresponding relation with running status from the operation of storage according to object run and determine target operation state, and
The running status of electronic equipment is adjusted to target operation state.
Embodiment 2
Additionally provide the control device of a kind of electronic equipment in the present embodiment, the device be used for realize above-described embodiment and
Preferred embodiment, repeating no more for explanation was carried out.As used below, term " module " can realize predetermined work(
The combination of the software and/or hardware of energy.Although device described by following examples is preferably realized with software, firmly
Part, or the realization of the combination of software and hardware is also what may and be contemplated.
Fig. 9 is the structured flowchart of the control device of a kind of electronic equipment according to embodiments of the present invention, as shown in figure 9, should
Device includes:
First acquisition module 92, the current signature parameter detected for obtaining electronic equipment, wherein, current signature parameter
The running environment being presently in for indicating electronic equipment;
Second acquisition module 94, for obtaining target control corresponding with current signature parameter by target nerve network model
Signal processed, wherein, target nerve network model is used for the corresponding relation of indicative character parameter and control signal, target control signal
Run for control electronics under target operation state, target operation state is to make electronic equipment in the operation being presently in
Operational efficiency under environment is higher than default efficiency and energy loss is less than the default running status being lost;
First sending module 96, for sending target control signal to electronic equipment.
Alternatively, the control device of above-mentioned electronic equipment can be, but not limited to be applied to by control device control electronics
Scene in.Such as:By the scene of control device control air-conditioning equipment.
Alternatively, the control device of above-mentioned electronic equipment can be, but not limited to be applied to control device, such as:The control is set
It is standby to can be, but not limited to include:Wireless communication module, router (such as Intelligent routing), server (such as cloud server),
Intelligent terminal (mobile phone, tablet personal computer, Intelligent worn device etc.), electronic equipment mainboard.
Alternatively, in the present embodiment, above-mentioned electronic equipment can be, but not limited to include:Intelligent home device, such as:It is empty
Tune, air purifier, fan, intelligent kitchen tools, intelligent sofa, intelligent table, Intelligent seat etc..
Alternatively, in the present embodiment, above-mentioned default efficiency and default loss can be, but not limited to be that basis sets electronics
Set for the low requirement of efficiency high energy consumption.Such as:By taking the control to air-conditioning equipment as an example, preset efficiency and default loss can
With but be not limited to the energy valid value and power consumption values set on the premise of it disclosure satisfy that user to the requirement of environment temperature so that it is empty
Adjust the efficiency and energy consumption relative equilibrium of equipment.
Alternatively, in the present embodiment, ambient parameter can be, but not limited to include:Indoor temperature, outdoor temperature, interior are wet
User profile in degree, outside humidity, regional information, Weather information, current environment etc..It should be noted that ambient parameter
For indicating the environment where electronic equipment, above-mentioned ambient parameter is a kind of example, and the ambient parameter of the present embodiment is not limited to
Above-mentioned ambient parameter.
Alternatively, in the present embodiment, the user profile in current environment can be, but not limited to include:User's sex, use
Family age, number of users, user's clothing information (thickness of wearing the clothes, clothing species etc.), user health information etc..Need to illustrate
, the user profile in current environment is used to indicating the information for the user being under a certain environment, in above-mentioned current environment
User profile is a kind of example, and the ambient parameter of the present embodiment is not limited to above-mentioned ambient parameter.
Alternatively, in the present embodiment, the control to electronic equipment running status can be, but not limited to be to electronic equipment
The control of middle load, the running status of load or the operational factor of control load etc. can be controlled.
By said apparatus, control device obtains the current signature parameter that electronic equipment detects, passes through target nerve net
Network model, which obtains, enables to operational efficiency of the electronic equipment under the running environment being presently in be higher than default efficiency and energy
Loss less than default loss target operation state, and by target control signal control electronics by running status adjust to
The target operation state, the environment that is presently in of adaptation of intelligence is capable of with the running status of control electronics so that electronics
The operation of equipment disclosure satisfy that demand of the user to energy-saving and emission-reduction environmental protection, this improves the control efficiency of electronic equipment,
The power consumption of electronic equipment is reduced, low to the control efficiency of electronic equipment in correlation technique causes electronic equipment work(so as to solve
Consume the problem of too high.
Alternatively, above-mentioned second acquisition module is used for:Obtained and current signature parameter pair by target nerve network model
The object run mark answered, wherein, target nerve network model is used for the corresponding relation of indicative character parameter and operation mark, fortune
Line identifier is used for unique mark control signal;Identified according to object run and determine target control signal.
Alternatively, said apparatus also includes:3rd acquisition module, for obtaining sample data, wherein, sample data is
It is labelled with the data of characteristic parameter and the corresponding relation of control signal;4th acquisition module, for obtaining instruction from sample data
Practice sample;Training module, for being trained by training sample to initial neural network model, obtain target nerve network mould
Type, wherein, initial neural network model is the network model being pre-configured with according to the data characteristicses of characteristic parameter and control signal.
Alternatively, training module is used for:The target input parameter and target output parameter of training sample are obtained, and will be initial
Neural network model is as Current Situation of Neural Network model;Following steps are repeated, until the output of Current Situation of Neural Network model
Error caused by parameter is less than default error amount, obtains target nerve network model:Target input parameter is inputted into current god
Through network model, current output parameter is obtained;Current neural net is determined according to current output parameter and target output parameter
The error current of network model;Judge whether error current is less than preset error value;Judging that error current is more than or equal to
In the case of preset error value, control device adjusts the model parameter of Current Situation of Neural Network model, obtains new Current neural net
Network model.
Alternatively, said apparatus also includes:
5th acquisition module, for obtaining test sample from sample data;Execution module, for by target nerve network
Model repeats following steps, until determining that neural network model to be tested is as neural network model to be tested
Target nerve network model:Neural network model to be tested is tested by test sample, obtains test error;Judge
Whether test error is less than default test error;Judging feelings of the test error more than or equal to default test error
Under condition, initial neural network model is trained again through training sample, obtains new neural network model to be tested;
In the case where judging that test error is less than default test error, it is target nerve to determine neural network model to be tested
Network model.
Alternatively, above-mentioned 4th acquisition module and the 5th acquisition module are used for:According to the characteristic parameter of sample data to sample
Notebook data is ranked up;The first data are extracted as training sample from the sample data after sequence according to default interval;Obtain
The second data in notebook data are sampled as test sample, wherein, the second data in sample data in addition to training sample
Total data.
Alternatively, above-mentioned 3rd acquisition module is used for:Obtain characteristic parameter corresponding to a variety of environmental forms;It is determined that every kind of
Make the operational efficiency of electronic equipment under environmental form higher than default efficiency and energy loss is less than the electronic equipment of default loss
Operational factor;Corresponding relation between characteristic parameter and operational factor is labeled, obtains initial data;From characteristic parameter
Obtain weight and be more than input parameter of the parameter of default weight as sample data, wherein, weight is used to indicate parameter to electronics
The influence degree of the running status of equipment, weight is bigger to represent that influence degree is bigger;Obtain control signal corresponding to operational factor
As the output parameter of sample data, wherein, control signal is used for control electronics in the operation shape indicated by operational factor
Run under state;The corresponding relation of input parameter and output parameter is extracted from the corresponding relation of initial data, obtains sample data.
Alternatively, characteristic parameter includes at least one of:Indoor temperature, outdoor temperature, indoor humidity, outside humidity,
User profile in regional information, Weather information, current environment;Control signal includes at least one of:Compressor is controlled to turn
The signal of speed, the signal of the outer rotation speed of fan of control, the signal for controlling electronic expansion valve opening, control inner blower rotating speed signal,
Control the signal in wind deflector direction.
The control device of another electronic equipment is additionally provided in the present embodiment, and Figure 10 is according to embodiments of the present invention
The structured flowchart of the control device of another electronic equipment, as shown in Figure 10, the device include:
Detection module 102, for detecting the current signature parameter of electronic equipment, wherein, current signature parameter is used to indicate
The running environment that electronic equipment is presently in;
Second sending module 104, for current signature parameter to be sent to control device, wherein, control device is used to lead to
Target neural network model is crossed to obtain target control signal corresponding with current signature parameter and send target control to electronic equipment
Signal processed, target nerve network model are used for the corresponding relation of indicative character parameter and control signal, and target control signal is used for
Control electronics are run under target operation state, and target operation state is to make electronic equipment in the running environment being presently in
Under operational efficiency be higher than default efficiency and energy loss less than default loss running status;
Receiving module 106, the target control signal returned for receiving control apparatus;
Adjusting module 108, the running status of electronic equipment is adjusted to object run shape for responding target control signal
State.
Alternatively, the control device of above-mentioned electronic equipment can be, but not limited to be applied to by control device control electronics
Scene in.Such as:By the scene of control device control air-conditioning equipment.
Alternatively, above-mentioned control device can be, but not limited to include:Wireless communication module, router (such as intelligent road
By), server (such as cloud server), intelligent terminal (mobile phone, tablet personal computer, Intelligent worn device etc.), electronics
Equipment mainboard.
Alternatively, in the present embodiment, above-mentioned electronic equipment can be, but not limited to include:Intelligent home device, such as:It is empty
Tune, air purifier, fan, intelligent kitchen tools, intelligent sofa, intelligent table, Intelligent seat etc..
Alternatively, in the present embodiment, above-mentioned default efficiency and default loss can be, but not limited to be that basis sets electronics
Set for the low requirement of efficiency high energy consumption.Such as:By taking the control to air-conditioning equipment as an example, preset efficiency and default loss can
With but be not limited to the energy valid value and power consumption values set on the premise of it disclosure satisfy that user to the requirement of environment temperature so that it is empty
Adjust the efficiency and energy consumption relative equilibrium of equipment.
Alternatively, in the present embodiment, ambient parameter can be, but not limited to include:Indoor temperature, outdoor temperature, interior are wet
User profile in degree, outside humidity, regional information, Weather information, current environment etc..It should be noted that ambient parameter
For indicating the environment where electronic equipment, above-mentioned ambient parameter is a kind of example, and the ambient parameter of the present embodiment is not limited to
Above-mentioned ambient parameter.
Alternatively, in the present embodiment, the user profile in current environment can be, but not limited to include:User's sex, use
Family age, number of users, user's clothing information (thickness of wearing the clothes, clothing species etc.), user health information etc..Need to illustrate
, the user profile in current environment is used to indicating the information for the user being under a certain environment, in above-mentioned current environment
User profile is a kind of example, and the ambient parameter of the present embodiment is not limited to above-mentioned ambient parameter.
Alternatively, in the present embodiment, the control to electronic equipment running status can be, but not limited to be to electronic equipment
The control of middle load, the running status of load or the operational factor of control load etc. can be controlled.
By said apparatus, control device obtains the current signature parameter that electronic equipment detects, passes through target nerve net
Network model, which obtains, enables to operational efficiency of the electronic equipment under the running environment being presently in be higher than default efficiency and energy
Loss less than default loss target operation state, and by target control signal control electronics by running status adjust to
The target operation state, the environment that is presently in of adaptation of intelligence is capable of with the running status of control electronics so that electronics
The operation of equipment disclosure satisfy that demand of the user to energy-saving and emission-reduction environmental protection, this improves the control efficiency of electronic equipment,
The power consumption of electronic equipment is reduced, low to the control efficiency of electronic equipment in correlation technique causes electronic equipment work(so as to solve
Consume the problem of too high.
Alternatively, object run mark is carried in target control signal, wherein, object run is identified for unique mark
Target control signal, above-mentioned adjusting module are used for:The running status of electronic equipment is adjusted to the mesh of object run mark instruction
Mark running status.
Alternatively, above-mentioned adjusting module is used for:Identified according to object run and determine target operation state, wherein, electronics is set
The corresponding relation of operation mark and running status is stored with standby;The running status of electronic equipment is adjusted to object run shape
State.
Embodiment 3
The control system of a kind of electronic equipment is additionally provided in the present embodiment, and the system includes:Control device and electronics
Equipment, wherein,
Control device, the current signature parameter detected for obtaining electronic equipment, wherein, current signature parameter is used to refer to
Show the running environment that electronic equipment is presently in;Target corresponding with current signature parameter is obtained by target nerve network model
Control signal, wherein, target nerve network model is used for the corresponding relation of indicative character parameter and control signal, target control letter
Number run for control electronics under target operation state, target operation state is to make electronic equipment in the fortune being presently in
Operational efficiency under row environment is higher than default efficiency and energy loss is less than the default running status being lost;Sent to electronic equipment
Target control signal;
Electronic equipment, for detecting the current signature parameter of electronic equipment;Current signature parameter is sent to control device;
The target control signal that receiving control apparatus returns;Response target control signal adjusts the running status of electronic equipment to target
Running status.
Alternatively, the control system of above-mentioned electronic equipment can be, but not limited to be applied to by control device control electronics
Scene in.Such as:By the scene of control device control air-conditioning equipment.
Alternatively, above-mentioned control device can be, but not limited to include:Wireless communication module, router (such as intelligent road
By), server (such as cloud server), intelligent terminal (mobile phone, tablet personal computer, Intelligent worn device etc.), electronics
Equipment mainboard.
Alternatively, in the present embodiment, above-mentioned electronic equipment can be, but not limited to include:Intelligent home device, such as:It is empty
Tune, air purifier, fan, intelligent kitchen tools, intelligent sofa, intelligent table, Intelligent seat etc..Electronic equipment can with but it is unlimited
In for one or more.
Alternatively, in the present embodiment, above-mentioned default efficiency and default loss can be, but not limited to be that basis sets electronics
Set for the low requirement of efficiency high energy consumption.Such as:By taking the control to air-conditioning equipment as an example, preset efficiency and default loss can
With but be not limited to the energy valid value and power consumption values set on the premise of it disclosure satisfy that user to the requirement of environment temperature so that it is empty
Adjust the efficiency and energy consumption relative equilibrium of equipment.
Alternatively, in the present embodiment, ambient parameter can be, but not limited to include:Indoor temperature, outdoor temperature, interior are wet
User profile in degree, outside humidity, regional information, Weather information, current environment etc..It should be noted that ambient parameter
For indicating the environment where electronic equipment, above-mentioned ambient parameter is a kind of example, and the ambient parameter of the present embodiment is not limited to
Above-mentioned ambient parameter.
Alternatively, in the present embodiment, the user profile in current environment can be, but not limited to include:User's sex, use
Family age, number of users, user's clothing information (thickness of wearing the clothes, clothing species etc.), user health information etc..Need to illustrate
, the user profile in current environment is used to indicating the information for the user being under a certain environment, in above-mentioned current environment
User profile is a kind of example, and the ambient parameter of the present embodiment is not limited to above-mentioned ambient parameter.
Alternatively, in the present embodiment, the control to electronic equipment running status can be, but not limited to be to electronic equipment
The control of middle load, the running status of load or the operational factor of control load etc. can be controlled.
By said system, control device obtains the current signature parameter that electronic equipment detects, passes through target nerve net
Network model, which obtains, enables to operational efficiency of the electronic equipment under the running environment being presently in be higher than default efficiency and energy
Loss less than default loss target operation state, and by target control signal control electronics by running status adjust to
The target operation state, the environment that is presently in of adaptation of intelligence is capable of with the running status of control electronics so that electronics
The operation of equipment disclosure satisfy that demand of the user to energy-saving and emission-reduction environmental protection, this improves the control efficiency of electronic equipment,
The power consumption of electronic equipment is reduced, low to the control efficiency of electronic equipment in correlation technique causes electronic equipment work(so as to solve
Consume the problem of too high.
In an optional embodiment, so that control device controls air-conditioning equipment as an example, as shown in figure 11, band channel radio
During the air-conditioning equipment operation of news, the characteristic parameters such as the operational factor of air-conditioning are uploaded to control device.Control device, which will be run, joins
Number is input in target nerve network model, and after target nerve network model computing, control device sends target control to air-conditioning
Signal processed.Alternatively, control device can be, but not limited to include wireless communication module, router, server, smart mobile phone etc.
Deng.
It should be noted that above-mentioned modules can be realized by software or hardware, for the latter, Ke Yitong
Cross in the following manner realization, but not limited to this:Above-mentioned module is respectively positioned in same processor;Or above-mentioned module is respectively positioned at more
In individual processor.
The above embodiments are merely illustrative of the technical solutions of the present invention rather than is limited, the ordinary skill of this area
Technical scheme can be modified by personnel or equivalent substitution, without departing from the spirit and scope of the present invention, this
The protection domain of invention should be to be defined described in claim.
Embodiment 4
Embodiments of the invention additionally provide a kind of storage medium, and the storage medium includes the program of storage, wherein, it is above-mentioned
The method described in any of the above-described is performed when program is run.
Alternatively, in the present embodiment, above-mentioned storage medium can be configured to the journey that storage is used to perform following steps
Sequence code:
S1, control device obtain the current signature parameter that electronic equipment detects, wherein, current signature parameter is used to indicate
The running environment that electronic equipment is presently in;
S2, control device obtain target control signal corresponding with current signature parameter by target nerve network model,
Wherein, target nerve network model is used for the corresponding relation of indicative character parameter and control signal, and target control signal is used to control
Electronic equipment processed is run under target operation state, and target operation state is to make electronic equipment under the running environment being presently in
Operational efficiency be higher than default efficiency and energy loss less than default loss running status;
S3, control device send target control signal to electronic equipment.
Alternatively, storage medium is also configured to the program code that storage is used to perform following steps:
S1, electronic equipment detect the current signature parameter of electronic equipment, wherein, current signature parameter is used to indicate that electronics is set
The standby running environment being presently in;
S2, electronic equipment send current signature parameter to control device, wherein, control device is used to pass through target nerve
Network model obtains target control signal corresponding with current signature parameter and sends target control signal, target to electronic equipment
Neural network model is used for the corresponding relation of indicative character parameter and control signal, and target control signal is used for control electronics
Run under target operation state, target operation state is the operational efficiency for making electronic equipment under the running environment being presently in
Higher than default efficiency and energy loss is less than the default running status being lost;
S3, the target control signal that electronic equipment receiving control apparatus returns;
S4, electronic equipment response target control signal adjust the running status of electronic equipment to target operation state.
Alternatively, in the present embodiment, above-mentioned storage medium can include but is not limited to:USB flash disk, read-only storage (Read-
Only Memory, referred to as ROM), it is random access memory (Random Access Memory, referred to as RAM), mobile hard
Disk, magnetic disc or CD etc. are various can be with the medium of store program codes.
Embodiments of the invention additionally provide a kind of processor, and the processor is used for operation program, wherein, program operation
Step in Shi Zhihang any of the above-described methods.
Alternatively, in the present embodiment, said procedure is used to perform following steps:
S1, control device obtain the current signature parameter that electronic equipment detects, wherein, current signature parameter is used to indicate
The running environment that electronic equipment is presently in;
S2, control device obtain target control signal corresponding with current signature parameter by target nerve network model,
Wherein, target nerve network model is used for the corresponding relation of indicative character parameter and control signal, and target control signal is used to control
Electronic equipment processed is run under target operation state, and target operation state is to make electronic equipment under the running environment being presently in
Operational efficiency be higher than default efficiency and energy loss less than default loss running status;
S3, control device send target control signal to electronic equipment.
Alternatively, in the present embodiment, said procedure is additionally operable to perform following steps:
S1, electronic equipment detect the current signature parameter of electronic equipment, wherein, current signature parameter is used to indicate that electronics is set
The standby running environment being presently in;
S2, electronic equipment send current signature parameter to control device, wherein, control device is used to pass through target nerve
Network model obtains target control signal corresponding with current signature parameter and sends target control signal, target to electronic equipment
Neural network model is used for the corresponding relation of indicative character parameter and control signal, and target control signal is used for control electronics
Run under target operation state, target operation state is the operational efficiency for making electronic equipment under the running environment being presently in
Higher than default efficiency and energy loss is less than the default running status being lost;
S3, the target control signal that electronic equipment receiving control apparatus returns;
S4, electronic equipment response target control signal adjust the running status of electronic equipment to target operation state.
Alternatively, the specific example in the present embodiment may be referred to described in above-described embodiment and optional embodiment
Example, the present embodiment will not be repeated here.
Obviously, those skilled in the art should be understood that above-mentioned each module of the invention or each step can be with general
Computing device realize that they can be concentrated on single computing device, or be distributed in multiple computing devices and formed
Network on, alternatively, they can be realized with the program code that computing device can perform, it is thus possible to they are stored
Performed in the storage device by computing device, and in some cases, can be with different from shown in order execution herein
The step of going out or describing, they are either fabricated to each integrated circuit modules respectively or by multiple modules in them or
Step is fabricated to single integrated circuit module to realize.So, the present invention is not restricted to any specific hardware and software combination.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.All any modifications within the principle of the present invention, made, etc.
With replacement, improvement etc., should be included in the scope of the protection.
Claims (16)
1. the control method of a kind of electronic equipment, it is characterised in that including:
Control device obtains the current signature parameter that electronic equipment detects, wherein, the current signature parameter is used to indicate institute
State the running environment that electronic equipment is presently in;
The control device obtains target control signal corresponding with the current signature parameter by target nerve network model,
Wherein, the target nerve network model is used for the corresponding relation of indicative character parameter and control signal, the target control letter
Number it is used to control the electronic equipment to run under target operation state, the target operation state is makes the electronic equipment exist
Operational efficiency under the running environment being presently in is higher than default efficiency and energy loss is less than the default operation shape being lost
State;
The control device sends the target control signal to the electronic equipment.
2. according to the method for claim 1, it is characterised in that the control device passes through the target nerve network model
Obtaining the target control signal corresponding with the current signature parameter includes:
The control device obtains object run corresponding with the current signature parameter by the target nerve network model
Mark, wherein, the target nerve network model is used for the corresponding relation of indicative character parameter and operation mark, and operation mark is used
In unique mark control signal;
The control device determines the target control signal according to object run mark.
3. according to the method for claim 1, it is characterised in that pass through the target nerve network mould in the control device
Before type obtains the target control signal corresponding with the current signature parameter, methods described also includes:
The control device obtains sample data, wherein, the sample data is to be labelled with characteristic parameter and control signal
The data of corresponding relation;
The control device obtains training sample from the sample data;
The control device is trained by the training sample to initial neural network model, obtains the target nerve net
Network model, wherein, the initial neural network model is what is be pre-configured with according to the data characteristicses of characteristic parameter and control signal
Network model.
4. according to the method for claim 3, it is characterised in that the control device is by the training sample to described first
Beginning neural network model is trained, and obtaining the target nerve network model includes:
The control device obtains the target input parameter and target output parameter of the training sample, and will be described initial neural
Network model is as Current Situation of Neural Network model;
Following steps are repeated, until error caused by the output parameter of the Current Situation of Neural Network model is less than default mistake
Difference, obtain the target nerve network model:
The target input parameter is inputted Current Situation of Neural Network model by the control device, obtains current output parameter;
The control device determines the Current Situation of Neural Network according to the current output parameter and the target output parameter
The error current of model;
The control device judges whether the error current is less than preset error value;
In the case where judging that the error current is more than or equal to the preset error value, the control device adjusts institute
The model parameter of Current Situation of Neural Network model is stated, obtains new Current Situation of Neural Network model.
5. the method according to claim 3 or 4, it is characterised in that pass through the training sample pair in the control device
The initial neural network model is trained, and after obtaining the target nerve network model, methods described also includes:
The control device obtains test sample from the sample data;
The control device repeats following step using the target nerve network model as neural network model to be tested
Suddenly, until determining that the neural network model to be tested is the target nerve network model:
The control device is tested the neural network model to be tested by the test sample, is obtained test and is missed
Difference;
The control device judges whether the test error is less than default test error;
In the case where judging that the test error is more than or equal to the default test error, the control device weight
Newly the initial neural network model is trained by the training sample, obtains new neutral net mould to be tested
Type;
In the case where judging that the test error is less than the default test error, treated described in the control device determination
The neural network model of test is the target nerve network model.
6. according to the method for claim 5, it is characterised in that described in the control device obtains from the sample data
Training sample and the test sample is obtained from the sample data include:
The control device is ranked up according to the characteristic parameter of the sample data to the sample data;
The control device extracts the first data as the instruction according to default interval from the sample data after sequence
Practice sample;
The control device obtains the second data in the sample data as the test sample, wherein, second number
According to for the total data in the sample data in addition to the training sample.
7. according to the method for claim 3, it is characterised in that the control device, which obtains the sample data, to be included:
The control device obtains characteristic parameter corresponding to a variety of environmental forms;
The control device determines to make under every kind of environmental form the operational efficiency of the electronic equipment to be higher than default efficiency and energy
Operational factor of the amount loss less than the electronic equipment of default loss;
The control device is labeled to the corresponding relation between the characteristic parameter and the operational factor, obtains original number
According to;
The control device obtains weight from the characteristic parameter and is more than the parameter of default weight as the sample data
Input parameter, wherein, the weight is used to indicate influence degree of the parameter to the running status of electronic equipment, the bigger expression of weight
Influence degree is bigger;
The control device obtains output parameter of the control signal as the sample data corresponding to the operational factor, its
In, the control signal is used to control the electronic equipment to run under the running status indicated by the operational factor;
The control device extracts pair of the input parameter and the output parameter from the corresponding relation of the initial data
It should be related to, obtain the sample data.
8. method according to any one of claim 1 to 7, it is characterised in that
Characteristic parameter includes at least one of:Indoor temperature, outdoor temperature, indoor humidity, outside humidity, regional information, day
User profile in gas information, current environment;
Control signal includes at least one of:Control the signal of compressor rotary speed, the signal of the outer rotation speed of fan of control, control electricity
The signal of sub- expansion valve opening, the signal for controlling inner blower rotating speed, the signal in control wind deflector direction.
9. the control method of a kind of electronic equipment, it is characterised in that including:
Electronic equipment detects the current signature parameter of the electronic equipment, wherein, the current signature parameter is described for indicating
The running environment that electronic equipment is presently in;
The electronic equipment sends the current signature parameter to control device, wherein, the control device is used to pass through mesh
Neural network model is marked to obtain target control signal corresponding with the current signature parameter and send institute to the electronic equipment
Target control signal is stated, the target nerve network model is used for the corresponding relation of indicative character parameter and control signal, described
Target control signal is used to control the electronic equipment to run under target operation state, and the target operation state is described to make
Operational efficiency of the electronic equipment under the running environment being presently in is higher than default efficiency and energy loss is less than default damage
The running status of consumption;
The electronic equipment receives the target control signal that the control device returns;
The electronic equipment responds the target control signal and adjusts the running status of the electronic equipment to target fortune
Row state.
10. according to the method for claim 9, it is characterised in that object run mark is carried in the target control signal
Know, wherein, the object run identifies responds the target for target control signal described in unique mark, the electronic equipment
Control signal, which adjusts the running status of the electronic equipment to the target operation state, to be included:
The electronic equipment adjusts the running status of the electronic equipment to the object run target for identifying instruction
Running status.
11. according to the method for claim 10, it is characterised in that the electronic equipment is by the operation shape of the electronic equipment
State, which is adjusted to the target operation state of object run mark instruction, to be included:
The electronic equipment determines the target operation state according to object run mark, wherein, in the electronic equipment
It is stored with the corresponding relation of operation mark and running status;
The electronic equipment adjusts the running status of the electronic equipment to the target operation state.
12. the control device of a kind of electronic equipment, applied to control device, it is characterised in that including:
First acquisition module, the current signature parameter detected for obtaining electronic equipment, wherein, the current signature parameter is used
In the running environment that the instruction electronic equipment is presently in;
Second acquisition module, for obtaining target control corresponding with the current signature parameter by target nerve network model
Signal, wherein, the target nerve network model is used for the corresponding relation of indicative character parameter and control signal, the target control
Signal processed is used to control the electronic equipment to run under target operation state, and the target operation state is to set the electronics
The standby operational efficiency under the running environment being presently in is higher than default efficiency and energy loss is less than the fortune for presetting loss
Row state;
First sending module, for sending the target control signal to the electronic equipment.
13. the control device of a kind of electronic equipment, applied to electronic equipment, it is characterised in that including:
Detection module, for detecting the current signature parameter of the electronic equipment, wherein, the current signature parameter is used to indicate
The running environment that the electronic equipment is presently in;
Second sending module, for the current signature parameter to be sent to control device, wherein, the control device is used to lead to
Target neural network model is crossed to obtain target control signal corresponding with the current signature parameter and send out to the electronic equipment
The target control signal is sent, the target nerve network model is used for the corresponding relation of indicative character parameter and control signal,
The target control signal is used to control the electronic equipment to run under target operation state, and the target operation state is to make
Operational efficiency of the electronic equipment under the running environment being presently in is higher than default efficiency and energy loss is less than pre-
If the running status of loss;
Receiving module, the target control signal returned for receiving the control device;
Adjusting module, the running status of the electronic equipment is adjusted to target fortune for responding the target control signal
Row state.
14. the control system of a kind of electronic equipment, it is characterised in that including:Control device and electronic equipment, wherein,
The control device, the current signature parameter detected for obtaining electronic equipment, wherein, the current signature parameter is used
In the running environment that the instruction electronic equipment is presently in;Obtained by target nerve network model and joined with the current signature
Target control signal corresponding to number, wherein, the target nerve network model is used for pair of indicative character parameter and control signal
It should be related to, the target control signal is used to control the electronic equipment to run under target operation state, the object run
State is operational efficiency of the electronic equipment under the running environment being presently in is higher than default efficiency and energy damage
Running status of the consumption less than default loss;The target control signal is sent to the electronic equipment;
The electronic equipment, for detecting the current signature parameter of the electronic equipment;The current signature parameter is sent out
Deliver to control device;Receive the target control signal that the control device returns;The target control signal is responded by institute
The running status for stating electronic equipment is adjusted to the target operation state.
A kind of 15. storage medium, it is characterised in that the storage medium includes the program of storage, wherein, when described program is run
Method any one of perform claim requirement 1 to 11.
A kind of 16. processor, it is characterised in that the processor is used for operation program, wherein, right of execution when described program is run
Profit requires the method any one of 1 to 11.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710834272.5A CN107844073B (en) | 2017-09-15 | 2017-09-15 | Control method of electronic device, device, system, storage medium and processor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710834272.5A CN107844073B (en) | 2017-09-15 | 2017-09-15 | Control method of electronic device, device, system, storage medium and processor |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107844073A true CN107844073A (en) | 2018-03-27 |
CN107844073B CN107844073B (en) | 2018-12-07 |
Family
ID=61683283
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710834272.5A Active CN107844073B (en) | 2017-09-15 | 2017-09-15 | Control method of electronic device, device, system, storage medium and processor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107844073B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108776436A (en) * | 2018-06-05 | 2018-11-09 | 南京邮电大学 | Energy management method and system are recognized towards wisdom family |
CN109471370A (en) * | 2018-11-23 | 2019-03-15 | 珠海格力电器股份有限公司 | A kind of behavior prediction and control method based on exhaust fan operation data, system |
CN109634129A (en) * | 2018-11-02 | 2019-04-16 | 深圳慧安康科技有限公司 | Implementation method, system and the device actively shown loving care for |
CN110967976A (en) * | 2018-09-28 | 2020-04-07 | 珠海格力电器股份有限公司 | Control method and device of intelligent home system |
WO2020155661A1 (en) * | 2019-01-28 | 2020-08-06 | 珠海格力电器股份有限公司 | Method for controlling smart household appliance, and smart household appliance and storage medium |
CN111931798A (en) * | 2019-05-13 | 2020-11-13 | 北京绪水互联科技有限公司 | Method for carrying out classification detection and service life prediction of cold head state |
CN116273692A (en) * | 2023-03-14 | 2023-06-23 | 深圳徕科技术有限公司 | Distributed high-speed injection valve combined control method, device, equipment and storage medium |
CN116594313A (en) * | 2023-07-18 | 2023-08-15 | 合肥战聚智能科技有限公司 | Smart home equipment management method, system, equipment and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102997374A (en) * | 2012-12-31 | 2013-03-27 | 深圳市奥宇控制系统有限公司 | Method and device for forecasting air-conditioning load and air-conditioner |
CN104374053A (en) * | 2014-11-25 | 2015-02-25 | 珠海格力电器股份有限公司 | Intelligent control method, device and system |
CN105890109A (en) * | 2016-03-31 | 2016-08-24 | 华南理工大学 | Online long-acting performance detection and optimized running method for room air conditioner |
CN106302041A (en) * | 2016-08-05 | 2017-01-04 | 深圳博科智能科技有限公司 | A kind of intelligent home equipment control method and device |
CN106322656A (en) * | 2016-08-23 | 2017-01-11 | 海信(山东)空调有限公司 | Air conditioner control method, server and air conditioner system |
-
2017
- 2017-09-15 CN CN201710834272.5A patent/CN107844073B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102997374A (en) * | 2012-12-31 | 2013-03-27 | 深圳市奥宇控制系统有限公司 | Method and device for forecasting air-conditioning load and air-conditioner |
CN104374053A (en) * | 2014-11-25 | 2015-02-25 | 珠海格力电器股份有限公司 | Intelligent control method, device and system |
CN105890109A (en) * | 2016-03-31 | 2016-08-24 | 华南理工大学 | Online long-acting performance detection and optimized running method for room air conditioner |
CN106302041A (en) * | 2016-08-05 | 2017-01-04 | 深圳博科智能科技有限公司 | A kind of intelligent home equipment control method and device |
CN106322656A (en) * | 2016-08-23 | 2017-01-11 | 海信(山东)空调有限公司 | Air conditioner control method, server and air conditioner system |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108776436A (en) * | 2018-06-05 | 2018-11-09 | 南京邮电大学 | Energy management method and system are recognized towards wisdom family |
CN110967976A (en) * | 2018-09-28 | 2020-04-07 | 珠海格力电器股份有限公司 | Control method and device of intelligent home system |
CN109634129B (en) * | 2018-11-02 | 2022-07-01 | 深圳慧安康科技有限公司 | Method, system and device for realizing active care |
CN109634129A (en) * | 2018-11-02 | 2019-04-16 | 深圳慧安康科技有限公司 | Implementation method, system and the device actively shown loving care for |
CN109471370A (en) * | 2018-11-23 | 2019-03-15 | 珠海格力电器股份有限公司 | A kind of behavior prediction and control method based on exhaust fan operation data, system |
CN109471370B (en) * | 2018-11-23 | 2020-07-10 | 珠海格力电器股份有限公司 | Behavior prediction and control method and system based on exhaust fan operation data |
WO2020155661A1 (en) * | 2019-01-28 | 2020-08-06 | 珠海格力电器股份有限公司 | Method for controlling smart household appliance, and smart household appliance and storage medium |
CN111931798A (en) * | 2019-05-13 | 2020-11-13 | 北京绪水互联科技有限公司 | Method for carrying out classification detection and service life prediction of cold head state |
CN111931798B (en) * | 2019-05-13 | 2023-05-23 | 北京绪水互联科技有限公司 | Method for classifying and detecting cold head state and predicting service life |
CN116273692A (en) * | 2023-03-14 | 2023-06-23 | 深圳徕科技术有限公司 | Distributed high-speed injection valve combined control method, device, equipment and storage medium |
CN116273692B (en) * | 2023-03-14 | 2023-08-15 | 深圳徕科技术有限公司 | Distributed high-speed injection valve combined control method, device, equipment and storage medium |
CN116594313A (en) * | 2023-07-18 | 2023-08-15 | 合肥战聚智能科技有限公司 | Smart home equipment management method, system, equipment and medium |
CN116594313B (en) * | 2023-07-18 | 2023-10-20 | 合肥战聚智能科技有限公司 | Smart home equipment management method, system, equipment and medium |
Also Published As
Publication number | Publication date |
---|---|
CN107844073B (en) | 2018-12-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107844073A (en) | Control method of electronic device, device, system, storage medium and processor | |
CN107797459A (en) | Control method, device, storage medium and the processor of terminal device | |
CN107883536B (en) | Parameter adjusting method and device of air conditioning equipment and terminal | |
CN107388478A (en) | A kind of intelligent air-conditioner control method and device | |
CN106196433A (en) | A kind of airconditioning control parameter determination device and method, air-conditioning and server | |
CN104728993B (en) | Air-conditioner control method and device | |
CN107655162A (en) | Refrigerant detection method, device, dehumidifier and equipment | |
CN106499656B (en) | A kind of fan wind speed intelligent control method | |
CN109882996A (en) | A kind of method and apparatus of control | |
CN106091247A (en) | Remotely control single-cooling air-conditioner Based Intelligent Control operation method | |
Abagissa et al. | IoT based smart agricultural device controlling system | |
CN106705372A (en) | Energy-saving control method and device for air conditioner | |
CN107676936A (en) | The control method and device of air-conditioning equipment | |
CN111121239B (en) | Intelligent control method and system for intelligent household appliance and intelligent household appliance | |
CN110736248A (en) | Control method and device for air conditioner air outlet temperature | |
CN109268936A (en) | Control method, device, air conditioner and the storage medium of air conditioner | |
CN108259279A (en) | The control method and system of air-conditioning, storage medium, processor | |
CN110736228B (en) | Control method and device of air conditioning equipment, storage medium and air conditioning system | |
CN104990231B (en) | The control method and device of Centralized Controller | |
Siswipraptini et al. | The design of a smart home controller based on ADALINE | |
CN112944624B (en) | Method for air conditioner control and air conditioner | |
Tong et al. | Surrogate model-based energy-efficient scheduling for LPWA-based environmental monitoring systems | |
CN107044711A (en) | The control method and device of air-conditioning | |
CN108036473B (en) | Intelligent temperature and humidity control method and device | |
CN108917101A (en) | Air conditioning control method and device, storage medium, processor |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |