CN104579873B - The method and system being controlled to intelligent home device - Google Patents
The method and system being controlled to intelligent home device Download PDFInfo
- Publication number
- CN104579873B CN104579873B CN201510040534.1A CN201510040534A CN104579873B CN 104579873 B CN104579873 B CN 104579873B CN 201510040534 A CN201510040534 A CN 201510040534A CN 104579873 B CN104579873 B CN 104579873B
- Authority
- CN
- China
- Prior art keywords
- control
- mapping
- self
- information
- conclusion
- 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.)
- Active
Links
Landscapes
- Selective Calling Equipment (AREA)
Abstract
The invention discloses the method and system being controlled to intelligent home device, wherein, this method includes：User terminal receives the burst control information of user's input, and burst control information and household identification are sent into server；Server is parsed to burst control information, is obtained the self-defined control mapping comprising condition and conclusion, is synchronized to controller corresponding with household identification；Controller carries out machine learning to the history control information of intelligent home device, obtains the machine learning control mapping comprising condition and conclusion；And the self-defined control mapping from server is received, equipment control command is determined based on machine learning control mapping and self-defined control mapping, intelligent home device is controlled according to equipment control command.The present invention program can make the control to intelligent home device more intelligent.
Description
Technical field
The present invention relates to intelligent control technology, more particularly to the method and system being controlled to intelligent home device.
Background technology
Current smart home field, frequently with technology of Internet of things by a range of various intelligent home devices (such as
Audio ＆ video equipment, illuminator, curtain equipment, air-conditioning equipment, safety-protection system, Digital Theater System, network home appliance and three tables
Make a copy for system etc.) connect together, each intelligent home device is controlled by intelligent home control device, including family is provided
Electric control, Lighting control, curtain control, remote control using telephone, indoor and outdoor remote control, burglar alarm, environmental monitoring, HVAC control,
A variety of functions such as infrared forwarding and programmable Timer control and means.The certain limit is, for example, home-ranges, office model
Enclose.
Compared with common household equipment, intelligent home device not only have traditional inhabitation function, also have both network service,
Information household appliances, equipment automatization, efficient, comfortable, the safe and convenient, ring that also offer collecting system, structure, service, management are integrated
The living environment of guarantor, can carry out comprehensive information exchange.Just can be to each intelligent home device by the controller of smart home
It is controlled, it is easy to operate, optimize the life style of people, help people effectively to arrange the time, strengthen the safety of life staying idle at home
Property.
How effectively to integrate, manage these intelligent home devices as a whole, be that can realize a core of smart home,
Exactly this core has expedited the emergence of the birth of many Intelligent housing schemes.
In terms of the automated execution that the intellectuality of Intelligent housing scheme of today is mainly reflected in.Usual way is
By the record of user's operation behavior, the behavioural habits and pattern of user are found by machine learning method, so that according to user
Model carrys out the operation of Automated condtrol intelligent home device.This method can record operation of the user every time to intelligent home device and believe
Breath, then calls ARM learning controllers to learn the behavior pattern of user, finds the behavioural habits of user；So that afterwards
In running, the behavior pattern that can learn according to these performs corresponding actions, the cumbersome stent of liberation user automatically
The operation of formula.
To sum up, existing scheme can only carry out automatic management based on operation behavior record to intelligent home device, but can not
The burst demand or abnormal conditions of user is handled, causes intelligent performance not high.
The content of the invention
The invention provides a kind of method being controlled to intelligent home device, this method can make to set smart home
Standby control is more intelligent.
The invention provides a kind of system being controlled to intelligent home device, the system can make to set smart home
Standby control is more intelligent.
A kind of method being controlled to intelligent home device, this method includes：
User terminal receives the burst control information of user's input, and burst control information and household identification are sent into service
Device；
Server is parsed to burst control information, obtains the self-defined control mapping comprising condition and conclusion, synchronous
To controller corresponding with household identification；
Controller carries out machine learning to the history control information of intelligent home device, obtains the machine comprising condition and conclusion
Device study control mapping；And the self-defined control mapping from server is received, mapped and self-defined based on machine learning control
Equipment control command is determined in control mapping, and intelligent home device is controlled according to equipment control command.
A kind of system being controlled to intelligent home device, the system includes user terminal, server and controller；
The user terminal, receives the burst control information of user's input, burst control information and household identification is sent to
The server；
The server, receives burst control information and household identification from the client, to burst control information
Parsed, obtain the self-defined control mapping comprising condition and conclusion, be synchronized to controller corresponding with household identification；
The controller, machine learning is carried out to the history control information of intelligent home device, obtains including condition and knot
The machine learning control mapping of opinion；The self-defined control mapping from server is received, based on machine learning control mapping and certainly
Equipment control command is determined in definition control mapping, and intelligent home device is controlled according to equipment control command.
From such scheme as can be seen that in the present invention, user terminal receives the burst control information of user's input, burst is controlled
Information processed and household identification are sent to server；Server is parsed to burst control information, obtains including condition and conclusion
Self-defined control mapping, be synchronized to controller corresponding with household identification；Controller is controlled the history of intelligent home device
Information carries out machine learning, obtains the machine learning control mapping comprising condition and conclusion；Receive from the self-defined of server
Control mapping, determines equipment control command, according to equipment control based on machine learning control mapping and self-defined control mapping
Order is controlled to intelligent home device.The present invention obtains the burst control information of user's input, is considering history control letter
On the basis of breath, intelligent home device is controlled with reference to burst control information, so that, realize the control to intelligent home device
System is more flexible, intelligent.
Brief description of the drawings
The method indicative flowchart that Fig. 1 is controlled for the present invention to intelligent home device；
The method flow diagram example that Fig. 2 is inputted and parsed to burst control for the present invention；
Fig. 3 is the method flow diagram example that controller of the present invention carries out intelligent home device control；
The system structure diagram that Fig. 4 is controlled for the present invention to intelligent home device.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, with reference to embodiment and accompanying drawing, to this
Invention is further described.
The present invention obtains the burst control information of user's input, on the basis of history control information is considered, with reference to burst
Control information is controlled to intelligent home device, so that, realize that the control to intelligent home device is more flexible, intelligent.
It is the method indicative flowchart that the present invention is controlled to intelligent home device, it comprises the following steps referring to Fig. 1：
Step 101, user terminal receives the burst control information of user's input, and burst control information and household identification are sent
To server.
Burst control information is some burst demands or abnormal conditions, and for example, bright rear two days (1.22-1.23) goes on business.
Each domestic installation one family mark, the burst control information of user's input correspondence household identification.
When implementing, burst control information can be inputted according to the template that pre-sets, for example input time and right respectively
The event answered.
The mode of user's input burst control information is not limited, including text message, voice messaging etc..For burst control
Information allows the situation of various ways, can use and implement as follows：User terminal judged the burst control information of reception,
If text message, then server is transmitted directly to, if being not text message, burst control information is converted into text
Information, is sent to server.
Step 102, server is parsed to burst control information, is obtained the self-defined control comprising condition and conclusion and is reflected
Penetrate, be synchronized to controller corresponding with household identification.
Self-defined control mapping includes condition and conclusion, that is to say, conclusion is set up when meeting condition.Gone on business within two days afterwards with bright
Example illustrate, its condition be date 1.22-1.23, conclusion for close parlor lamp.
Step 103, controller carries out machine learning to the history control information of intelligent home device, obtain comprising condition and
The machine learning control mapping of conclusion；And the self-defined control mapping from server is received, control to map based on machine learning
Equipment control command is determined with self-defined control mapping, intelligent home device is controlled according to equipment control command.
Further, before being controlled intelligent home device according to equipment control command, equipment can also be controlled to order
Order feeds back to user and confirmed, specifically：
Equipment control command is showed into user, is indicated if receiving the mandate from user, performs the basis
The step of equipment control command is controlled to intelligent home device., can if being not received by the mandate from user to indicate
Performed in the way of acquiescence；Default behavior can voluntarily be set, and could be arranged to perform equipment control command, it can also be provided that
Refusal performs equipment control command.Receive after the mandate instruction from user, it can also be preserved, for execution next time
Carry out subsequent operation is directly transferred during equipment control command.
The present invention determines equipment control command based on machine learning control mapping and self-defined control mapping, so,
Consider on the basis of history control information, intelligent home device is controlled with reference to burst control information so as to intelligent family
The control for occupying equipment is more flexible, intelligent.
Mapping and self-defined control mapping is controlled to determine the concrete scheme of equipment control command based on machine learning, can root
According to needing to be configured, citing below is illustrated.
Scheme one,
Controller obtains environment sensing information, judges whether environment sensing information meets machine learning control mapping and make by oneself
Condition in justice control mapping, if it is, judging that machine learning controls the conclusion checking item in mapping and self-defined control to reflect
Whether the conclusion penetrated is consistent, if unanimously, the conclusion of machine learning control mapping is set up, and generates equipment control instruction.Work as ring
When border perception information meets the condition in machine learning control mapping and self-defined control mapping, with machine learning control mapping
Corresponding conclusion verifies as checking item to the conclusion, judges that the conclusion in machine learning control mapping verifies item and certainly
Whether the conclusion of definition control mapping is consistent, if unanimously, being set up as the conclusion of checking item, generating setting on the conclusion
Standby control command.The project of environment sensing information can voluntarily be set, for example, time, brightness value etc..
Scheme two,
Environment sensing information is obtained, judges whether environment sensing information meets machine learning control mapping and self-defined control
Condition in mapping, if it is, judging the conclusion checking item in machine learning control mapping and the knot of self-defined control mapping
By whether consistent, if unanimously, the conclusion of machine learning control mapping is set up, and generates equipment control instruction, is sent to described
Actuator；If it is inconsistent, comparing the confidence level of machine learning control mapping and self-defined control mapping, confidence level is determined
Big control mapping, extracts the conclusion in the control mapping determined, generates the equipment control instruction on extracted conclusion.
Scheme two is that machine learning control mapping and self-defined control mapping set confidence level respectively, in environment sensing information
The condition in machine learning control mapping and self-defined control mapping is met, but machine learning control mapping and self-defined control are reflected
When the conclusion penetrated is inconsistent, conclusion is chosen according to confidence level, control instruction is generated.
Scheme one and scheme two are two relatively good implementations, however it is not limited to both schemes.For example, for scheme
Two, the control mapping in machine learning control mapping and self-defined control mapping can also be chosen in advance according to confidence level, then
Whether set up in conjunction with environment sensing information and the control mapping judgement conclusion of selection, equipment control command is generated during establishment.
In order to improve precise control, further, controller is periodically detected to self-defined control mapping, is deleted and is lost
The self-defined control mapping of effect.It is 7 days for example to set the periodic scanning cycle, and then the condition for self-defined control mapping is carried out
Judge, if the setting of time correlation, such as " 12.10-12.12->Close parlor lamp ", but scanning when time
Through being the time after 12.12, then it represents that this mapping can not be enabled again, then the expired mapping of this condition needs
Delete..
Below by Fig. 2,3 flow, the present invention program is illustrated.
Be the method flow diagram example that the present invention is inputted and parsed to burst control referring to Fig. 2, this method including with
Lower step：
Step 201, user terminal receives the burst control information of user's input, if the burst control information of input is voice
Information, then be converted to text message, performs step 202；If the burst control information of input is text message, directly perform
Step 202.
User terminal provides software operation pages to user, and user directly can be controlled on software to the equipment in family
System, can also be switched to abnormal inputting interface, input the abnormal demand of user, can be phonetic entry or text input, so
The input information transfer of user is parsed to server by network afterwards.
Step 202, burst control information and household identification are sent to server by user terminal.
User terminal can be the equipment that mobile phone, computer etc. can carry out network connection, and user terminal carries out network with server
Connection, logs in Intelligent housing webpage, according to webpage prompting input burst control information and corresponding household identification.
Step 203, server is parsed to burst control information, is obtained the self-defined control comprising condition and conclusion and is reflected
Penetrate.
This step can be parsed using the interpretive model of sets itself to burst control information, obtain correspondence burst control
The self-defined control mapping of information.This step can be realized using 2013-2033 scheme：
Step 2031, server is analyzed burst control information, extracts Time And Event therein.
This step carries out natural language analysis, extraction time and time to burst control information.Such as burst control information
Two days (1.22-1.23) goes on business after bright, then the time extracted is 1.22-1.23, and event is to go on business.
Step 2032, server inquires corresponding control in commonsense knowledge base according to event and required.
Commonsense knowledge base stores general knowledge, the control requirement comprising correspondence event.Exemplified by going on business, commonsense knowledge base
Defined in event of going on business, the expression people that goes on business stayed out, it is necessary to close controlled intelligent home device, then corresponding control is required
To close controlled plant.
Step 2033, intelligent home device information corresponding with corresponding household identification is inquired from customer equipment storehouse, is tied
Close intelligent home device information, time and control to require, the self-defined control mapping of generation correspondence intelligent home device, in rule
Self-defined control mapping is stored in thesaurus.
The intelligent home device information of each household identification of customer equipment library storage correspondence；Based on the smart home inquired
Facility information is the self-defined control mapping of each intelligent home device generation, if multiple intelligent home devices, is then generated many
The self-defined control mapping of bar.In this example, it is assumed that the time is 1.22-1.23, control to require to close, then the self-defined control generated
System be mapped as " period->Close intelligent home device N "；Period therein namely condition, when the time meets 1.22-1.23,
Conclusion " closes intelligent home device N " to set up.
Self-defined control mapping is alternatively referred to as custom rule.
Step 204, self-defined control mapping is synchronized to controller corresponding with household identification by server.
In the family, intelligent home device is controlled by controller.Server is reflected self-defined control by network
Penetrate and be synchronized to corresponding controller.
It is the method flow diagram example that controller of the present invention carries out intelligent home device control referring to Fig. 3, this method includes
Following steps：
Step 301, controller carries out machine learning to the history control information of intelligent home device, obtain comprising condition and
The machine learning control mapping of conclusion.
Controller have recorded the history control information of user's operation behavior, and the behavior of user is found by machine learning method
Custom and pattern, obtain machine learning control mapping.Machine learning is carried out to history control information, machine learning mapping pass is obtained
System, is prior art, seldom repeats here.
Machine learning can be periodically carried out.
Machine learning control mapping storage is mapped in thesaurus to family.
Step 302, controller receives the self-defined control mapping from server, based on machine learning control mapping and certainly
Definition control mapping carries out inference engine, determines equipment control command.
This step may particularly include：Controller obtains environment sensing information, judges whether environment sensing information meets machine
Condition in study control mapping and self-defined control mapping, if it is, judging that the conclusion in machine learning control mapping is tested
Item is demonstrate,proved whether consistent with the conclusion that self-defined control maps, if unanimously, generating the conclusion that mapping is controlled on machine learning
Equipment control instruction；If it is inconsistent, conclusion is invalid.
Assuming that there is one to be mapped as in the mapping that machine learning is obtained：" the if times are 7 points, the brightness of and parlors<th,then
Open parlor lamp "；It is self-defined to control to be mapped as " the if times are 2014.9.9-2014.9.10, and then is without opening parlor lamp ".
When reckoning based on such mapping, environment sensing information includes time and ambient brightness；When environment sensing information is full
(time is met during first mapping of foot for and parlor brightness at 7 points<Th), the conclusion for needing to open parlor lamp will be drawn, but
Be if simultaneously the time also meet Article 2 mapping when, can draw again without open parlor lamp conclusion, now conflict,
Inference engine can not provide conclusion, also result in intelligence system and occur exception, it is impossible to normal work.In order to solve this problem,
This example introduces general knowledge skill of deduction and calculation, and the method that general knowledge is calculated has a lot, and a kind of feasible method is to use Default
Logic, carries out basic introduction, with the description features of the present invention more visualized to Default Logic below.
Shown in Default Logic general principle equation below：
(α(x):β(x))/γ(x)
If if the understanding of the formula is α (x) establishments, and β (x) can meet uniformity under the present circumstances, then
Conclusion γ (x) is set up；It is, environment sensing information all meets the bar in machine learning control mapping and self-defined control mapping
Part (i.e. α (x) is set up, and the α (x) each mapped is different under normal circumstances), and the conclusion checking in machine learning control mapping
, i.e. β (x), with it is self-defined control mapping conclusion it is consistent, then machine learning control mapping conclusion establishment (i.e. γ (x) into
It is vertical).That is on the basis of routinely calculating, it is necessary to first do consistency checking before drawing a conclusion.
, there is a Default Theory in correspondence Default Logic<D,W>, what W was represented is stable still endless
Whole World Affairs, extension W that D is represented and the rational rule that defines, but these rules are defeasible.Correspond to this hair
In the case of bright, it is environment sensing information that W is corresponding, and self-defined control mapping；D corresponding is obtained by machine learning
Machine learning control mapping.Machine learning control mapping in D is required for being updated to the form for meeting above-mentioned formula, a letter
Single method is exactly that β (x) and γ (x) are identical, i.e., " A/B " is updated to " A:B/B”；A is the condition in mapping, " A:In B/B "
First B is the conclusion checking item in mapping, " A:Second B in B/B " is conclusion.When inference engine makes inferences
Wait, the A in the condition A in mapping, and mapping is met if based on environment sensing information:In conclusion checking item B and W in B
In the case that information is consistent, then B establishments can be released.From this explanation as can be seen that the release of conclusion and uniformity judge very
There is relation.By this method, the mapping of conclusion contradiction can be caused and deposited, and calculated based on such mapping, obtained
Equipment control command.For our situation, as conclusion verifies that item is with conclusion herein, so it can be appreciated that machine
Study control mapping conclusion it is consistent with the conclusion that self-defined control map in the case of, machine learning control map conclusion into
It is vertical.
For previous example：Machine learning controls to be mapped as that " the if times are, the brightness of and parlors at 7 points<Th, then open visitor
Room lamp "；It is self-defined to control to be mapped as " the if times are 2014.9.9-2014.9.10, and then is without opening parlor lamp ".If environment
Perception information meets first mapping and (meets the time for and parlor brightness at 7 points<Th) and Article 2 mapping (meeting the time is
2014.9.9-2014.9.10), because both conclusions are inconsistent, then do not extrapolate conclusion.Introduce after Default Logic,
Above-mentioned machine learning controls mapping to be updated to, and (the if times are 7 points, the brightness of and parlors<th):Open parlor lamp (i.e. conclusion
Verify item)/open parlor lamp (i.e. conclusion) ", above-mentioned general principle formula is corresponded to, i.e. α (x) is " the if times are, and at 7 points
Brightness<Th ", β (x)=γ (x)=" opening parlor lamp ".So when calculating, environment sensing information meets engineering
The premise of control mapping is practised, this mapping is enabled, then needs to judge whether β (x) now meets uniformity.It will be apparent that
Environment sensing information now equally enables self-defined control mapping, and conclusion is " without opening parlor lamp ", then β
(x) this conclusion checking item and the conclusion of self-defined control mapping are inconsistent, so the conclusion of machine learning control mapping can not
Set up.
A kind of above-mentioned method to resolve contradiction；The method that probability can also be used, is assigned necessarily to all mappings
Probable value, and probable value attenuation function is defined, as time goes by, probable value can gradually decay, so newer mapping meeting
With higher confidence level (the time gap current time for mapping generation is nearer, and its confidence level is higher), so as to be drawn by reasoning
Hold up and used, obtain corresponding equipment control command.
Step 303, equipment control command is showed user by controller, is indicated if receiving the mandate from user,
Then perform step 304；If not receiving user feedback in setting time section, according to default behavior, step is directly performed
304。
Equipment control command is fed back into user interface, so that user's operation behavior follow-up to control system is browsed
And control.Herein the controlling behavior of user can simply be divided into three kinds-" Never ", " OK ", " Not This Time ".
" Never " represents this conclusion mistake, and inference engine is when drawing a conclusion next time, and conclusion is anti-before push；" OK " is represented
Out of question, inference engine conclusion is correct, and user can receive；" Not This Time " represent only current current inaccurate, reasoning
Engine is not processed for such case, is specifically currently the specially treated of user.Feedback time section is set, if user
Corresponding operation is not made, and system default inference conclusion is accurate, that is, obtains the mandate of user；After the mandate of user is obtained, hold
The corresponding equipment controlling behavior of row.
Step 304, intelligent home device is controlled according to equipment control command.
Instant invention overcomes the shortcoming of prior art, there is provided a kind of intelligent home furnishing control method calculated based on general knowledge.
General knowledge, which is calculated, has two features, nonmonotonicity and time harmony, obtains most reasonably calculating conclusion based on current knowledge, can be with
Tolerate the presence of contradiction.This feature can just solve the collision problem that emergency case is brought in intelligent home control system.
Realizing for general knowledge reckoning is main comprising commonsense knowledge base and inference engine, and the acquisition of commonsense knowledge base has number of ways, can
To be the crawl of online data, user's contribution data, or utilize existing commonsense knowledge base；Inference engine is mainly realized often
Know reasoning algorithm, carry out calculating the rational conclusion of acquisition based on commonsense knowledge base.The main object of the present invention is to solve existing skill
Inference engine can not handle the problem of contradiction or conflict in art, and effectively prevent intelligence control system can not normal operation, increasing
The strong fault-tolerant ability of inference engine so that system more intelligently autonomous operation.
It is the system structure diagram that the present invention is controlled to intelligent home device referring to Fig. 4, the system includes user
End, server and controller；
The user terminal, receives the burst control information of user's input, burst control information and household identification is sent to
The server；
The server, receives burst control information and household identification from the client, to burst control information
Parsed, obtain the self-defined control mapping comprising condition and conclusion, be synchronized to controller corresponding with household identification；
The controller, machine learning is carried out to the history control information of intelligent home device, obtains including condition and knot
The machine learning control mapping of opinion；The self-defined control mapping from server is received, based on machine learning control mapping and certainly
Equipment control command is determined in definition control mapping, and intelligent home device is controlled according to equipment control command.
It is preferred that the server includes Mapping Resolution device, commonsense knowledge base, customer equipment storehouse and mapping thesaurus；
The customer equipment storehouse, the intelligent home device information of each household identification of storage correspondence；
The commonsense knowledge base, stores general knowledge, the control requirement comprising correspondence event；
The Mapping Resolution device, receives burst control information and household identification from client, to burst control information
Natural-sounding analysis is carried out, Time And Event therein is extracted, is inquired according to event in the commonsense knowledge base corresponding
Control is required；Intelligent home device information corresponding with corresponding household identification is inquired from the customer equipment storehouse, with reference to intelligence
Energy home equipment information, time and control require that the self-defined control for generating correspondence intelligent home device maps, and storage is described in
Map in thesaurus；
The mapping thesaurus, stores the self-defined control mapping from the Mapping Resolution device, is synchronized to and is marked with family
Know corresponding controller.
It is preferred that the controller includes family's mapping thesaurus, inference engine module and actuator；
The family maps thesaurus, receives the self-defined control mapping from the server, is stored；And store
The machine learning that controller is obtained to the historical operation record of smart home by machine learning mode controls to map；
The inference engine module, extraction machine study control mapping and self-defined control from family mapping thesaurus
Equipment control command is determined in system mapping, the control mapping based on extraction, is sent to the actuator；
The actuator, receives the equipment control command from the inference engine module, corresponding smart home is set
It is standby to be controlled.
It is preferred that the inference engine module includes the first inference engine submodule, environment sensing information is obtained, ring is judged
Whether border perception information meets the condition in machine learning control mapping and self-defined control mapping, if it is, judging machine
Study control mapping in conclusion checking item it is whether consistent with the conclusion that self-defined control maps, if unanimously, generate on
The equipment control instruction of machine learning control mapping conclusion, is sent to the actuator.
It is preferred that the inference engine module includes the second inference engine submodule, environment sensing information is obtained, ring is judged
Whether border perception information meets the condition in machine learning control mapping and self-defined control mapping, if it is, judging machine
Whether the conclusion checking item in study control mapping is consistent with the conclusion that self-defined control maps, if unanimously, generation closed
The equipment control instruction of mapping conclusion is controlled in machine learning, the actuator is sent to；If it is inconsistent, comparing engineering
The confidence level of control mapping and self-defined control mapping is practised, the control mapping of confidence level greatly is determined, extracts the control determined
Conclusion in mapping, generates the equipment control instruction on extracted conclusion, is sent to the actuator.
It is preferred that the user terminal includes MIM message input module and information text module；
Described information input module, receives the burst control information of user's input, is sent to described information textual module；
Described information textual module, judges the burst control information of reception, if text message, then directly
Server is sent to, if being not text message, burst control information is converted into text message, server is sent to.
It is preferred that family mapping thesaurus, is also periodically detected to self-defined control mapping, delete failure from
Definition control mapping.
In the control system scheme that the present invention is provided, user can input client by any information such as mobile phone, computer,
By demand or the emergency case input control system in the form of voice or text that happens suddenly；Mapping Resolution device is known by means of general knowledge
Information will be inputted and be converted to the available mapping of reckoning by knowing storehouse and natural language analysis technology, as self-defined control mapping, and
It is stored in mapping thesaurus.Inference engine module maps the mapping in thesaurus based on family and calculated, it is concluded that, from
Obtained from equipment control command, call actuator to perform corresponding equipment control command to reach the automated execution of equipment.
Mapping Resolution device is mainly the burst control information of parsing user's input and is converted to self-defined control mapping, by
The latent meaning of burst control information is analyzed in natural language technology and commonsense knowledge base, and is converted into corresponding self-defined control
System mapping, deposit mapping thesaurus.
The mapping that inference engine module is mainly responsible for mapping based on family in thesaurus carries out general knowledge reckoning, obtains rational
Conclusion.It is a kind of non-monotonic reckoning that general knowledge, which is calculated, is divided into the method and alogical method of logic, the method for logic can pass through
Two kinds of approach, a kind of is the method studied under classical logic framework, and another is to set up new semantic mechanism with patrolling
The method for the system of collecting.The combination of logical method and NOT logic method is also the active research field of comparison now.
Family's mapping thesaurus is mainly responsible for the storage and renewal of mapping.Basic mapping from machine learning method to
The regular study of family equipment operation record, obtains the operation behavior mode of user, the foundation run as equipment automatization.Emphasis
It is the renewal of self-defined control mapping；From the output of Mapping Resolution device, conflict may be produced with original behavior pattern,
How to solve the mapping of conclusion conflict and deposit the problem of exactly family's mapping thesaurus and inference engine module need to solve,
It is the core place of the present invention.
Using the present invention program, the burst demand input of user can be received, and is converted to self-defined control mapping, as
Follow-up derivation reference；Also, commonsense reasoning technology is also introduced, the mapping of conclusion conflict can be received and deposited, and it is basic herein
Upper reckoning obtains rational conclusion.So so that the control to intelligent home device is more intelligent and flexible, and lifting user's makes
With experience.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
God is with principle, and any modification, equivalent substitution and improvements done etc. should be included within the scope of protection of the invention.
Claims (12)
1. a kind of method being controlled to intelligent home device, it is characterised in that this method includes：
User terminal receives the burst control information of user's input, and user terminal is judged the burst control information of reception, if
For text message, then server is transmitted directly to, if being not text message, burst control information is converted into text envelope
Breath, is sent to server, household identification is sent into server；
Server is parsed to burst control information, obtains the self-defined control mapping comprising condition and conclusion, be synchronized to
The corresponding controller of household identification；
Controller carries out machine learning to the history control information of intelligent home device, obtains the engineering comprising condition and conclusion
Practise control mapping；And the self-defined control mapping from server is received, based on machine learning control mapping and self-defined control
Equipment control command is determined in mapping, and intelligent home device is controlled according to equipment control command.
2. the method as described in claim 1, it is characterised in that the server carries out parsing to burst control information to be included：
Server is analyzed burst control information, Time And Event therein is extracted, according to event in commonsense knowledge base
Corresponding control is inquired to require；Intelligent home device letter corresponding with corresponding household identification is inquired from customer equipment storehouse
Breath, is required with reference to intelligent home device information, time and control, the self-defined control mapping of generation correspondence intelligent home device.
3. the method as described in claim 1, it is characterised in that the controller is based on machine learning control mapping and self-defined
Control mapping determines that equipment control command includes：
Controller obtains environment sensing information, judges whether environment sensing information meets machine learning control mapping and self-defined control
The condition in mapping is made, if it is, judging that the conclusion in machine learning control mapping verifies what item and self-defined control mapped
Whether conclusion is consistent, if unanimously, the conclusion of machine learning control mapping is set up, and generates equipment control instruction.
4. the method as described in claim 1, it is characterised in that the controller is based on machine learning control mapping and self-defined
Control mapping determines that equipment control command includes：
Environment sensing information is obtained, judges whether environment sensing information meets machine learning control mapping and self-defined control mapping
In condition, if it is, judge machine learning control mapping in conclusion checking item and self-defined control mapping conclusion be
It is no consistent, if unanimously, the conclusion of machine learning control mapping is set up, and equipment control instruction is generated, by equipment control command
It is sent to actuator；If it is inconsistent, comparing the confidence level of machine learning control mapping and self-defined control mapping, determine
The control mapping of confidence level greatly, extracts the conclusion in the control mapping determined, generates and controlled on the equipment of extracted conclusion
Instruction.
5. the method as described in claim 1, it is characterised in that this method also includes：
Controller is periodically detected to self-defined control mapping, deletes the self-defined control mapping of failure.
6. the method as any one of claim 1 to 5, it is characterised in that it is described according to equipment control command to intelligence
Before home equipment is controlled, this method also includes：
Equipment control command is showed into user, indicates, performs described according to equipment if receiving the mandate from user
The step of control command is controlled to intelligent home device.
7. a kind of system being controlled to intelligent home device, it is characterised in that the system includes user terminal, server and control
Device processed；
The user terminal, receives the burst control information of user's input, and user terminal is judged the burst control information of reception,
If text message, then server is transmitted directly to, if being not text message, burst control information is converted into text
Information, is sent to server, and household identification is sent into the server；
The server, receives burst control information and household identification from the user terminal, and burst control information is carried out
Parsing, obtains the self-defined control mapping comprising condition and conclusion, is synchronized to controller corresponding with household identification；
The controller, machine learning is carried out to the history control information of intelligent home device, is obtained comprising condition and conclusion
Machine learning control mapping；The self-defined control mapping from server is received, is mapped and self-defined based on machine learning control
Equipment control command is determined in control mapping, and intelligent home device is controlled according to equipment control command.
8. system as claimed in claim 7, it is characterised in that the server includes Mapping Resolution device, commonsense knowledge base, visitor
Family equipment library and mapping thesaurus；
The customer equipment storehouse, the intelligent home device information of each household identification of storage correspondence；
The commonsense knowledge base, stores general knowledge, the control requirement comprising correspondence event；
The Mapping Resolution device, receives burst control information and household identification from client, and burst control information is carried out
Natural language analysis, extracts Time And Event therein, corresponding control is inquired in the commonsense knowledge base according to event
It is required that；Intelligent home device information corresponding with corresponding household identification is inquired from the customer equipment storehouse, with reference to intelligent family
Occupy facility information, time and control to require, the mapping is arrived in the self-defined control mapping of generation correspondence intelligent home device, storage
In thesaurus；
The mapping thesaurus, stores the self-defined control mapping from the Mapping Resolution device, is synchronized to and household identification pair
The controller answered.
9. system as claimed in claim 7, it is characterised in that the controller includes family's mapping thesaurus, inference engine
Module and actuator；
The family maps thesaurus, receives the self-defined control mapping from the server, is stored；And store control
The machine learning that device is obtained to the historical operation record of smart home by machine learning mode controls to map；
The inference engine module, extraction machine study control mapping and self-defined control are reflected from family mapping thesaurus
Penetrate, equipment control command is determined in the control mapping based on extraction, is sent to the actuator；
The actuator, receives the equipment control command from the inference engine module, corresponding intelligent home device is entered
Row control.
10. system as claimed in claim 9, it is characterised in that the inference engine module includes the first inference engine submodule
Block, obtains environment sensing information, judges whether environment sensing information meets machine learning control mapping and self-defined control mapping
In condition, if it is, judge machine learning control mapping in conclusion checking item and self-defined control mapping conclusion be
It is no consistent, if unanimously, the conclusion of machine learning control mapping is set up, and is generated equipment control instruction, is sent to the execution
Device.
11. system as claimed in claim 9, it is characterised in that the inference engine module includes the second inference engine submodule
Block, obtains environment sensing information, judges whether environment sensing information meets machine learning control mapping and self-defined control mapping
In condition, if it is, judge machine learning control mapping in conclusion checking item and self-defined control mapping conclusion be
It is no consistent, if unanimously, the conclusion of machine learning control mapping is set up, and is generated equipment control instruction, is sent to the execution
Device；If it is inconsistent, compare the confidence level of machine learning control mapping and self-defined control mapping, determine that confidence level is big
Control mapping, extracts the conclusion in the control mapping determined, generates the equipment control instruction on extracted conclusion, be sent to
The actuator.
12. the system as any one of claim 7 to 11, it is characterised in that the user terminal includes information and inputs mould
Block and information text module；
Described information input module, receives the burst control information of user's input, is sent to described information textual module；
Described information textual module, judges the burst control information of reception, if text message, then directly transmits
To server, if being not text message, burst control information is converted into text message, server is sent to.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510040534.1A CN104579873B (en) | 2015-01-27 | 2015-01-27 | The method and system being controlled to intelligent home device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510040534.1A CN104579873B (en) | 2015-01-27 | 2015-01-27 | The method and system being controlled to intelligent home device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104579873A CN104579873A (en) | 2015-04-29 |
| CN104579873B true CN104579873B (en) | 2017-09-22 |
Family
ID=53095130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510040534.1A Active CN104579873B (en) | 2015-01-27 | 2015-01-27 | The method and system being controlled to intelligent home device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104579873B (en) |
Families Citing this family (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106292302A (en) * | 2015-05-22 | 2017-01-04 | 阿里巴巴集团控股有限公司 | The control method of intelligent domestic system and device |
| CN104881013B (en) * | 2015-05-29 | 2018-01-16 | 四川长虹电器股份有限公司 | The intelligent household electrical appliance linkage control method excavated based on user's habits and customs |
| CN104898634B (en) * | 2015-06-30 | 2018-08-07 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN105137779B (en) * | 2015-07-30 | 2018-02-16 | 四川长虹电器股份有限公司 | A kind of information processing method and smart home environment control device |
| CN105404161A (en) * | 2015-11-02 | 2016-03-16 | 百度在线网络技术（北京）有限公司 | Intelligent voice interaction method and device |
| CN107045291B (en) * | 2016-02-05 | 2020-05-08 | 中国电信股份有限公司 | Method, device and system for forming control rule of intelligent terminal |
| GB2547932B (en) * | 2016-03-03 | 2019-08-14 | Arm Ip Ltd | Time-limited access to configuration settings |
| CN106527168A (en) * | 2016-12-27 | 2017-03-22 | 海尔优家智能科技（北京）有限公司 | AllJoyn linkage control conflict resolution method, trigger and server |
| CN109218049B (en) * | 2017-06-30 | 2021-10-26 | 华为技术有限公司 | Control method, related equipment and system |
| CN107688329B (en) * | 2017-08-21 | 2020-02-14 | 杭州博联智能科技股份有限公司 | Intelligent home control method and intelligent home control system |
| CN107564522A (en) * | 2017-09-18 | 2018-01-09 | 郑州云海信息技术有限公司 | A kind of intelligent control method and device |
| CN108111378A (en) * | 2017-12-22 | 2018-06-01 | 南京物联传感技术有限公司 | The conflict coordination system and method for work of a kind of scene settings of smart home |
| CN108919669B (en) * | 2018-09-11 | 2022-04-29 | 深圳和而泰数据资源与云技术有限公司 | Intelligent home dynamic decision method and device and service terminal |
| CN109324585A (en) * | 2018-11-20 | 2019-02-12 | 曹景荣 | A kind of monitoring system and method for smart home |
| CN109361766A (en) * | 2018-12-04 | 2019-02-19 | 安徽信息工程学院 | A kind of internet of things net controller based on SDN |
| CN109683715B (en) * | 2018-12-29 | 2020-12-18 | 北京诺亦腾科技有限公司 | VR equipment control method and device and computer readable storage medium |
| CN110888336A (en) * | 2019-12-02 | 2020-03-17 | 蚁蜂(广州)智能科技有限公司 | Intelligent household control system and control method |
| CN112328325A (en) * | 2020-11-06 | 2021-02-05 | 深圳壹账通智能科技有限公司 | Execution method and device of model file, terminal equipment and storage medium |
| CN114722050B (en) * | 2022-06-10 | 2022-09-30 | 辰星（天津）自动化设备有限公司 | Data synchronization method of robot system and robot system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20080046964A (en) * | 2006-11-24 | 2008-05-28 | (주)오로라 디자인랩 | A service method of the intelligence type home network system for the user of an equipment control base |
| CN201435002Y (en) * | 2009-07-16 | 2010-03-31 | 吕晓冬 | Remote automation control system of intelligent household |
| CN202939771U (en) * | 2012-11-04 | 2013-05-15 | 张宁 | Intelligent home safety monitoring system |
| CN103393412A (en) * | 2013-08-15 | 2013-11-20 | 重庆邮电大学 | Intelligent home based old person caring device |
| CN103744411A (en) * | 2014-02-07 | 2014-04-23 | 上海金牌软件开发有限公司 | Control method related to ZigBee technology for realizing smart home |
-
2015
- 2015-01-27 CN CN201510040534.1A patent/CN104579873B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20080046964A (en) * | 2006-11-24 | 2008-05-28 | (주)오로라 디자인랩 | A service method of the intelligence type home network system for the user of an equipment control base |
| CN201435002Y (en) * | 2009-07-16 | 2010-03-31 | 吕晓冬 | Remote automation control system of intelligent household |
| CN202939771U (en) * | 2012-11-04 | 2013-05-15 | 张宁 | Intelligent home safety monitoring system |
| CN103393412A (en) * | 2013-08-15 | 2013-11-20 | 重庆邮电大学 | Intelligent home based old person caring device |
| CN103744411A (en) * | 2014-02-07 | 2014-04-23 | 上海金牌软件开发有限公司 | Control method related to ZigBee technology for realizing smart home |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104579873A (en) | 2015-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104579873B (en) | The method and system being controlled to intelligent home device | |
| CN108919669B (en) | Intelligent home dynamic decision method and device and service terminal | |
| TWI244637B (en) | Voice control system for operating home electrical appliances | |
| CN104898634B (en) | Information processing method and electronic equipment | |
| CN109933029A (en) | A kind of intelligent home control system based on Cloud Server | |
| CN107179701B (en) | Intelligent household equipment self-adaptive linkage rule generation method | |
| CN106713113A (en) | Intelligent household control apparatus based on instant messaging, and personalized interaction method | |
| CN104965416A (en) | Intelligent household electrical appliance control method and apparatus | |
| CN102736526A (en) | Control apparatus, control method, program and system | |
| CN105467846A (en) | Intelligent household appliance control method and system | |
| CN109450745A (en) | Information processing method, device, intelligence control system and intelligent gateway | |
| CN109407538A (en) | Intelligent home furnishing control method and system | |
| JP6400834B2 (en) | RECOMMENDATION DEVICE, RECOMMENDATION DETERMINING METHOD, AND COMPUTER PROGRAM | |
| KR20170006120A (en) | Home IoT controlling system based on occupants inference probability and method threreof | |
| CN113900383A (en) | Intelligent household equipment control method, router, intelligent household system and medium | |
| Sai et al. | Smart Home Messenger Notifications System using IoT | |
| Ibarra et al. | Temporal reasoning for intuitive specification of context-awareness | |
| CN106254186A (en) | A kind of interactive voice control system for identifying | |
| CN106201530A (en) | The screen display method of application card and device | |
| KR102075381B1 (en) | System and Method Things Co-operation Service and the Modeling Tool thereof | |
| JP2009027523A (en) | Remote monitoring control apparatus | |
| KR100643294B1 (en) | System and method simulating for home network | |
| JP5896934B2 (en) | Supervisory control system | |
| US20230196305A1 (en) | Devices to service physical conditions of rooms | |
| JP6909984B2 (en) | Home appliance management server, home appliance management method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |