CN108983625A - A kind of smart home system and service creation method - Google Patents
A kind of smart home system and service creation method Download PDFInfo
- Publication number
- CN108983625A CN108983625A CN201810804333.8A CN201810804333A CN108983625A CN 108983625 A CN108983625 A CN 108983625A CN 201810804333 A CN201810804333 A CN 201810804333A CN 108983625 A CN108983625 A CN 108983625A
- Authority
- CN
- China
- Prior art keywords
- service
- smart home
- knowledge
- article
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000000694 effects Effects 0.000 claims abstract description 63
- 238000001514 detection method Methods 0.000 claims abstract description 37
- 238000004891 communication Methods 0.000 claims abstract description 4
- 230000006399 behavior Effects 0.000 claims description 59
- 230000033001 locomotion Effects 0.000 claims description 58
- 230000000875 corresponding effect Effects 0.000 claims description 45
- 230000009471 action Effects 0.000 claims description 31
- 230000007613 environmental effect Effects 0.000 claims description 27
- 238000013507 mapping Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 16
- 238000004088 simulation Methods 0.000 claims description 11
- 230000003542 behavioural effect Effects 0.000 claims description 10
- 230000019771 cognition Effects 0.000 claims description 10
- 230000005284 excitation Effects 0.000 claims description 6
- 230000008447 perception Effects 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 241000208340 Araliaceae Species 0.000 claims description 4
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 4
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 4
- 235000008434 ginseng Nutrition 0.000 claims description 4
- 238000011897 real-time detection Methods 0.000 claims description 4
- 230000035899 viability Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 2
- 238000004321 preservation Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 230000002452 interceptive effect Effects 0.000 abstract description 6
- 208000012661 Dyskinesia Diseases 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 20
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 description 6
- 238000010411 cooking Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 230000007958 sleep Effects 0.000 description 3
- 230000036772 blood pressure Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000035479 physiological effects, processes and functions Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- WSFSSNUMVMOOMR-NJFSPNSNSA-N methanone Chemical compound O=[14CH2] WSFSSNUMVMOOMR-NJFSPNSNSA-N 0.000 description 1
- 239000008267 milk Substances 0.000 description 1
- 210000004080 milk Anatomy 0.000 description 1
- 235000013336 milk Nutrition 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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] or computer integrated manufacturing [CIM]
- G05B19/4183—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] or computer integrated manufacturing [CIM] characterised by data acquisition, e.g. workpiece identification
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a kind of smart home system and service creation methods, including smart home emulation platform, the smart home emulation platform carries out information communication with knowledge base management system, service robot platform respectively, and the smart home emulation platform, service robot platform distinguish receiving sensor system information collected;In the present invention, in the case where not interfering user behavior activity and privacy, dispose corresponding sensing system to monitor user behavior activity and abnormal movement, such as: detection is fallen down in active sequences monitoring;Smart home system can realize that real time environment monitors simultaneously, and the autonomous offer exception services such as environment and behavior.
Description
Technical field
The present invention relates to Smart Home technical fields, more particularly to a kind of smart home system and service creation method.
Background technique
The technologies such as Internet of Things, general fit calculation are constantly progressive the fast development for having pushed smart home, and smart home is as one
Effectively method can be relieved problem brought by population growth to kind, such as: medical resource guarantee, old man's monitoring, community service, together
When can also service/help people to improve their living standard.With the continuous improvement of people's lives level, people couple
The quality of life require it is also higher and higher, it is desirable to smart home system it will be appreciated that their intention, and with a kind of correct
Ground mode provides for them properly to be serviced.However, presently, there are most of smart home system only improve people
Living environment, and provided method of service can not allow people satisfied.
Chinese invention patent number is that ZL201410480103.2 has invented a kind of smart home system, passes through infrared sensor
Mobile article is perceived, when mobile there are article, start camera recorded video and is uploaded to remote server, user is long-range
Family can remotely be monitored, while by that remotely can realize intelligent management to intelligent socket.
Chinese invention patent number is that a kind of smart home system has also been invented in ZL201410273087.X, passes through acquisition module
The monitoring, including smokescope, gas concentration, concentration of formaldehyde etc. for realizing home environment, while under the mode of leaving home, when sound,
Light has anomalous variation or when there are objects moving, and intelligent terminal can realize the monitoring to household situation.
Chinese invention patent number is that ZL201510546929.9 has invented a kind of home intelligent clothes based on wireless sensor
Business method detects the living habit of user and generates user individual by disposing wireless sensor node indoors
Custom tabular, sensor acquires the scene information of user in real time, and is searched in user individual custom tabular, then root
Corresponding operation is executed to corresponding equipment according to service.The patent is only collected some habits of user, as illumination is set
The use habit applied does not relate to the detection of behavior.
In addition, Chinese invention application No. is 201410627717.9 disclose a kind of home-services robot and with its
Home services system detects the home environment parameter in family by the sensor of home-services robot, and according to family's ring
Border parameter generates the control instruction of corresponding household appliance, directly controls household electrical appliance to realize, and can be carried out complicated control
System.
The above invention is mainly based upon detection and monitoring of the data realization to environmental information, and is not mentioned to user
On the other hand the monitoring of behavioral activity is to realize service execution using the instruction of setting, not when executing service operations
Service etc. can be executed with a kind of method of servicing of hommization.
Summary of the invention
In order to solve the deficiencies in the prior art, the present invention provides a kind of smart home system, the present invention not only can be right
Environment is monitored in real time, can also in the case where not interfering the movable situation of user behavior, effectively monitor user behavior activity and
Abnormal behavior, another aspect service robot can be by learning user behavior active sequences, and then with a kind of natural, hommization
Method of servicing service user, while the article knowledge of profound cognition can be obtained on demand and environment executes, to improve Service Quality
Amount.
A kind of smart home system, including smart home emulation platform, the smart home emulation platform respectively with knowledge
Base management system, service robot platform carry out information communication, the smart home emulation platform, service robot platform difference
Receiving sensor system information collected;
The smart home emulation platform study obtains every kind of corresponding user behavior sequence of service and is based on extensive chemical
The execution parameter that simulation obtains record and hold described by the implementation procedure for practising each movement in modelling customer behavior sequence
The combination producing of row parameter and behavior sequence executes the complete service knowledge of the service, and uploads knowledge base management system guarantor
It deposits;
The service robot platform is inferred according to sensing system perception real time information and knowledge base management system
Service needed for user or the service order for receiving user's sending, it includes holding that service robot platform, which then obtains execute the service,
The service knowledge of row parameter and behavior sequence.
Further preferred technical solution, the smart home system based on user behavior sequence further include intelligent execution
Device systems, the intelligence executes device systems and smart home emulation platform communicates and receives the sensor system
It unites information collected.
Further preferred technical solution, the sensing system include behavioral activity detection sensor, environmental information inspection
Sensor and user's physical signs detection sensor are surveyed, the measured value of specific sensor is all made of this in the sensing system
Body technique is expressed as semantic knowledge to it.
The real time data information of further preferred technical solution, the activity detection sensor detection is complete through ontology
After the semantic representation of knowledge, the movable detection and reasoning of real-time implementation user, and be transmitted to smart home emulation platform and be used for
Service knowledge study;
The real time data information of environmental information detection sensor detection after ontology completes semantic knowledge expression,
The detection and service reasoning of real-time implementation environment, and the service transmission of required execution to service robot platform or intelligence are executed
Device systems complete the execution of service;
The physical signs detection sensor is used for the physiological characteristic information of real-time detection user.
Further preferred technical solution, the knowledge base management system include service knowledge library, rule-based knowledge base, article
Knowledge base and environmental knowledge library;
The service knowledge library includes the User Activity behavior sequence learnt and execution parameters knowledge;
Reasoning of the rule-based knowledge base for service automatically infers required service when regular premise meets, and wraps
Exception service and personalized service are included, the service of institute's reasoning executes device systems by service robot platform or intelligence and executes;
The article knowledge base includes the more educated description to operation article, realizes and recognizes to the profound of operation article;
The environmental knowledge library includes the knowledge description to environment, convenient for the execution of cognition and service to home environment.
Disclosed herein as well is a kind of service creation method of smart home system, including robot service creation step,
Specifically:
Semantic knowledge mapping will be completed between User Activity behavior and operation article;
The User Activity behavior of perception is transmitted to smart home emulation platform and is stored;
There is maximum probability based on User Activity historical knowledge and learns in emulated robot in smart home emulation platform
The sequence of the optimal execution behavior, referred to herein as service;
For each movement in each service, the optimal movement ginseng for executing each movement is simulated based on intensified learning
Number;
The real time information of sensor based system perception, pushes away in conjunction with the rule in rule-based knowledge base in knowledge base management system
It manages out and services;
After service robot platform receives the service of reasoning, the service and mould that smart home emulation platform learns are obtained
Quasi- execution action parameter executes service with a kind of natural, hommization method of service;
Viability is executed in service robot platform, the automatic article knowledge obtained in knowledge base management system on demand,
Environmental knowledge, to guarantee going on smoothly for service robot service execution.
Further preferred technical solution, it is described that the optimal movement ginseng for executing each movement is simulated based on intensified learning
Number, its step are as follows:
Smart home emulation platform is using the movement in service sequences as input, to execute the corresponding operation article of the movement
Optimal action parameter as output;
The judgment criteria for selecting article condition combination to complete as movement, it is when article condition changes, then corresponding to move
Make parameter to execute the corresponding parameter of service action;
By constructing feature vector of the neural network by combinations of states transcoding for fixed dimension, measured using cosine similarity
The deviation of state repository vector and the state vector generated after the simulation of smart home emulation platform, to export corresponding excitation
Value;
In conjunction with nitrification enhancement, according to the corresponding value function of article condition, value function is obtained using gradient descent algorithm
Local derviation, and to state parameter be finely adjusted rear corresponding action parameter be complete service required for parameter.
Further preferred technical solution, the judgment criteria for selecting article condition combination to complete as movement, needs to construct
The corresponding article condition combination for completing a movement of article condition library H, H (i), wherein the corresponding movement of i, executed in movement
Cheng Zhong, smart home emulation platform is by the combination of building various motion and parameter setting, so that object model be made to meet H (i)
Corresponding state, to obtain the action parameter for generating the state and needing.
Further preferred technical solution, the corresponding value function of the article condition are as follows:
Vθ(s)=E [r (h)]
Wherein, θ is state parameter, and s record executes the movement and is related to the current state of article, and h storage is in different time periods
Article condition is expressed asR (h) can return to the corresponding excitation value of h;T refers to service ending time, S (Ht) indicate
The article condition set of t period;
The local derviation of value function is obtained using gradient descent algorithm, and is finely adjusted to state parameter:
Here p=(a | s, θ) is the probability that generation acts a under softmax function output state s.When state parameter reaches
When convergence, at this time Vθ(s) value tends to be maximum, and corresponding action parameter is parameter required for completing to service.
Further preferred technical solution, a kind of service creation method of smart home system, further includes environment and physiology
Indexes Abnormality service creation step, specifically:
Threshold value δ is arranged to relevant environmental parameter and physical signs respectively, when environmental sensor or the measured value of physical signs
More than setting threshold value δ when, then be defined as that environment or physical signs exception item has occurred;
Its SWRL rule is defined to environment and physical signs exception service cognitive process according to the mankind;
Based on real-time environment and physical signs information, reasoning and performing environment and physical signs exception service.
Further preferred technical solution, a kind of service creation method of smart home system, further includes that User Activity is different
Informal dress business generation step, specifically:
Semantic knowledge mapping will be completed between User Activity behavior and operation article;
It is accustomed to setting normal activity time of the act threshold tau according to user;
Its SWRL rule is defined to crawler behavior exception service cognitive process according to the mankind;
Based on the crawler behavior and time parameter information perceived in real time, reasoning and execution activity exception service;
Semantic knowledge mapping method between the User Activity behavior and operation article are as follows:
Definition: O, which represents completion activity, need to operate article, and M indicates that the mapping template based on ontology, H indicate article O's
Semantic knowledge, that is, crawler behavior;
When sensor detects one of article movement that completion activity need to operate, which is become by 0
It is 1, then the numerical value 1 of the sensor, which describes it by the mapping template M based on ontology, acts corresponding semantic knowledge;
When perceiving a certain movement generation or the non-origination interval time is more than the time threshold τ of setting, then it is defined as sending out
Movable abnormal item is given birth to.
Further preferred technical solution, a kind of service creation method of smart home system, further includes personalized service
Generation step, specifically:
Semantic knowledge mapping will be completed between User Activity behavior and operation article;
According to the similar setting personalized service time error threshold value of service
According to individual subscriber behavioural habits, personalized service SWRL rule is defined;
Based on the crawler behavior and time parameter information perceived in real time, reasoning simultaneously executes personalized service.
Compared with prior art, the beneficial effects of the present invention are:
1, in the present invention, in the case where not interfering user behavior activity and privacy, corresponding sensing system is disposed
User behavior activity and abnormal movement are monitored, such as: detection is fallen down in active sequences monitoring;Smart home system can realize reality simultaneously
When environmental monitoring, and autonomous provide the exception services such as environment and behavior.
2, it in the present invention, by the real-time behavioral activity of user, may be implemented to service based on active sequences and time attribute
Reasoning, while according to the personal preference of user, it is possible to provide personalized service, meanwhile, recognized based on multiattribute article profound level
Know that the execution for service provides guarantee.
3, in the present invention, User Activity behavior sequence can be learnt in smart home analogue system, and be based on intensified learning
The execution parameter for simulating object manipulation, based on the service knowledge learnt, robot can be according to the active sequences of user's habit
Executes service with a kind of natural, hommization method of servicing, while robot is in execution viability, it can on-demand autonomous acquisition
Environmental knowledge and article knowledge in knowledge base, to improve service quality.
Detailed description of the invention
The accompanying drawings constituting a part of this application is used to provide further understanding of the present application, and the application's shows
Meaning property embodiment and its explanation are not constituted an undue limitation on the present application for explaining the application.
Fig. 1 is a kind of smart home system schematic diagram of of the embodiment of the present invention;
Fig. 2 is the semantic knowledge mapping method schematic diagram between the operation article and behavioral activity of of the embodiment of the present invention;
In figure, 10 knowledge base management systems, 20 smart home emulation platforms, 301 service robot platforms, 302 intelligence are held
Row device systems, 303 sensing systems, 101 service knowledge libraries, 102 rule-based knowledge bases, 103 article knowledge bases, 104 environment are known
Know library.
Specific embodiment
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the application.Unless another
It indicates, all technical and scientific terms used herein has usual with the application person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
In a kind of specific embodiment of the application, a kind of smart home system is provided, as shown in Figure 1, including knowledge
Base management system 10, smart home emulation platform 20, service robot platform 301, intelligence execute device systems 302 and sensor
System 303, in which:
Smart home emulation platform is the virtual home environment built based on softwares such as V-REP, Python, including household,
The entities such as sensor, robot, service robot platform are exactly the service platform combined by robot common in family, simply
Ground is said, is exactly multi-robot system
Intelligence executes equipment and refers mainly to intelligent actuator in family, such as: intelligent switch, intelligent socket, smart machine control
Device etc., what is be all made of is wireless communication.
Knowledge in knowledge base management system 10 includes service knowledge library 101, rule-based knowledge base 102, article knowledge base 103
With environmental knowledge library 104, wherein knowledge base management system 10 and 20 two-way interactive of smart home emulation platform.
Service knowledge library 101 is used to instruct smart home emulation platform 20 and services the execution that robot platform 301 services,
Including the User Activity behavior sequence learnt and parameters knowledge is executed, and service knowledge library 101 may be implemented new demand servicing and know
The automatic modification of the automatic addition and old knowledge known, to ensure that the update and growth in service knowledge library 101.
It is a variety of executive modes that the activity that is directed to includes by H about study User Activity behavior sequence, by calculating this
The probability that a little sequences occur is used to instruct to execute by probability of occurrence is maximum, referred to as learns the action sequence for obtaining or determining
It executes.
Above-mentioned guidance, which refers to, provides the sequences such as main action command, such as " taking cup " → " arriving parlor " for robot
Guidance.
The study for executing parameter uses the method based on intensified learning, and the strategy and parameter learnt is known as knowledge.
About the update and modification in service knowledge library, the update of the information such as environment, article mainly in home environment, than
As soon as certain article is moved to another place by a place, then some relationship knowledge of this article need to update and replace
It changes, such as the update of position, with the addition of the association knowledge of other new articles etc., because the data of above-mentioned variation are to pass through this
Body Template Map is knowledge relevant to service at semantic knowledge, so referred to as service knowledge.
Rule-based knowledge base 102 is mainly used for the reasoning of service, and rule-based knowledge base 102 uses SWRL (Semantic
WebRule Language) logical language expression, when regular premise meets, required service can be automatically inferred, including different
Informal dress business and personalized service, the service of institute's reasoning execute device systems 302 by service robot platform 301 and/or intelligence and hold
Row.
Article knowledge base 103 mainly includes the more educated description to operation article, main by increasing category attribute, physics
Attribute, perceptual property, status attribute, functional attributes, operational attribute, which are realized, recognizes the profound of operation article, the classification category
Property mainly description article described in classification, such as container class, the physical attribute be mainly describe article can quantitative description category
Property, such as size, the perceptual property is the visual signature for describing article, and such as color, the status attribute is that description article is current
Possessed state, as cup be it is empty, the functional attributes be description article meet certain functional requirement, can such as grab,
The operational attribute required attribute, such as grasping force when being description object manipulation.
Environmental knowledge library 104 is mainly the knowledge description to environment, the number of structure, room including indoor environment, room
Between the knowledge such as function, convenient for the execution of cognition and service to home environment.
In embodiments herein, 20 one side of smart home emulation platform is used for the User Activity row for learning to perceive
For sequence, on the other hand, using execution of the method dummy robot to article based on intensified learning, the sequence knowledge that will be acquired
The execution parameter obtained with simulation is stored into knowledge base management system 10, while can realize knowledge with service robot platform 301
Real-time, interactive.
Wherein, service robot platform 301 mainly executes more complex service, such as: one glass of milk is provided for user,
Simultaneously in service execution, service knowledge library 101, required article knowledge base 103 and environment in knowledge base management system 10 are known
Knowing library 104 can be obtained and be utilized by service robot platform 301 in real time, to guarantee the smoothly progress of service.
And intelligence executes device systems 302 and mainly completes better simply service, and such as: it is independently completed according to indoor temperature and humidity
The adjusting of air-conditioning equipment is serviced according to user's habit from suitable light of main regulation etc..
In addition, sensing system 303 is not using before interfering user's daily behavior movable in embodiments herein
Put, by it is seamless, natural, suitably in a manner of be distributed and be embedded into home environment, be broadly divided into three categories: behavioral activity detection
Sensor, environmental information detection sensor and user's physical signs detection sensor.
Specifically, the measured value of sensing system 303, which is all made of ontology, is expressed as semantic knowledge, such as pressure to it
Sensor is attached on cup, and when the pressure sensor numeric state becomes 1, semantic description is to pick up cup.
About ontology, it is particularly used for the representation of knowledge, briefly, for example sensing data is exactly some numbers,
It can not directly understand meaning described in this number, however by the mapping of ontology, just directly it is able to reflect out the language of that
Adopted knowledge, the content that also energy people can understand.See document: Ganz F, Barnaghi P, Carrez F.Automated
Semantic Knowledge Acquisition From Sensor Data[J].IEEE Systems Journal,2016,
10(3):1214-1225.
In the specific implementation, activity detection sensor mainly include pressure sensor, contact sensor, motion sensor,
Infrared sensor, switch sensor, proximity sensor and other users activity detection sensor, pressure sensor are attached to article
On, it can be used for detecting picking up or putting down for article, contact sensor is infrared for detecting whether user is in contact with the article
In sensor deployment room, the number of deployment is determined according to the measurement range of infrared sensor, for whether detecting user at certain
In a room, motion sensor is disposed in room, the number of deployment is determined according to the measurement range of motion sensor, for detecting
Whether user moves in the room, switch sensor mainly for detection of the on or off of article being presently in state, such as it is micro-
The switch state of wave fire door, proximity sensor are mounted on door, the operation switched for detecting user to door, activity detection
The real time data information of sensor detection is after ontology completes semantic knowledge expression, the movable detection of real-time implementation user
With reasoning, and be transmitted to smart home emulation platform 20 for service knowledge learn.
In the specific implementation, environmental information detection sensor mainly includes temperature sensor, humidity sensor, illumination sensing
Device, gas concentration sensor, concentration of formaldehyde sensor, CO2Sensor and other environmental detection sensors, are respectively used to detect
The temperature of environment, humidity, intensity of illumination, concentration of formaldehyde, CO2The other environmental information such as concentration, the inspection of environmental information detection sensor
The real time data information of survey is after ontology completes semantic knowledge expression, the detection and service reasoning of real-time implementation environment, and
The service transmission of required execution to service robot platform 301 or intelligence are executed into the execution that device systems 302 complete service.
The expression of above-mentioned data and its semantic knowledge be sensing system in complete, that is to say, sensor obtains number
According to rear, it is just mapped as semantic knowledge, is specifically shown in the mapping method of Fig. 2.
The detection of User Activity is exactly the variation of sensor detection data.And reasoning is executed in knowledge base management system
, because the reasoning of service needs to be related to inference rule.
In the specific implementation, physical signs detection sensor mainly includes that the physiology such as blood pressure sensor, heart rate sensor refer to
Sensor is marked, is mainly used for the physiological characteristic informations such as blood pressure, the heart rate of real-time detection user, the physical signs sensor can also
For the multifunctional intellectual bracelet for being able to detect physical signs.
In another specific embodiment of the application, smart home system service creation method is additionally provided, comprising: environment
Abnormal and physical signs service creation method, User Activity exception service generation method, personalized service generation method and machine
People's service creation method.
Wherein, environment and physical signs exception service, User Activity exception service and personalized service are according to sensing
The environment and user activity information of 303 system real-time detection of device, it is real by the rule-based knowledge base 102 in knowledge base management system 10
When the information on services that infers, and robot platform 301 is reasonably distributed into the service of reasoning or intelligence executes device systems
302 complete the execution of service, while during service execution, can obtain article on demand from knowledge base management system 10 in real time and know
The content in library 103 and the content in environmental knowledge library 104 are known, to guarantee going on smoothly for service.
In still another embodiment of the application, environment and physical signs exception service generation method are disclosed, comprising:
Step a1: threshold value δ is arranged to relevant environmental parameter and physical signs respectively;
Step a2: its SWRL rule is defined to environment and physical signs exception service cognitive process according to the mankind;
Step a3: real-time environment and physical signs information, reasoning and performing environment and physical signs exception service are based on;
Wherein, the purpose of the step a1 is when the measured value of environment or physical signs sensor is more than the threshold value δ of setting
When, then it is defined as that environment or physical signs exception item has occurred.
For environment and physical signs exception service generation method, with one simply example be illustrated, such as: " kitchen
Room gas concentration is excessively high " exception service, first setting gas concentration outlier threshold δ, its rule is then defined using SWRL:
Its meaning indicates are as follows: when kitchen, gas concentration sensor detects that concentration is higher than given threshold, automatic execute is beaten
It opens kitchen window and issues and issue the user with warning service.
Likewise, being then physically different when detecting that physical signs is more than normality threshold (being the threshold value of setting).
In still another embodiment of the application, User Activity exception service generation method is disclosed, comprising:
Step b1: semantic knowledge mapping will be completed between User Activity behavior and operation article;
Step b2: setting normal activity time of the act threshold tau is accustomed to according to user;
Step b3: its SWRL rule is defined to crawler behavior exception service cognitive process according to the mankind;
Step: b4: based on the crawler behavior and time parameter information perceived in real time, reasoning and execution activity clothes extremely
Business.
Wherein, semantic knowledge mapping method such as Fig. 2 institute between crawler behavior described in the step b1 and operation article
Showing, O indicates that completion activity need to operate article, and M indicates that the mapping template based on ontology, H indicate the semantic knowledge of article O,
Namely crawler behavior, such as, it is assumed that o1 represents micro-wave oven, and switch sensor is attached to the suitable position of door of micro-wave oven
It sets, the state of the on or off for detecting door for microwave oven, when the sensor status values become 1 from 0, then the numerical value of the sensor
1 describes it to act h1 semantic knowledge to be " door for opening micro-wave oven " by the mapping template M based on ontology;The step b2
Purpose be when perceive a certain movement (multiple movements one crawler behavior of composition, that is to say h1, h2 in Fig. 2, h3, h4,
H5, h6) occur or when the non-origination interval time is more than the time threshold τ of setting, is then defined as having occurred movable abnormal item.
For User Activity exception service generation method, with one simply example be illustrated, such as: user " falls down
Behavior " exception service, first setting normal activity time of the act threshold tau, then define its rule using SWRL:
Its meaning indicates are as follows: when room, infrared sensor detects that user exists, and room motion sensor is not examined
Movement is measured, while in the presence of user, the time not moved is more than the time threshold of setting, then inferring
" falling down behavior " and give a warning service.
In another specific embodiment of the application, personalized service generation method is disclosed, comprising:
Step c1: semantic knowledge mapping will be completed between User Activity behavior and operation article;
Step c2: according to the similar setting personalized service time error threshold value of service
Step c3: according to individual subscriber behavioural habits, personalized service SWRL rule is defined;
Step c4: based on the crawler behavior and time parameter information perceived in real time, reasoning simultaneously executes personalized service.
Wherein, the purpose of the step c1 is consistent with movable exception service step b1 purpose;The purpose of the step c2 is
, can't be proper consistent since everyone is when crawler behavior executes, only can in a time range, such as:
User is usually 9 points of sleeps at night, does not imply that just 9 points of sleeps, but this behavior occurs at 9 points or so, thus
Time error threshold value is defined, as long as the user preference time difference of the time and definition occurred is in this time error threshold value
Interior, that is, being defined as the time meets the personalized service.
For user individual service creation method, with one simply example be illustrated, such as: detect that user returns
The personalized service of bedroom during sleep, first setting personalized service time error threshold valueThen its rule is defined using SWRL
Then:
Wherein TimeRangeTest is to compare current time whether in the error range of personal preference time, rule
Meaning indicates are as follows: when sensing system 303 detects that user enters bedroom, and the current time is in the mistake of user's sack time
Within the scope of difference, services then inferring " opening bedside lamp " and be automatically adjusted to " SoftWhite " state, while service-delivery machine
People's platform 301 executes " SendMilk " personalized service.
In still another embodiment of the application, robot service creation method is disclosed, comprising:
Step d1: semantic knowledge mapping will be completed between User Activity behavior and operation article;
Step d2: the User Activity behavior of perception is transmitted to smart home emulation platform and is stored;
Step d3: the emulated robot in smart home emulation platform 20 is learnt out most based on the historical knowledge of User Activity
It is excellent execute the behavior sequence, optimal execution sequence here is exactly the maximum sequence of probability of occurrence, referred to herein as service;
Step d4: it for each movement in each service, is simulated based on intensified learning and executes the optimal of each movement
Action parameter;
Step d5: the real time information that sensor based system 303 perceives, in conjunction with rule knowledge in knowledge base management system 10
102 infer service;
Step d6: after service robot platform 301 receives the service inferred, smart home emulation platform 20 can be obtained
The execution action parameter of the service and simulation that learn, to realize that robot can be with a kind of natural, hommization method of service
Execute service;
Step d7: during service robot platform 301 executes, the object of knowledge base management system 10 can be obtained on demand automatically
Product knowledge, environmental knowledge, to guarantee going on smoothly for service robot.
Wherein, the step d4 is related to a kind of action simulation method based on intensified learning, and method is as follows:
Movement of the smart home emulation platform 20 using in service sequences is as input, to execute the corresponding operation object of the movement
The optimal action parameter of product is as output.The judgment criteria for selecting article condition combination to complete as movement, when article condition is sent out
Raw to change, then corresponding action parameter is to execute the corresponding parameter of service action.Firstly, building article state repository H, H (i) are corresponding
The article condition combination of a movement is completed, wherein the corresponding movement of i.Therefore, in action executing process, smart home is imitative
True platform 20 can be combined by building various motion and parameter setting, so that object model is made to meet the corresponding state of H (i),
To obtain the action parameter for generating the state and needing.
The feature vector that transcoding is fixed dimension article condition is combined by building neural network, utilizes cosine similarity
The deviation for measuring state repository vector and the state vector generated after the simulation of smart home emulation platform 20, to export corresponding
Excitation value.
In conjunction with nitrification enhancement, the corresponding value function of article condition are as follows:
Vθ(s)=E [r (h)]
Wherein, V is value function, and E indicates the expectation of r (h), and θ is state parameter, and s record executes the movement and is related to article
Current state, h store article condition in different time periods, are represented byR (h) can return to the corresponding excitation of h
Value, T refer to service ending time, S (Ht) indicate the t period article condition set.
The local derviation of value function is obtained using gradient descent algorithm, and is finely adjusted to state parameter:
Wherein, the article condition distribution under p (h | θ) expression parameter θ, θ is learning parameter.
Here p=(a | s, θ) is the probability that generation acts a under softmax function output state s, and t indicates the corresponding time,
When state parameter reaches convergence, at this time Vθ(s) value tends to be maximum, and corresponding action parameter is required for completing service
Parameter.
For robot service creation method is further explicitly described, combined with Figure 1 and Figure 2, with one simply example into
Row explanation, it is assumed that Fig. 2 is that User Activity maps representation method, then H is the row crawler behavior, h1, h2, h3, h4, h5 and h6
It represents user and completes the movement that the activity needs to be implemented, M is corresponding semantic knowledge mapping template, and O is that user completes the activity
The execution article being related to, article o1, o2, o3, o4, o5 and o6 are corresponding with movement h1, h2, h3, h4, h5 and h6 respectively, need
It is noted that user is directed to activity H, the sequence of movement executed every time might not be identical, such as the habit sequence of last time
For h1 → h2 → h3 → h4 → h5 → h6, and current sequence: h1 → h4 → h3 → h5 → h2 → h6, so which results in one
A activity has corresponded to various motion sequence, and generated various motion sequence can be transmitted to smart home emulation platform 20 and be stored up
Deposit and for action sequence study.
Assuming that user is in execution activity H, it is most with sequence of movement h1 → h2 → h3 → h4 → h5 → h6 frequency of occurrence,
It is exactly frequency highest of the user according to sequence of movement h1 → h2 → h3 → h4 → h5 → h6 completion activity H appearance, then first
Smart home emulation platform 20 can learn these movement knowledge, learn user out automatically and execute the active actions sequence probability of occurrence
The sequence of movement of maximum (that is to say frequency highest), according to it is above-mentioned it is assumed that namely study to action sequence h1 → h2 → h3 →
H4 → h5 → h6 executes the action sequence of the service as robot, for example user executes " cooking coffee " this activity, then producing
Raw maximum probability action sequence will execute the sequence of " cooking coffee " this service as robot.
If the behavioral activity of user has greatly changed within a period of time (such as one week), such as: upper one week user
When execution activity H, the frequency highest that action sequence h1 → h2 → h3 → h4 → h5 → h6 occurs, and this week, action sequence h1
→ h3 → h4 → h6 → h2 → h5, then the action sequence for guidance machine people to execute the service will also will be updated.
Then, the service action sequence obtained for study, it is every that smart home emulation platform 20 is based on intensified learning simulation
The implementation procedure of a movement gets off the execution reference record that simulation obtains, these execute the group symphysis of parameter and action sequence
At the complete service knowledge of the execution service, and upload the preservation of the service knowledge 101 in data base management system 10.
Then, when the real time information and rule knowledge 102 that combine sensing system 303 to perceive have inferred clothes needed for user
Business H (such as " cooking coffee ") or the service order for receiving user's sending, then service robot platform 301, which can obtain, executes the clothes
It is dynamic can to ensure that robot can be accustomed to according to user in this way for the service knowledge (including executing parameter and action sequence) of business
Work sequence executes the service, to ensure that robot completes service role according to a kind of natural, hommization sequence.
Execute viability in service robot platform 301, required article knowledge and environmental knowledge can be on-demand from
It is obtained automatically in knowledge base management system 10, " cooking coffee " this service is such as executed, then the acquisition coffee that robot can be on-demand
The knowledge such as the belonging positions of coffee cup, current state ensure that the service order of robot carries out, and ensure that the matter of service
Amount.
The foregoing is merely preferred embodiment of the present application, are not intended to limit this application, for the skill of this field
For art personnel, various changes and changes are possible in this application.Within the spirit and principles of this application, made any to repair
Change, equivalent replacement, improvement etc., should be included within the scope of protection of this application.
Claims (10)
1. a kind of smart home system, characterized in that including smart home emulation platform, the smart home emulation platform difference
Information communication is carried out with knowledge base management system, service robot platform, the smart home emulation platform, service robot are flat
Platform distinguishes receiving sensor system information collected;
The smart home emulation platform study obtains every kind of corresponding user behavior sequence of service and is based on intensified learning mould
The implementation procedure of each movement in quasi- user behavior sequence, the execution parameter that simulation obtains record and executes ginseng for described
It is several to execute the complete service knowledge of the service with the combination producing of behavior sequence, and upload knowledge base management system preservation;
The user that the service robot platform perceives real time information according to sensing system and knowledge base management system infers
It is required service or receive user sending service order, service robot platform then obtain execute the service include execute ginseng
Several service knowledges with behavior sequence.
2. a kind of smart home system as described in claim 1, characterized in that the intelligent family based on user behavior sequence
The system of residence further includes that intelligence executes device systems, and it is logical that the intelligence execution device systems and smart home emulation platform carry out information
Believe and receives sensing system information collected.
3. a kind of smart home system as described in claim 1, characterized in that the sensing system includes behavioral activity inspection
Sensor, environmental information detection sensor and user's physical signs detection sensor are surveyed, is specifically passed in the sensing system
The measured value of sensor is all made of ontology and is expressed as semantic knowledge to it.
4. a kind of smart home system as described in claim 1, characterized in that the activity detection sensor detects real-time
Data information is after ontology completes semantic knowledge expression, the movable detection and reasoning of real-time implementation user, and is transmitted to
Smart home emulation platform learns for service knowledge;
The real time data information of the environmental information detection sensor detection is after ontology completes semantic knowledge expression, in real time
It realizes the detection and service reasoning of environment, and the service transmission of required execution to service robot platform or intelligence is executed into equipment
System completes the execution of service;
The physical signs detection sensor is used for the physiological characteristic information of real-time detection user.
5. a kind of smart home system as described in claim 1, characterized in that the knowledge base management system includes that service is known
Know library, rule-based knowledge base, article knowledge base and environmental knowledge library;
The service knowledge library includes the User Activity behavior sequence learnt and execution parameters knowledge;
Reasoning of the rule-based knowledge base for service automatically infers required service, including different when regular premise meets
Informal dress business and personalized service, the service of institute's reasoning execute device systems by service robot platform or intelligence and execute;
The article knowledge base includes the more educated description to operation article, realizes and recognizes to the profound of operation article;
The environmental knowledge library includes the knowledge description to environment, convenient for the execution of cognition and service to home environment.
6. a kind of service creation method of smart home system, characterized in that including robot service creation step, specifically:
Semantic knowledge mapping will be completed between User Activity behavior and operation article;
The User Activity behavior of perception is transmitted to smart home emulation platform and is stored;
Emulated robot in smart home emulation platform be based on User Activity historical knowledge occur maximum probability learn it is optimal out
Execute the behavior sequence, referred to herein as service;
For each movement in each service, the optimal action parameter for executing each movement is simulated based on intensified learning;
The real time information of sensor based system perception, goes out in conjunction with the rule-based reasoning in rule-based knowledge base in knowledge base management system
Service;
After service robot platform receives the service of reasoning, the service and simulation that smart home emulation platform learns are obtained
Action parameter is executed, service is executed with a kind of natural, hommization method of service;
Viability, the automatic article knowledge obtained in knowledge base management system on demand, environment are executed in service robot platform
Knowledge, to guarantee going on smoothly for service robot service execution.
7. a kind of service creation method of smart home system as claimed in claim 6, characterized in that described to be based on extensive chemical
Habit simulates the optimal action parameter for executing each movement, and its step are as follows:
Smart home emulation platform is using the movement in service sequences as input, to execute the corresponding operation article of the movement most
Excellent action parameter is as output;
The judgment criteria for selecting article condition combination to complete as movement, when article condition changes, then corresponding movement is joined
Number is the corresponding parameter of execution service action;
By constructing feature vector of the neural network by combinations of states transcoding for fixed dimension, cosine similarity is utilized to measure state
The deviation of library vector and the state vector generated after the simulation of smart home emulation platform, to export corresponding excitation value;
In conjunction with nitrification enhancement, according to the corresponding value function of article condition, the inclined of value function is obtained using gradient descent algorithm
It leads, and is parameter required for completing to service to rear corresponding action parameter is finely adjusted to state parameter.
8. a kind of service creation method of smart home system as claimed in claim 6, characterized in that select article condition group
The judgment criteria that cooperation is completed for movement needs to construct article state repository H, the corresponding article condition group for completing a movement of H (i)
Close, wherein the corresponding movement of i, in action executing process, smart home emulation platform by the combination of building various motion with
And parameter setting, to make object model meet the corresponding state of H (i), to obtain the action parameter for generating the state and needing;
The corresponding value function of the article condition are as follows:
Vθ(s)=E [r (h)]
Wherein, V is value function, and E indicates the expectation of r (h), and θ is state parameter, and s record executes the movement and is related to the current of article
State, h store article condition in different time periods, are expressed asR (h) can return to the corresponding excitation value of h, T
Refer to service ending time, S (Ht) indicate the t period article condition set;
The local derviation of value function is obtained using gradient descent algorithm, and is finely adjusted to state parameter:
Wherein, the article condition distribution under p (h | θ) expression parameter θ, θ is learning parameter;
Here p=(a | s, θ) is the probability that generation acts a under softmax function output state s, when state parameter reaches convergence
When, at this time Vθ(s) value tends to be maximum, and corresponding action parameter is parameter required for completing to service.
9. a kind of service creation method of smart home system as claimed in claim 6, characterized in that further include environment and life
Indexes Abnormality service creation step is managed, specifically:
Threshold value δ is arranged to relevant environmental parameter and physical signs respectively, when the measured value of environmental sensor or physical signs is more than
When the threshold value δ of setting, then it is defined as that environment or physical signs exception item has occurred;
Its SWRL rule is defined to environment and physical signs exception service cognitive process according to the mankind;
Based on real-time environment and physical signs information, reasoning and performing environment and physical signs exception service;
Further preferred technical solution, a kind of service creation method of smart home system further include that User Activity takes extremely
Business generation step, specifically:
Semantic knowledge mapping will be completed between User Activity behavior and operation article;
It is accustomed to setting normal activity time of the act threshold tau according to user;
Its SWRL rule is defined to crawler behavior exception service cognitive process according to the mankind;
Based on the crawler behavior and time parameter information perceived in real time, reasoning and execution activity exception service;
Semantic knowledge mapping method between the User Activity behavior and operation article are as follows:
Definition: O, which represents completion activity, need to operate article, and M indicates that the mapping template based on ontology, H indicate the semanteme of article O
Knowledge, that is, crawler behavior;
When sensor detects one of article movement that completion activity need to operate, which becomes 1 from 0,
So the numerical value 1 of the sensor describes it by the mapping template M based on ontology and acts corresponding semantic knowledge;
When perceiving a certain movement generation or the non-origination interval time is more than the time threshold τ of setting, then it is defined as having occurred
Movable exception item.
10. a kind of service creation method of smart home system as claimed in claim 6, characterized in that further include personalization
Service creation step, specifically:
Semantic knowledge mapping will be completed between User Activity behavior and operation article;
According to the similar setting personalized service time error threshold value of service
According to individual subscriber behavioural habits, personalized service SWRL rule is defined;
Based on the crawler behavior and time parameter information perceived in real time, reasoning simultaneously executes personalized service.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810804333.8A CN108983625B (en) | 2018-07-20 | 2018-07-20 | Intelligent household system and service generation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810804333.8A CN108983625B (en) | 2018-07-20 | 2018-07-20 | Intelligent household system and service generation method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108983625A true CN108983625A (en) | 2018-12-11 |
CN108983625B CN108983625B (en) | 2021-05-25 |
Family
ID=64549881
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810804333.8A Active CN108983625B (en) | 2018-07-20 | 2018-07-20 | Intelligent household system and service generation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108983625B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109634140A (en) * | 2018-12-25 | 2019-04-16 | 珠海格力电器股份有限公司 | Update method, device, unit and the computer equipment of running environment data |
CN110110245A (en) * | 2019-05-06 | 2019-08-09 | 山东大学 | Dynamic article searching method and device under a kind of home environment |
CN110989735A (en) * | 2019-11-12 | 2020-04-10 | 珠海格力电器股份有限公司 | Self-adaptive adjustment method and device for sleep environment and electronic equipment |
CN111045339A (en) * | 2019-11-21 | 2020-04-21 | 南京理工大学 | Method for describing intelligent household environment requirements based on user behaviors |
CN111338227A (en) * | 2020-05-18 | 2020-06-26 | 南京三满互联网络科技有限公司 | Electronic appliance control method and control device based on reinforcement learning and storage medium |
CN111522246A (en) * | 2020-05-09 | 2020-08-11 | 刘玉华 | Method for detecting abnormity of single sensor in intelligent home system |
CN113190012A (en) * | 2021-05-10 | 2021-07-30 | 山东大学 | Robot task autonomous planning method and system |
CN113408029A (en) * | 2021-06-22 | 2021-09-17 | 杭州群核信息技术有限公司 | Intelligent home design and simulation system |
WO2022227549A1 (en) * | 2021-04-30 | 2022-11-03 | 青岛海尔空调器有限总公司 | Safety monitoring method and apparatus for household appliance, and household appliance |
CN117955754A (en) * | 2024-03-27 | 2024-04-30 | 清华大学 | Abnormality detection method, device, equipment and storage medium of Internet of things equipment |
CN117955754B (en) * | 2024-03-27 | 2024-06-25 | 清华大学 | Abnormality detection method, device, equipment and storage medium of Internet of things equipment |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103399638A (en) * | 2013-08-08 | 2013-11-20 | 山东大学 | Understanding system of human behaviors in intelligent space and application of understanding system |
CN103592925A (en) * | 2013-11-25 | 2014-02-19 | 吉林大学 | Smart home system based on semantic fusion |
US20150113462A1 (en) * | 2012-02-24 | 2015-04-23 | Honeywell International Inc. | Generating an operational user interface for a building management system |
KR20150094408A (en) * | 2014-02-11 | 2015-08-19 | 한국전자통신연구원 | System of recognizing service in cloud environment by using IoT data |
CN104991456A (en) * | 2015-05-26 | 2015-10-21 | 北京海尔广科数字技术有限公司 | Intelligent electrical appliance control method and device |
CN105045222A (en) * | 2015-05-26 | 2015-11-11 | 北京海尔广科数字技术有限公司 | Intelligent household electrical appliance control method and device |
CN105228089A (en) * | 2015-09-30 | 2016-01-06 | 成都信汇聚源科技有限公司 | A kind of wearable device multisensor adaptation and real-time data acquisition method |
CN105425607A (en) * | 2015-12-29 | 2016-03-23 | 上海大学 | Intelligent household central control system based on multiple Agents and control method thereof |
US20170343980A1 (en) * | 2016-05-25 | 2017-11-30 | Alper Uzmezler | Edge Analytics Control Devices and Methods |
-
2018
- 2018-07-20 CN CN201810804333.8A patent/CN108983625B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150113462A1 (en) * | 2012-02-24 | 2015-04-23 | Honeywell International Inc. | Generating an operational user interface for a building management system |
CN103399638A (en) * | 2013-08-08 | 2013-11-20 | 山东大学 | Understanding system of human behaviors in intelligent space and application of understanding system |
CN103592925A (en) * | 2013-11-25 | 2014-02-19 | 吉林大学 | Smart home system based on semantic fusion |
KR20150094408A (en) * | 2014-02-11 | 2015-08-19 | 한국전자통신연구원 | System of recognizing service in cloud environment by using IoT data |
CN104991456A (en) * | 2015-05-26 | 2015-10-21 | 北京海尔广科数字技术有限公司 | Intelligent electrical appliance control method and device |
CN105045222A (en) * | 2015-05-26 | 2015-11-11 | 北京海尔广科数字技术有限公司 | Intelligent household electrical appliance control method and device |
CN105228089A (en) * | 2015-09-30 | 2016-01-06 | 成都信汇聚源科技有限公司 | A kind of wearable device multisensor adaptation and real-time data acquisition method |
CN105425607A (en) * | 2015-12-29 | 2016-03-23 | 上海大学 | Intelligent household central control system based on multiple Agents and control method thereof |
US20170343980A1 (en) * | 2016-05-25 | 2017-11-30 | Alper Uzmezler | Edge Analytics Control Devices and Methods |
Non-Patent Citations (3)
Title |
---|
宋劼: "基于语义的智能家居管理系统关键技术研究", 《中国硕士学位论文全文数据库•信息科技辑》 * |
秦海越: "基于语义的智能家居自配置系统的研究与设计", 《中国硕士学位论文全文数据库•工程科技‖辑》 * |
路飞: "智能空间环境下基于本体的机器人服务自主认知及规划", 《机器人》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109634140A (en) * | 2018-12-25 | 2019-04-16 | 珠海格力电器股份有限公司 | Update method, device, unit and the computer equipment of running environment data |
CN110110245A (en) * | 2019-05-06 | 2019-08-09 | 山东大学 | Dynamic article searching method and device under a kind of home environment |
CN110110245B (en) * | 2019-05-06 | 2021-03-16 | 山东大学 | Dynamic article searching method and device in home environment |
CN110989735A (en) * | 2019-11-12 | 2020-04-10 | 珠海格力电器股份有限公司 | Self-adaptive adjustment method and device for sleep environment and electronic equipment |
CN111045339A (en) * | 2019-11-21 | 2020-04-21 | 南京理工大学 | Method for describing intelligent household environment requirements based on user behaviors |
CN111522246A (en) * | 2020-05-09 | 2020-08-11 | 刘玉华 | Method for detecting abnormity of single sensor in intelligent home system |
CN111338227B (en) * | 2020-05-18 | 2020-12-01 | 南京三满互联网络科技有限公司 | Electronic appliance control method and control device based on reinforcement learning and storage medium |
CN111338227A (en) * | 2020-05-18 | 2020-06-26 | 南京三满互联网络科技有限公司 | Electronic appliance control method and control device based on reinforcement learning and storage medium |
WO2022227549A1 (en) * | 2021-04-30 | 2022-11-03 | 青岛海尔空调器有限总公司 | Safety monitoring method and apparatus for household appliance, and household appliance |
CN113190012A (en) * | 2021-05-10 | 2021-07-30 | 山东大学 | Robot task autonomous planning method and system |
CN113190012B (en) * | 2021-05-10 | 2022-08-12 | 山东大学 | Robot task autonomous planning method and system |
CN113408029A (en) * | 2021-06-22 | 2021-09-17 | 杭州群核信息技术有限公司 | Intelligent home design and simulation system |
CN113408029B (en) * | 2021-06-22 | 2023-08-11 | 杭州群核信息技术有限公司 | Intelligent home design and simulation system |
CN117955754A (en) * | 2024-03-27 | 2024-04-30 | 清华大学 | Abnormality detection method, device, equipment and storage medium of Internet of things equipment |
CN117955754B (en) * | 2024-03-27 | 2024-06-25 | 清华大学 | Abnormality detection method, device, equipment and storage medium of Internet of things equipment |
Also Published As
Publication number | Publication date |
---|---|
CN108983625B (en) | 2021-05-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108983625A (en) | A kind of smart home system and service creation method | |
Zhu et al. | Bridging e-health and the internet of things: The sphere project | |
US11531891B2 (en) | Cooking apparatus for determining cooked-state of cooking material and control method thereof | |
Novák et al. | Anomaly detection in user daily patterns in smart-home environment | |
CN104965552B (en) | A kind of smart home environment cooperative control method based on emotional robot and system | |
Babangida et al. | Internet of things (IoT) based activity recognition strategies in smart homes: a review | |
Doctor et al. | A fuzzy embedded agent-based approach for realizing ambient intelligence in intelligent inhabited environments | |
CN110494697A (en) | Data learning server and for generate and using its learning model method | |
KR20190096851A (en) | Vision recognition based method and device for controlling cooker | |
CN108846314A (en) | A kind of food materials identification system and food materials discrimination method based on deep learning | |
CN108710947A (en) | A kind of smart home machine learning system design method based on LSTM | |
Nathan et al. | A survey on smart homes for aging in place: Toward solutions to the specific needs of the elderly | |
CN105045234A (en) | Intelligent household energy management method based on intelligent wearable equipment behavior perception | |
CN105910225A (en) | Air conditioner load control system and method based on personnel information detection | |
CN105652677B (en) | A kind of intelligent home furnishing control method based on user behavior analysis, device and system | |
CN108446021B (en) | Application method of P300 brain-computer interface in intelligent home based on compressed sensing | |
CN109858376A (en) | A kind of intelligent desk lamp with child healthy learning supervisory role | |
CN107229262A (en) | A kind of intelligent domestic system | |
CN110119766A (en) | A kind of multiple groups close the green pepper greenhouse temperature intelligence prior-warning device of intelligent model | |
CN111694280A (en) | Control system and control method for application scene | |
CN105912632A (en) | Device service recommending method and device | |
CN114265320A (en) | Smart home control method and system for analyzing user habits based on deep learning | |
CN111141284A (en) | Intelligent building personnel thermal comfort level and thermal environment management system and method | |
KR20090007972A (en) | Method for configuring genetic code in software robot | |
CN116736734A (en) | Intelligent household equipment control method and system based on sensing network |
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 |