CN109471370A - A kind of behavior prediction and control method based on exhaust fan operation data, system - Google Patents
A kind of behavior prediction and control method based on exhaust fan operation data, system Download PDFInfo
- Publication number
- CN109471370A CN109471370A CN201811406808.4A CN201811406808A CN109471370A CN 109471370 A CN109471370 A CN 109471370A CN 201811406808 A CN201811406808 A CN 201811406808A CN 109471370 A CN109471370 A CN 109471370A
- Authority
- CN
- China
- Prior art keywords
- exhaust fan
- parameter
- behavior prediction
- neural network
- output
- 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
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- 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
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
Abstract
The invention belongs to information technology fields, and in particular to a kind of behavior prediction and control method based on exhaust fan operation data, system, which comprises obtain the historical operating data of exhaust fan；It screens in historical operating data with behavior prediction relevant parameter as input parameter；Using action event and corresponding operating time as output parameter, input-output parameter pair is established；It is trained using the input-output parameter to neural network algorithm；Obtain the behavior prediction model of action event and corresponding operating time as output parameter.The curve that user's usage behavior changes with date and time can effectively be fitted, in conjunction with sensing datas such as air qualities, user can be analyzed and use the use habit of the household appliances such as water heater, to provide accurate judgment basis for user's behavior prediction, it is effective that the user experience is improved, while user enjoys smart home system, cost is saved, estimated performance stability is high, accuracy is high.
Description
Technical field
The invention belongs to Smart Home technical fields, and in particular to a kind of behavior prediction based on exhaust fan operation data and
Control method, system.
Background technique
Smart home be using house as platform, using comprehensive wiring technology, network communication technology, security precautions technology, from
Dynamic control technology, audio and video technology integrate related with home life facility (such as: household electrical appliances), efficient to construct
The management system of housing facilities and family's schedule affairs, promotes the multiple performance of smart home, and realizes the inhabitation of environmental protection and energy saving
Environment.
Smart home needs to embody intelligence, rather than controls household appliance simply by the detection of long-range or sensor.
Exhaust fan is the basic outfit equipment in each family, and usually it is for bathroom discharge fog, peculiar smell etc..Current many exhaust fans
The function of being possessed is more single, can not obtain user behavior information.Common water heater does not all have analysis user's habit
Function, the cost for replacing whole water heater is excessively high, and the exhaust fan manufacturing cost in bathroom is low, and occupied space is fairly small, if will
Exhaust fan increases intelligent function, becomes the important ring in smart home, and it is more using water heater etc. to can be used for analyzing user
The behavioural habits of kind equipment, and then targeted valuable recommendation is provided for user.
User is more regular to the frequency of use of exhaust fan in one day, therefore the use data of exhaust fan can be used for
Analyze the behavior of user.Meanwhile exhaust fan may also be combined with the smart machines such as air quality sensor and fog inductor, for obtaining
Take more accurate environmental information data.By these data, and the proposed algorithm in machine learning is combined to be analyzed, can be use
Family provides valuable information, for example the parameter for recommending to control the operation of other household electrical appliances is arranged according to the preference of each user,
Neural neural network algorithm is combined with smart home, intelligent recommendation is made by the intelligence that can embody smart home system
For a critical function of exhaust fan, allow user that can enjoy Intelligent life.
Summary of the invention
It is more single in order to solve the function that many exhaust fans are possessed at present, user behavior information can not be obtained.It is logical
Normal water heater does not all have the function of analysis user's habit, replaces the excessively high problem of the cost of whole water heater, and the present invention mentions
For a kind of behavior prediction based on exhaust fan operation data and control method, system.
In order to solve the above-mentioned technical problem, the embodiment of the present invention adopts the following technical scheme that
On the one hand, the embodiment of the invention provides a kind of behavior prediction model construction sides based on exhaust fan operation data
Method, which comprises
Obtain the historical operating data of exhaust fan；It screens in historical operating data with behavior prediction relevant parameter as input
Parameter；Using action event and corresponding operating time as output parameter, input-output parameter pair is established；Use the input-
Output parameter is trained to neural network algorithm；Obtain the row of action event and corresponding operating time as output parameter
For prediction model.
It further, include exhaust fan operating parameter and environment with behavior prediction relevant parameter in the historical operating data
Parameter.
Further, according to the input-output parameter to basic structure, the net for primarily determining the neural network algorithm
Network input number of nodes, network output node number, network hidden layer number, Hidden nodes, network initial weight.
Further, the structure of the neural network algorithm by BP network structure, RNN network structure, LSTM network structure,
CNN network structure generates.
Further, the training method is adjusted in real time according to the structure and/or training process of neural network algorithm.
Further, the desired output and reality of neural network algorithm are judged in the neural network algorithm training process
Whether output meets output accuracy, if satisfied, then terminating to train；If not satisfied, then updating input layer in neural network algorithm, hidden
Weight and/or biasing containing layer and output layer.
Further, after the completion of the neural network algorithm training, using the input-output parameter to positive test institute
State neural network algorithm.
Further, judge that the test error is enough to meet the requirements, network training test is completed if meeting；If discontented
Foot, then re -training neural network algorithm.
Second aspect, the embodiment of the invention also provides a kind of behavior prediction model constructions based on exhaust fan operation data
System, the system comprises: data source modules, screening module and algorithm training module, it is described
Data source modules, for obtaining exhaust fan historical operating data；
Screening module will operate thing as input parameter for screening behavior prediction relevant parameter in historical operating data
Part and corresponding operating time as output parameter, establish input-output parameter pair.
Algorithm training module is grasped for being trained using the input-output parameter to neural network algorithm
Make the behavior prediction model of event and corresponding operating time as output parameter.
Further, the algorithm training module includes adjustment unit, for according to the structure of neural network algorithm and/or
Training process carries out real-time adjusting training method.
Further, the algorithm training module includes precision judging unit, for judging the neural network algorithm
Whether desired output and reality output meet output accuracy.
Further, the algorithm training module includes test cell, after the completion of neural network algorithm training,
Use input-output parameter neural network algorithm described in positive test.
Further, the algorithm training module includes error judgment unit, for judging that the test error is enough full
Foot requires.
The third aspect, the embodiment of the invention also provides a kind of control methods of smart home device, which comprises
Obtain exhaust fan with behavior prediction relevant parameter；
Trained behavior prediction model is brought into as input parameter with behavior prediction relevant parameter using in operation data；
Action event and the output parameter of corresponding operating time are obtained, and is sent to controlling terminal.
Fourth aspect, the embodiment of the invention also provides a kind of control methods of smart home device, which comprises
Receive action event and the output parameter of corresponding operating time；
Control instruction is generated according to action event and the output parameter of corresponding operating time；
Control instruction is sent to smart home device, the intelligentized Furniture equipment is controlled and is worked according to control instruction.
5th aspect, the embodiment of the invention also provides a kind of control system of smart home device, the system comprises:
It is described including acquisition device, prediction meanss, controlling terminal and smart home device
Acquisition device is sent to prediction meanss for acquiring exhaust fan operating parameter and environmental parameter, and by acquisition signal；
The prediction meanss, when for going out action event and corresponding operation according to trained behavior prediction model prediction
Between, and prediction result is sent to controlling terminal；
The controlling terminal refers to for controlling to generate to control according to action event and the output parameter of corresponding operating time
It enables；
The smart home device, works according to control instruction.
Further, the smart home device includes air purifier, fumigating machine, dehumidifier, heater, intelligent sound
One of case, smart television are a variety of.
The present invention provides a kind of behavior prediction based on exhaust fan operation data and control method, system have it is beneficial below
Effect: the historical operating data of exhaust fan is obtained；It screens in historical operating data with behavior prediction relevant parameter as input ginseng
Number；Using action event and corresponding operating time as output parameter, input-output parameter pair is established；It is defeated using the input-
Parameter is trained to neural network algorithm out；Obtain the behavior of action event and corresponding operating time as output parameter
Prediction model.The rule of exhaust fan user behavior is analyzed using the neural neural network algorithm under artificial intelligence subject branch,
The moving law of exhaust fan the past period is found by the self study of artificial neural network, adaptive characteristic, and is found
Go existing between value and future value contact.The curve that user's usage behavior changes with date and time can be effectively fitted,
In conjunction with sensing datas such as air qualities, user can be analyzed using the use habit of the household appliances such as water heater, thus
Accurate judgment basis is provided for user's behavior prediction.Exhaust fan is increased into intelligent function, becomes the weight in smart home
A ring is wanted, can be used for analyzing user using the behavioural habits of the plurality of devices such as water heater, and then provides for user and targetedly has
The recommendation of value, effective the user experience is improved, while user enjoys smart home system, has saved cost.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the behavior prediction model building method of exhaust fan operation data in the embodiment of the present invention；
Fig. 2 is a kind of schematic diagram of input-output pair in the embodiment of the present invention；
Fig. 3 is a kind of schematic diagram of neural network algorithm model in the embodiment of the present invention；
Fig. 4 is a kind of BP neural network basic structure schematic diagram in the embodiment of the present invention；
Fig. 5 is a kind of signal of the behavior prediction model construction system based on exhaust fan operation data in the embodiment of the present invention
Figure；
Fig. 6 is a kind of flow chart of the control method of smart home device in the embodiment of the present invention；
Fig. 7 is a kind of flow chart of the control method of smart home device in the embodiment of the present invention；
Fig. 8 is a kind of schematic diagram of the control system of exhaust fan in the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, is clearly and completely retouched to the technical solution in the present invention
It states, it is clear that the described embodiments are merely a part of the embodiments of the present invention, instead of all the embodiments.
The embodiment of the invention discloses a kind of behavior prediction model building method based on exhaust fan operation data, this method
Flow chart it is as shown in Figure 1, comprising:
S101: exhaust fan operation data is obtained；
Obtain exhaust fan operation data, the operation note including daily user's exhaust fan；Specific acquisition modes are included in
Operating parameter under laboratory simulation environment collects the exhaust fan operating parameter etc. when actual user uses by technology of Internet of things
Mode；
S102: with behavior prediction relevant parameter as input parameter in screening historical operating data, by action event and right
The operating time answered as output parameter, establishes input-output parameter pair；
After obtaining exhaust fan operation data, screening behavior prediction relevant parameter is as input parameter, by action event and right
The operating time answered as output parameter, establishes input-output parameter pair, as shown in Figure 2；The behavior prediction relevant parameter packet
Include temperature, humidity, PM2.5, date, time；By the analysis to data and expertise knowledge is combined, is chosen to exhaust fan
The influential parameter of user's behavior prediction is used as output parameter as input parameter, by predicted time point and operation；Input parameter
Including but not limited to following is one or more: temperature, humidity, PM2.5, date, time；Inputting parameter is not only single ginseng
Number also includes the input parameter one or more dimensions array for extracting feature composition according to certain rules；
By the numerical value conversion of prediction at specific operation by obtained input, output parameter pair, a part is used as training book
Sample data, a part are used as test sample data；For example, input parameter is Thursday, at 7 points in evening, temperature is high, humidity is high, empty
Makings amount is low, working day；Output parameter is exhaust fan unlatching, discharge mode, runing time 1 hour；Inputting parameter indicates user
Current environment and moment；Output parameter is then prediction as a result, controlling according to this exhaust fan；
S103: being trained using the input-output parameter to neural network algorithm, and action event and correspondence are obtained
Behavior prediction model of the operating time as output parameter；
According to the input-output parameter to basic structure, the network inputs section for primarily determining the neural network algorithm
Points, network output node number, network hidden layer number, Hidden nodes, network initial weight, the neural network algorithm model is as schemed
Shown in 3；The structure of the neural network algorithm is by BP network structure, RNN network structure, LSTM network structure, CNN network structure
It generates；Wherein, BP neural network basic structure schematic diagram is as shown in Figure 4；According to different ambient temperature and humidities, operating time section etc.
Operation data to exhaust fan and its rule contained can primarily determine the basic structure of network, the input of network, output section
Points, network hidden layer number, Hidden nodes, network initial weight etc.；
Primarily determine the basic structure of network, the input of network, output node number, network hidden layer number, Hidden nodes, network
After the structural parameters such as initial weight, it is trained using the input-output parameter to neural network algorithm, the training side
Method is adjusted in real time according to the structure and/or training process of neural network algorithm；
Judge in the neural network algorithm training process neural network algorithm desired output and reality output whether
Meet output accuracy, if satisfied, then terminating to train；If not satisfied, then updating input layer in neural network algorithm, hidden layer and defeated
The weight of layer and/or biasing out；
For example, defeated according to the reality that the basic structure of network, network initial weight and biasing calculate neural network algorithm
A (x) out, i.e. a (x)=1/ (1+e-z), wherein Z=Wk*x+bl, judge that the desired output y (x) of neural network algorithm and reality are defeated
Whether a (x) meets output accuracy requirement i.e. out: ‖ y (x)-a (x) ‖ < ∈, ∈ is target minimal error, if meeting required precision
Then terminate to train；The weight W of network is updated according to following manner if being unsatisfactory forkWith biasing bl, until the phase of neural network algorithm
Until hoping output y (x) and reality output a (x) whether meet output accuracy requirement, the weight W for updating neural network algorithmk
With biasing blMethod it is as follows:
Wherein, C (w, b) is error energy function (by taking standard variance function as an example), and n is the total quantity of training sample, is asked
Be to be carried out on total training sample x；
Wherein: WkFor initial weight,It is error energy function to the partial derivative of weight；
Wherein: blFor initial bias,It is error energy function to the partial derivative of biasing；
After the completion of the neural network algorithm training, input-output parameter nerve net described in positive test is used
Network algorithm；Judge that the test error is enough to meet the requirements, network training test is completed if meeting；If not satisfied, then again
Training neural network algorithm；
Trained neural network algorithm is exported and obtains action event and corresponding operating time as output parameter
Behavior prediction model.
The embodiment of the invention discloses a kind of the behavior prediction model construction system based on exhaust fan operation data, the system
Schematic diagram as shown in figure 5, the system comprises data source modules 11, screening module 12 and algorithm training module 13,
The data source modules 11, for obtaining exhaust fan historical operating data；The exhaust fan operation data includes every
The operation note of it user's exhaust fan；Specific acquisition modes include the operating parameter under laboratory simulation environment, pass through object
Networking technology collects the modes such as exhaust fan operating parameter when actual user uses；
The screening module 12, will as input parameter for screening behavior prediction relevant parameter in historical operating data
Action event and corresponding operating time as output parameter, establish input-output parameter pair；
The algorithm training module 13, for being trained using the input-output parameter to neural network algorithm,
Obtain the behavior prediction model of action event and corresponding operating time as output parameter；The algorithm training module 12 includes
Adjustment unit 121, precision judging unit 122, test cell 123 and error judgment unit 124, the adjustment unit 121 are used for
Real-time adjusting training method is carried out according to the structure of neural network algorithm and/or training process；The precision judging unit 122 is used
Whether meet output accuracy in the desired output and reality output for judging the neural network algorithm；The test cell 123 is used
After the completion of neural network algorithm training, input-output parameter neural network algorithm described in positive test is used；
The error judgment unit 124 is for judging that the test error is enough to meet the requirements.
The embodiment of the invention discloses a kind of control methods of smart home device, are applied to analysing terminal, this method
Flow chart is as shown in Figure 6, which comprises
S201: obtain exhaust fan with behavior prediction relevant parameter；
Acquisition exhaust fan operating parameter and current environment parameter in real time after acquiring data, screen behavior prediction relevant parameter
As input parameter, the behavior prediction relevant parameter includes temperature, humidity, PM2.5, date, time；The input parameter packet
Include single parameter, one-dimension array or Multidimensional numerical；
S202: trained behavior prediction mould is brought into as input parameter with behavior prediction relevant parameter using in operation data
Type；
Using in operation data with behavior prediction relevant parameter as input parameter, input parameter is inputted into trained behavior
In prediction model, usage behavior prediction model is fitted anticipation function to discrete point, then predicts future value, will be in prediction future value
Action event and the corresponding operating time as output parameter；
S203: action event and the output parameter of corresponding operating time will be obtained, and is sent to controlling terminal；
It will be according to the action event obtained with behavior prediction relevant parameter and corresponding operating time for obtaining exhaust fan
Output parameter is sent to controlling terminal；
The analysing terminal includes but is not limited to wireless communication module, router, server, smart phone etc..
The embodiment of the invention discloses a kind of control methods of smart home device, are applied to controlling terminal, this method
Flow chart is as shown in Figure 7, which comprises
S301: action event and the output parameter of corresponding operating time are received, according to action event and corresponding operation
The output parameter of time generates control instruction；
Controlling terminal is received according to the action event of exhaust fan obtained with behavior prediction relevant parameter and corresponding behaviour
Make the output parameter of time；Control instruction is generated according to action event and the output parameter of corresponding operating time；The behavior
Predict that relevant parameter includes temperature, humidity, PM2.5, date, time；
S302: being sent to smart home device for control instruction, controls the intelligentized Furniture equipment according to control instruction work
Make；
Control instruction is sent to smart home device by controlling terminal, controls the intelligentized Furniture equipment according to control instruction
Work；The intelligentized Furniture equipment carries out sending prompting message according to the predicting strategy；The prompting message includes that voice disappears
Breath, message push；The intelligentized Furniture equipment includes air purifier, fumigating machine, dehumidifier, heater, intelligent sound box, intelligence
TV；
The intelligent terminal includes but is not limited to wireless communication module, router, server, smart phone etc..
The embodiment of the invention discloses a kind of control system of smart home device, the schematic diagram of the system as shown in figure 8,
The system comprises: acquisition device 21, prediction meanss 22, controlling terminal 23 and smart home device 24,
The acquisition device 21, for acquiring exhaust fan operating parameter and environmental parameter, and will acquisition signal be sent to it is pre-
Survey device；
The prediction meanss 22, for going out action event and corresponding operation according to trained behavior prediction model prediction
Time, and prediction result is sent to controlling terminal；As defeated after the data processing that prediction meanss 22 acquire acquisition device 21
Enter parameter to input in trained behavior prediction model, when converting action event and corresponding operation for the output parameter of acquisition
Between；Prediction meanss 22 will input parameter and input in trained neural network algorithm, quasi- to discrete point using neural network algorithm
Anticipation function is closed, then predicts future value, will predict that the action event in future value and corresponding operating time join as output
Number, and prediction result is converted by the output parameter of acquisition, and prediction result is sent to controlling terminal 23；
The controlling terminal 23 generates control according to action event and the output parameter of corresponding operating time for controlling
Instruction；
The smart home device 24 works according to the control instruction that controlling terminal 23 is sent；The smart home
Equipment includes one of air purifier, fumigating machine, dehumidifier, heater, intelligent sound box, smart television or a variety of.
It above are only preferred embodiment of the invention, but the design concept of the present invention is not limited to this, all benefits
It is made a non-material change to the present invention, should all be belonged to behavior that violates the scope of protection of the present invention with this design.
Claims (17)
1. a kind of behavior prediction model building method based on exhaust fan operation data, which is characterized in that the described method includes:
Obtain the historical operating data of exhaust fan；
It screens in historical operating data with behavior prediction relevant parameter as input parameter；
Using action event and corresponding operating time as output parameter, input-output parameter pair is established；
It is trained using the input-output parameter to neural network algorithm；
Obtain the behavior prediction model of action event and corresponding operating time as output parameter.
2. a kind of behavior prediction model building method based on exhaust fan operation data according to claim 1, feature
It is: with behavior prediction relevant parameter includes exhaust fan operating parameter and environmental parameter in the historical operating data.
3. a kind of behavior prediction model building method based on exhaust fan operation data according to claim 1, feature
It is: according to the input-output parameter to basic structure, the network inputs node for primarily determining the neural network algorithm
Number, network output node number, network hidden layer number, Hidden nodes, network initial weight.
4. a kind of behavior prediction model building method based on exhaust fan operation data according to claim 1, feature
Be: the structure of the neural network algorithm is by BP network structure, RNN network structure, LSTM network structure, CNN network structure
It generates.
5. a kind of behavior prediction model building method based on exhaust fan operation data according to claim 4, feature
Be: the training method is adjusted in real time according to the structure and/or training process of neural network algorithm.
6. a kind of behavior prediction model building method based on exhaust fan operation data according to claim 5, feature
It is: judges whether the desired output of neural network algorithm meets with reality output in the neural network algorithm training process
Output accuracy, if satisfied, then terminating to train；If not satisfied, then updating input layer in neural network algorithm, hidden layer and output layer
Weight and/or biasing.
7. a kind of behavior prediction model building method based on exhaust fan operation data according to claim 1, feature
It is: after the completion of the neural network algorithm training, is calculated using input-output parameter neural network described in positive test
Method.
8. a kind of behavior prediction model building method based on exhaust fan operation data according to claim 7, feature
It is: judges that the test error is enough to meet the requirements, network training test is completed if meeting；If not satisfied, then instructing again
Practice neural network algorithm.
9. a kind of behavior prediction model construction system based on exhaust fan operation data, which is characterized in that the system comprises: number
It is described according to source module, screening module and algorithm training module
Data source modules, for obtaining exhaust fan historical operating data；
Screening module, for screening in historical operating data behavior prediction relevant parameter as input parameter, by action event and
The corresponding operating time as output parameter, establishes input-output parameter pair.
Algorithm training module obtains operation thing for being trained using the input-output parameter to neural network algorithm
The behavior prediction model of part and corresponding operating time as output parameter.
10. a kind of behavior prediction model construction system based on exhaust fan operation data according to claim 9, feature
Be: the algorithm training module includes adjustment unit, for being carried out according to the structure and/or training process of neural network algorithm
Real-time adjusting training method.
11. a kind of behavior prediction model construction system based on exhaust fan operation data according to claim 9, feature
Be: the algorithm training module includes precision judging unit, for judging the desired output and reality of the neural network algorithm
Whether border output meets output accuracy.
12. a kind of behavior prediction model construction system based on exhaust fan operation data according to claim 9, feature
Be: the algorithm training module includes test cell, after the completion of neural network algorithm training, using described defeated
Enter-output parameter neural network algorithm described in positive test.
13. a kind of behavior prediction model construction system based on exhaust fan operation data according to claim 12, special
Sign is: the algorithm training module includes error judgment unit, for judging that the test error is enough to meet the requirements.
14. a kind of control method of smart home device, which is characterized in that the described method includes:
Obtain exhaust fan with behavior prediction relevant parameter；
Trained behavior prediction model is brought into as input parameter with behavior prediction relevant parameter using in operation data；
Action event and the output parameter of corresponding operating time are obtained, and is sent to controlling terminal.
15. a kind of control method of smart home device, which is characterized in that the described method includes:
Receive action event and the output parameter of corresponding operating time；
Control instruction is generated according to action event and the output parameter of corresponding operating time；
Control instruction is sent to smart home device, the intelligentized Furniture equipment is controlled and is worked according to control instruction.
16. a kind of control system of smart home device, which is characterized in that the system comprises: including acquisition device, prediction dress
It sets, controlling terminal and smart home device, it is described
Acquisition device is sent to prediction meanss for acquiring exhaust fan operating parameter and environmental parameter, and by acquisition signal；
The prediction meanss, for going out action event and corresponding operating time according to trained behavior prediction model prediction,
And prediction result is sent to controlling terminal；
The controlling terminal generates control instruction according to action event and the output parameter of corresponding operating time for controlling；
The smart home device, works according to control instruction.
17. a kind of control system of exhaust fan according to claim 16, it is characterised in that: the smart home device packet
Include one of air purifier, fumigating machine, dehumidifier, heater, intelligent sound box, smart television or a variety of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811406808.4A CN109471370B (en) | 2018-11-23 | 2018-11-23 | Behavior prediction and control method and system based on exhaust fan operation data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811406808.4A CN109471370B (en) | 2018-11-23 | 2018-11-23 | Behavior prediction and control method and system based on exhaust fan operation data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109471370A true CN109471370A (en) | 2019-03-15 |
| CN109471370B CN109471370B (en) | 2020-07-10 |
Family
ID=65674047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811406808.4A Active CN109471370B (en) | 2018-11-23 | 2018-11-23 | Behavior prediction and control method and system based on exhaust fan operation data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109471370B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705799A (en) * | 2019-10-10 | 2020-01-17 | 北京小米移动软件有限公司 | Method, device and medium for intelligently prompting combing and washing related information |
| CN110748941A (en) * | 2019-10-16 | 2020-02-04 | 佛山市云米电器科技有限公司 | Method and system for self-defining use mode of intelligent bathroom heater |
| CN110824944A (en) * | 2019-11-22 | 2020-02-21 | 珠海格力电器股份有限公司 | Sleep behavior information prediction method and system based on intelligent household equipment |
| CN111007731A (en) * | 2019-11-11 | 2020-04-14 | 珠海格力电器股份有限公司 | User operation prediction method and device, electronic equipment and readable storage medium |
| CN111797980A (en) * | 2020-07-20 | 2020-10-20 | 房健 | Self-adaptive learning method for personalized floor heating use habits |
| WO2021204117A1 (en) * | 2020-04-07 | 2021-10-14 | 佛山市顺德区美的洗涤电器制造有限公司 | Household appliance control method, household appliance, and computer-readable storage medium |
| CN117216505A (en) * | 2023-11-09 | 2023-12-12 | 广州视声智能股份有限公司 | User habit prediction method and system based on smart home use record |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133427A (en) * | 2013-05-03 | 2014-11-05 | 于庆广 | Intelligent household control method and system |
| CN104855249A (en) * | 2015-05-21 | 2015-08-26 | 赵致钧 | Modularized automatic control system and method thereof |
| CN105259957A (en) * | 2015-10-19 | 2016-01-20 | 珠海格力电器股份有限公司 | Control method capable of linkage control of household appliances and controller |
| CN107730425A (en) * | 2017-09-11 | 2018-02-23 | 深圳市易成自动驾驶技术有限公司 | Carbon emission amount computational methods, device and storage medium |
| CN107844073A (en) * | 2017-09-15 | 2018-03-27 | 珠海格力电器股份有限公司 | Control method of electronic device, device, system, storage medium and processor |
| CN107860099A (en) * | 2017-09-15 | 2018-03-30 | 珠海格力电器股份有限公司 | Frosting detection method, device, storage medium and the equipment of a kind of air-conditioning |
| CN108194398A (en) * | 2017-12-29 | 2018-06-22 | 青岛海信医疗设备股份有限公司 | Control method for fan and device |
-
2018
- 2018-11-23 CN CN201811406808.4A patent/CN109471370B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133427A (en) * | 2013-05-03 | 2014-11-05 | 于庆广 | Intelligent household control method and system |
| CN104855249A (en) * | 2015-05-21 | 2015-08-26 | 赵致钧 | Modularized automatic control system and method thereof |
| CN105259957A (en) * | 2015-10-19 | 2016-01-20 | 珠海格力电器股份有限公司 | Control method capable of linkage control of household appliances and controller |
| CN107730425A (en) * | 2017-09-11 | 2018-02-23 | 深圳市易成自动驾驶技术有限公司 | Carbon emission amount computational methods, device and storage medium |
| CN107844073A (en) * | 2017-09-15 | 2018-03-27 | 珠海格力电器股份有限公司 | Control method of electronic device, device, system, storage medium and processor |
| CN107860099A (en) * | 2017-09-15 | 2018-03-30 | 珠海格力电器股份有限公司 | Frosting detection method, device, storage medium and the equipment of a kind of air-conditioning |
| CN108194398A (en) * | 2017-12-29 | 2018-06-22 | 青岛海信医疗设备股份有限公司 | Control method for fan and device |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705799A (en) * | 2019-10-10 | 2020-01-17 | 北京小米移动软件有限公司 | Method, device and medium for intelligently prompting combing and washing related information |
| CN110748941A (en) * | 2019-10-16 | 2020-02-04 | 佛山市云米电器科技有限公司 | Method and system for self-defining use mode of intelligent bathroom heater |
| CN111007731A (en) * | 2019-11-11 | 2020-04-14 | 珠海格力电器股份有限公司 | User operation prediction method and device, electronic equipment and readable storage medium |
| CN110824944A (en) * | 2019-11-22 | 2020-02-21 | 珠海格力电器股份有限公司 | Sleep behavior information prediction method and system based on intelligent household equipment |
| WO2021204117A1 (en) * | 2020-04-07 | 2021-10-14 | 佛山市顺德区美的洗涤电器制造有限公司 | Household appliance control method, household appliance, and computer-readable storage medium |
| CN111797980A (en) * | 2020-07-20 | 2020-10-20 | 房健 | Self-adaptive learning method for personalized floor heating use habits |
| CN117216505A (en) * | 2023-11-09 | 2023-12-12 | 广州视声智能股份有限公司 | User habit prediction method and system based on smart home use record |
| CN117216505B (en) * | 2023-11-09 | 2024-03-19 | 广州视声智能股份有限公司 | User habit prediction method and system based on smart home use record |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109471370B (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109471370A (en) | A kind of behavior prediction and control method based on exhaust fan operation data, system | |
| Zhou et al. | Multi-population parallel self-adaptive differential artificial bee colony algorithm with application in large-scale service composition for cloud manufacturing | |
| CN106482502B (en) | The intelligence drying long-range control method and system recommended based on cloud platform big data | |
| US11669059B2 (en) | Autonomous and semantic optimization approach for real-time performance management in a built environment | |
| Dong et al. | A learner based on neural network for cognitive radio | |
| Ahmadi-Karvigh et al. | Intelligent adaptive automation: A framework for an activity-driven and user-centered building automation | |
| CN105005204A (en) | Intelligent engine system capable of automatically triggering intelligent home and intelligent life scenes and method | |
| Van Segbroeck et al. | Learning to coordinate in complex networks | |
| Al-Daraiseh et al. | Multi-agent system for energy consumption optimisation in higher education institutions | |
| WO2016147298A1 (en) | Recommendation device, recommendation method, and computer program | |
| CN115826428A (en) | Control method and device of household equipment, storage medium and electronic device | |
| Lachhab et al. | Context-driven monitoring and control of buildings ventilation systems using big data and Internet of Things–based technologies | |
| Abusukhon | Toward achieving a balance between the user satisfaction and the power conservation in the internet of things | |
| CN110793166A (en) | Configuration parameter determination method and device for air purifier | |
| CN110738120A (en) | Environment data adjusting method and device, electronic equipment and medium | |
| Yan et al. | Occupant behavior impact in buildings and the artificial intelligence-based techniques and data-driven approach solutions | |
| Lee | Modeling multiple occupant behaviors in buildings for increased simulation accuracy: An agent-based modeling approach | |
| Albataineh et al. | DEVS-Based IoT Management System for Modeling and Exploring Smart Home Devices | |
| Schachinger et al. | Adaptive learning-based time series prediction framework for building energy management | |
| Schulz et al. | A network approach to consumption | |
| CN108292122A (en) | The communication between distributed information agency in data and energy storage Internet architecture | |
| Mayerhoffer et al. | A Network Approach to Consumption | |
| CN112364936A (en) | Greenhouse control method, device and equipment based on artificial intelligence and storage medium | |
| Das et al. | Segmentation analysis in human centric cyber-physical systems using graphical lasso | |
| Calis et al. | A Methodology to Develop a User-Behaviour Tool to Optimize Building Users’ Comfort and Energy Use |
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 |