CN110427801A - Intelligent home furnishing control method and device, electronic equipment and non-transient storage media - Google Patents
Intelligent home furnishing control method and device, electronic equipment and non-transient storage media Download PDFInfo
- Publication number
- CN110427801A CN110427801A CN201910525188.4A CN201910525188A CN110427801A CN 110427801 A CN110427801 A CN 110427801A CN 201910525188 A CN201910525188 A CN 201910525188A CN 110427801 A CN110427801 A CN 110427801A
- Authority
- CN
- China
- Prior art keywords
- user
- enters
- drawing picture
- location drawing
- history
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000001052 transient effect Effects 0.000 title claims abstract description 8
- 230000006698 induction Effects 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 34
- 230000005484 gravity Effects 0.000 claims description 27
- 238000001514 detection method Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000004378 air conditioning Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Networks & Wireless Communication (AREA)
- Automation & Control Theory (AREA)
- Ophthalmology & Optometry (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention proposes a kind of intelligent home furnishing control method and devices, electronic equipment and non-transient storage media, are related to field of artificial intelligence, wherein this method comprises: obtaining the discrepancy location drawing picture in the space that smart home is acted on;Discrepancy location drawing picture input user is entered and left into state recognition model, corresponding user is exported and enters and leaves state;State is entered and left according to the user, it is determined whether adjusts the running parameter of the smart home.According to the technical solution of the present invention, the model detected whether into space is established in a manner of deep learning, the use habit closer to user in real life is detected than simple algorithm, so that the switch of smart home more adapts to the use demand of user, the user experience is improved.
Description
[technical field]
The present invention relates to field of artificial intelligence more particularly to a kind of intelligent home furnishing control method and device, electronics to set
Standby and non-transient storage media.
[background technique]
With the development of science and technology, smart home gradually enters into people's lives, for example, user is when into family, smart home
It can sense that user enters in family by way of infrared detection, automatically turn on then, the manual operation of user be save, to mention
Rise user experience.
However, the detection of infrared ray is affected by position and distance, if when user enters door and smart home away from
From far, or the detection dead angle of the pyroscan positioned at the smart home, then smart home can not just detect user's
It arrives and automatically turns on, the life of user can not be facilitated.
Therefore, the degree of intelligence for how further promoting smart home, becomes a technical problem to be solved urgently.
[summary of the invention]
The embodiment of the invention provides a kind of intelligent home furnishing control methods and device, electronic equipment and non-transient storage to be situated between
Matter, it is intended to solve the technical problem that infrared mode detection user in the related technology enters and leaves state inaccuracy, be able to ascend intelligence
The degree of intelligence of household further adapts to the use demand of user.
In a first aspect, the embodiment of the invention provides a kind of intelligent home furnishing control methods, comprising: obtain smart home and made
The discrepancy location drawing picture in space;Discrepancy location drawing picture input user is entered and left into state recognition model, is exported corresponding
User enters and leaves state;State is entered and left according to the user, it is determined whether adjusts the running parameter of the smart home.
In the above embodiment of the present invention, optionally, in the discrepancy position in the space that the acquisition smart home is acted on
Before the step of image, further includes: the history for obtaining the space enters and leaves location drawing picture;The location drawing is entered and left obtaining the history
In the first scheduled duration as after, detect whether the smart home gets user's operation information;It is described in testing result
In the case that smart home gets the user's operation information, determine that the history enters and leaves the corresponding user of location drawing picture
Discrepancy state is to have user to enter the space;It is that the user's operation information has not been obtained in the smart home in testing result
In the case where, determining that the history enters and leaves the corresponding user of location drawing picture to enter and leave state is that no user enters the space;
The history is entered and left into location drawing picture as input, the history is entered and left into the corresponding user of location drawing picture and enters and leaves state work
For output, training obtains the user and enters and leaves state recognition model.
In the above embodiment of the present invention, optionally, in the discrepancy position in the space that the acquisition smart home is acted on
Before the step of image, further includes: the history for obtaining the space enters and leaves location drawing picture;Judge that the history enters and leaves location drawing picture
In whether have personage and the personage whether towards the space;In the case where judging result, which is, is, gone through described in determination
It is to have user to enter the space that history, which enters and leaves the corresponding user of location drawing picture and enters and leaves state, otherwise, it determines the history goes out
Entering the corresponding user of location drawing picture to enter and leave state is that no user enters the space;The history is entered and left location drawing picture to make
For input, the history is entered and left into the corresponding user of location drawing picture and enters and leaves state as output, training obtains the user
Enter and leave state recognition model.
In the above embodiment of the present invention, optionally, in the discrepancy position in the space that the acquisition smart home is acted on
Before the step of image, further includes: the history for obtaining the space enters and leaves location drawing picture;The location drawing is entered and left obtaining the history
In the second scheduled duration as after, obtain the first gravity sensing device the first induction result and the second gravity sensing device the
Two induction results, wherein first gravity sensing device is located at outside the space, and the discrepancy position in the space is arranged in
Outside, second gravity sensing device are located in the space, and the inside of the discrepancy position in the space is arranged in;Judge institute
It states the second induction result and whether is later than the first induction result and obtain, and the second induction result and first induced junction
The difference of fruit is less than predetermined value;In the case where judging result, which is, is, determine that the history enters and leaves the corresponding institute of location drawing picture
Stating user and entering and leaving state is to have user to enter the space, otherwise, it determines the history enters and leaves the corresponding use of location drawing picture
It is that no user enters the space that family, which enters and leaves state,;The history is entered and left into location drawing picture as input, the history is entered and left
The corresponding user of location drawing picture enters and leaves state as output, and training obtains the user and enters and leaves state recognition model.
In the above embodiment of the present invention, optionally, the discrepancy location drawing for obtaining the space that smart home is acted on
The step of picture, specifically includes: obtaining the discrepancy location drawing picture in the space that the smart home is acted in real time;Or every
Third scheduled duration obtains the discrepancy location drawing picture in the space that the smart home is acted on.
Second aspect, the embodiment of the invention provides a kind of intelligent home control devices, comprising: image acquisition unit is used
In the discrepancy location drawing picture for obtaining the space that smart home is acted on;State recognition unit is entered and left, is used for the discrepancy position
Image inputs user and enters and leaves state recognition model, exports corresponding user and enters and leaves state;Execution unit, for according to the user
Discrepancy state, it is determined whether adjust the running parameter of the smart home.
In the above embodiment of the present invention, optionally, further includes: history image acquiring unit, for being obtained in described image
Before taking unit to obtain the discrepancy location drawing picture, the history for obtaining the space enters and leaves location drawing picture;Operation information detection is single
Member, for detecting whether the smart home obtains in the first scheduled duration after obtaining the history and entering and leaving location drawing picture
To user's operation information;Status determining unit is entered and left, for being that the smart home gets the user behaviour in testing result
In the case where making information, determining that the history enters and leaves the corresponding user of location drawing picture to enter and leave state is to have described in user's entrance
Space determines that the history goes out in the case where testing result is that the user's operation information has not been obtained in the smart home
Entering the corresponding user of location drawing picture to enter and leave state is that no user enters the space;Model training unit, being used for will be described
History enters and leaves location drawing picture as input, and the history is entered and left the corresponding user of location drawing picture and enters and leaves state as defeated
Out, training obtains the user and enters and leaves state recognition model.
In the above embodiment of the present invention, optionally, further includes: history image acquiring unit, for being obtained in described image
Before taking unit to obtain the discrepancy location drawing picture, the history for obtaining the space enters and leaves location drawing picture;History image judgement is single
Member, for judging the history enters and leaves in location drawing picture whether have personage and whether the personage is towards the space;It enters and leaves
Status determining unit, in the case where judging result, which is, is, determining that it is corresponding described that the history enters and leaves location drawing picture
It is to have user to enter the space that user, which enters and leaves state, otherwise, it determines the history enters and leaves the corresponding user of location drawing picture
Discrepancy state is that no user enters the space;Model training unit, for using the history enter and leave location drawing picture as input,
The history is entered and left into the corresponding user of location drawing picture and enters and leaves state as output, training obtains the user and enters and leaves state
Identification model.
In the above embodiment of the present invention, optionally, history image acquiring unit, for being obtained in described image acquiring unit
Before taking the discrepancy location drawing picture, the history for obtaining the space enters and leaves location drawing picture;Incude result acquiring unit, is used for
It obtains in the second scheduled duration after the history enters and leaves location drawing picture, obtains the first induction result of the first gravity sensing device
Result is incuded with the second of the second gravity sensing device, wherein first gravity sensing device is located at outside the space, setting
In the outside of the discrepancy position in the space, second gravity sensing device is located in the space, is arranged in the space
Discrepancy position inside;Result judging unit is incuded, for judging whether the second induction result is later than first sense
Should result obtain, and it is described second induction result and it is described first induction result difference be less than predetermined value;Discrepancy state determines
Unit enters and leaves in the case where judging result, which is, is, determining that the history enters and leaves the corresponding user of location drawing picture
State is to have user to enter the space, otherwise, it determines the history, which enters and leaves the corresponding user of location drawing picture, enters and leaves state
Enter the space for no user;Model training unit is gone through for the history to be entered and left location drawing picture as input by described
History enters and leaves the corresponding user of location drawing picture and enters and leaves state as output, and training obtains the user and enters and leaves state recognition mould
Type.
In the above embodiment of the present invention, optionally, described image acquiring unit is used for: obtaining the smart home in real time
The discrepancy location drawing picture in the space acted on;Or every third scheduled duration, obtain what the smart home was acted on
The discrepancy location drawing picture in space.
The third aspect, the embodiment of the invention provides a kind of electronic equipment, comprising: at least one processor;And with institute
State the memory of at least one processor communication connection;Wherein, be stored with can be by least one described processor for the memory
The instruction of execution, described instruction are arranged to be used for executing method described in any one of above-mentioned first aspect.
Fourth aspect, the embodiment of the invention provides a kind of non-transient storage media, are stored with computer executable instructions,
The computer executable instructions are for executing method flow described in any one of above-mentioned first aspect.
The technical problem of state inaccuracy, the above technical side are entered and left for infrared mode detection user in the related technology
Case proposes, inputs preset user by the discrepancy location drawing picture in the space for being acted on smart home and enters and leaves state recognition model
Accurately to judge that user enters and leaves state.Specifically, shooting dress can be placed in the discrepancy position in the space that smart home is acted on
It sets, obtain discrepancy location drawing picture by filming apparatus as long as having detected that user enters room, can so open automatically
Open smart home, and in the scheme for entering and leaving position and placing shooting image, relative to the scheme of infrared detection user in the related technology,
Close, the influence of not examined distance with the user distance at discrepancy position, and discrepancy position can be directly facing and shot,
Dead angle is not detected, as long as user being can be detected and entering room This move, and then start intelligence in this way, user enters room
Energy household provides service for user.
Further, in the technical scheme, location drawing picture and corresponding use are entered and left by a large amount of history in this space
Family enters and leaves state, and training has obtained user and entered and left state recognition model, as long as therefore the discrepancy location drawing picture in space is inputted user
Enter and leave state recognition model can directly obtain the conclusion for whether having user to enter space.In the technical program, with deep learning
Mode establish the model detected whether into space, than simple algorithm detect closer to user in real life
Use habit, so that the switch of smart home more adapts to the use demand of user, the user experience is improved.
[Detailed description of the invention]
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this field
For those of ordinary skill, without creative efforts, it can also be obtained according to these attached drawings other attached drawings.
Fig. 1 shows the flow chart of the intelligent home furnishing control method of one embodiment of the present of invention;
Fig. 2 shows the flow charts that the user of one embodiment of the present of invention enters and leaves the method for building up of state recognition model;
The user that Fig. 3 shows another embodiment of the invention enters and leaves the process of the method for building up of state recognition model
Figure;
The user that Fig. 4 shows yet another embodiment of the present invention enters and leaves the process of the method for building up of state recognition model
Figure;
Fig. 5 shows the block diagram of the intelligent home control device of one embodiment of the present of invention;
Fig. 6 shows the block diagram of the electronic equipment of one embodiment of the present of invention.
[specific embodiment]
For a better understanding of the technical solution of the present invention, being retouched in detail to the embodiment of the present invention with reference to the accompanying drawing
It states.
It will be appreciated that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
Its embodiment, shall fall within the protection scope of the present invention.
The term used in embodiments of the present invention is only to be not intended to be limiting merely for for the purpose of describing particular embodiments
The present invention.In the embodiment of the present invention and the "an" of singular used in the attached claims, " described " and "the"
It is also intended to including most forms, unless the context clearly indicates other meaning.
Fig. 1 shows the flow chart of the intelligent home furnishing control method of one embodiment of the present of invention.
Step 102, the discrepancy location drawing picture in the space that smart home is acted on is obtained.
Smart home includes but is not limited to all people electronic equipment used in everyday, such as individual air-conditioning, central air-conditioning, new
Wind system, television set, mobile phone etc..The room that the Spatial General 6 R that smart home is acted on is acted on by smart home, space
Discrepancy location drawing picture be the room inlet image, for example, for the air-conditioning in bedroom, the space that is acted on
For bedroom, the discrepancy location drawing picture in space is the image of bedroom inlet.
In a kind of implementation of the invention, the discrepancy location drawing picture for obtaining space specifically be can be by obtaining in real time
What the discrepancy location drawing picture in the space that the smart home is acted on was realized.Due to user enter the process in room often compared with
Short, obtaining discrepancy location drawing picture in real time without interruption can be monitored the discrepancy position in space with percentage, any to guarantee
When all to user enter and leave state be monitored, for further determining whether to adjust the running parameter of the smart home.
In another implementation of the invention, it can obtain the smart home every third scheduled duration and be acted on
Space the discrepancy location drawing picture.Primary discrepancy location drawing picture is obtained every third scheduled duration, prison can be effectively reduced
The energy consumption of control saves electric cost.
Step 104, discrepancy location drawing picture input user is entered and left into state recognition model, exports corresponding user and enters and leaves
State.
Step 106, state is entered and left according to the user, it is determined whether adjust the running parameter of the smart home.
The technical problem of state inaccuracy, the above technical side are entered and left for infrared mode detection user in the related technology
Case proposes, inputs preset user by the discrepancy location drawing picture in the space for being acted on smart home and enters and leaves state recognition model
Accurately to judge that user enters and leaves state.Specifically, shooting dress can be placed in the discrepancy position in the space that smart home is acted on
It sets, obtain discrepancy location drawing picture by filming apparatus as long as having detected that user enters room, can so open automatically
Open smart home, and in the scheme for entering and leaving position and placing shooting image, relative to the scheme of infrared detection user in the related technology,
Close, the influence of not examined distance with the user distance at discrepancy position, and discrepancy position can be directly facing and shot,
Dead angle is not detected, as long as user being can be detected and entering room This move, and then start intelligence in this way, user enters room
Energy household provides service for user.
Further, in the technical scheme, location drawing picture and corresponding use are entered and left by a large amount of history in this space
Family enters and leaves state, and training has obtained user and entered and left state recognition model, as long as therefore the discrepancy location drawing picture in space is inputted user
Enter and leave state recognition model can directly obtain the conclusion for whether having user to enter space.In the technical program, with deep learning
Mode establish the model detected whether into space, than simple algorithm detect closer to user in real life
Use habit, so that the switch of smart home more adapts to the use demand of user, the user experience is improved.
Fig. 2 shows the flow charts that the user of one embodiment of the present of invention enters and leaves the method for building up of state recognition model.
Step 202, the history for obtaining space enters and leaves location drawing picture.Space refers to intelligence here and within a context
The space of family's shelter effect.
The step for obtaining the history discrepancy location drawing picture in space can be real-time or periodically acquire, but anyway
Obtain, detect user's operation information due to defining in scheduled duration after the acquisition, as long as detecting, that is, can determine user into
Enter space, and then is used for training pattern.That is, no matter a user's operation corresponds to which or several times at time point
Point wants corresponding record, only image itself and corresponding user to the following model generation to be established effects in other words
Discrepancy state, and have nothing to do with other factors.
Step 204, in the first scheduled duration after obtaining the history and entering and leaving location drawing picture, the smart home is detected
Whether user's operation information is got.
Step 206, in the case where testing result is that the smart home gets the user's operation information, institute is determined
Stating history and entering and leaving the corresponding user of location drawing picture to enter and leave state is to have user to enter the space;It is described in testing result
In the case that the user's operation information has not been obtained in smart home, determine that the history enters and leaves the corresponding use of location drawing picture
It is that no user enters the space that family, which enters and leaves state,.
Step 208, the history is entered and left into location drawing picture as input, the history is entered and left into the corresponding institute of location drawing picture
It states user and enters and leaves state as output, training obtains the user and enters and leaves state recognition model.
In this scheme, if obtaining smart home in the first scheduled duration after history enters and leaves location drawing picture gets user behaviour
Make information, illustrates that user does enter into room, and there is use demand to smart home, therefore it is true its user can be entered and left state
Think there is user to enter the space.Conversely, being said if user's operation information has not been obtained in smart home in the first scheduled duration
Bright user does not have use demand to smart home, can regard as no user into the space.In short, will acquire history discrepancy
Whether smart home gets user's operation information in the first scheduled duration after location drawing picture, as judge user enter and leave state
Foundation why.In turn, history is entered and left into location drawing picture as input, history is entered and left into the corresponding user of location drawing picture and is gone out
Enter state to be trained as output, can be obtained and enter and leave the corresponding relationship that location drawing picture and user enter and leave state, according to obtaining
User enter and leave state recognition model, as long as by the discrepancy location drawing picture taken input, can correspond to output user enter and leave shape
State, that is to say, that whether can there is user to pass in and out space according to entering and leaving location drawing picture and directly determining, and then determine the need for intelligence
The parameter of energy household is adjusted, and passes in and out situation to adapt to new user.
The user that Fig. 3 shows another embodiment of the invention enters and leaves the process of the method for building up of state recognition model
Figure.
Step 302, the history for obtaining space enters and leaves location drawing picture.
Step 304, judge that whether there is personage in the history discrepancy location drawing picture and whether the personage is towards described
Space.
Step 306, in the case where judging result, which is, is, determine that the history enters and leaves the corresponding use of location drawing picture
It is to have user to enter the space that family, which enters and leaves state, is gone out otherwise, it determines the history enters and leaves the corresponding user of location drawing picture
Entering state is that no user enters the space.
Step 308, the history is entered and left into location drawing picture as input, the history is entered and left into the corresponding institute of location drawing picture
It states user and enters and leaves state as output, training obtains the user and enters and leaves state recognition model.
It is that the particular content of location drawing picture is entered and left by identification history to judge why user enters and leaves state in this scheme.
Can specifically be judged by face recognition, iris recognition personage whether space-oriented.
In a kind of implementation of the invention, settable filming apparatus in the discrepancy position in face space, in this way, if
Personage space-oriented, then entire positive face can all be taken enters and leaves in location drawing picture in history, therefore, passes through iris recognition, face
Whether have personage enter space, conversely, detecting that no personage enters sky if knowing detection history otherwise and enter and leave in location drawing picture
Between when, can also by personage's figure viewed from behind know otherwise, judge whether personage is leaving space, if recognizing the back of personage
Shadow determines that personage is leaving space, if the unidentified figure viewed from behind to personage, illustrates that discrepancy position at this time does not have personage's appearance.
In another implementation of the invention, settable filming apparatus is then clapped in the side of the discrepancy position in space
The history for taking the photograph device shooting enters and leaves in location drawing picture, if there is personage, personage therefore, is known by face towards image side
Other technology illustrates that personage is going into space when detecting personage towards image specified side, and if detecting personage towards specified
The opposite direction of side then illustrates that personage is leaving space;If personage is not detected, illustrate that space is passed in and out without personage, without becoming
The state of dynamic smart home.
Thus testing result can train corresponding user to enter and leave state recognition model.
The user that Fig. 4 shows yet another embodiment of the present invention enters and leaves the process of the method for building up of state recognition model
Figure.
Step 402, the history for obtaining space enters and leaves location drawing picture.
Step 404, in the second scheduled duration after obtaining the history and entering and leaving location drawing picture, the first gravity sensing is obtained
First induction result of device and the second induction result of the second gravity sensing device.
Wherein, first gravity sensing device is located at outside the space, and the outer of the discrepancy position in the space is arranged in
Side, second gravity sensing device are located in the space, and the inside of the discrepancy position in the space is arranged in.
Step 406, judge whether the second induction result is later than the first induction result and obtains, and second sense
Result and the difference of the first induction result is answered to be less than predetermined value.
Step 408, in the case where judging result, which is, is, determine that the history enters and leaves the corresponding use of location drawing picture
It is to have user to enter the space that family, which enters and leaves state, is gone out otherwise, it determines the history enters and leaves the corresponding user of location drawing picture
Entering state is that no user enters the space.
Step 410, the history is entered and left into location drawing picture as input, the history is entered and left into the corresponding institute of location drawing picture
It states user and enters and leaves state as output, training obtains the user and enters and leaves state recognition model.
In the technical scheme, the first gravity sensing device of difference outside and inside is provided in the position that enters and leaves in space
Illustrate casting aside inspection if the difference of the second induction result and the first induction result is less than predetermined value with the second gravity sensing device
In the case where surveying precision, the second induction result is close with the first induction result, it is likely that tramples generation for same user.
And the second induction result is later than the first induction result and obtains, then illustrates that this user first tramples the first gravity outside space
Sensing device, then the second gravity sensing device in space is trampled, since the first gravity sensing device and the second gravity sensing fill
It sets at the discrepancy position for being respectively positioned on space, therefore illustrate this user execution is the movement for entering this space, can be assert at this time
It is to have user to enter space that user, which enters and leaves state,.That is, by the first gravity sensing device and the second weight in this implementation
The induction result of power sensing device as judge user enter and leave state foundation why.
In addition, in conjunction with Fig. 2 to Fig. 4 embodiment it is found that can also into Fig. 4, three kinds of determining users enter and leave state by Fig. 2
Mode any two be used in combination or three kinds of combined uses, for example, will judge that the history enters and leaves in location drawing picture and whether has
Personage and the step of whether the personage is towards the space and judge whether the second induction result is later than described first and feels
Should result obtain, and it is described second induction result and it is described first induction result difference be less than predetermined value the step of, while into
Row determines that the history enters and leaves the corresponding user of location drawing picture and enters and leaves shape only in the case where judging result, which is, is
State is to have user to enter the space, otherwise, it determines the corresponding user's discrepancy state of history discrepancy location drawing picture is
No user enters the space.Thus, it is possible to more accurately judge whether user enters the space, improve to smart home
The accuracy of regulation has further adapted to the life requirement of user.
In the embodiment of Fig. 2 to Fig. 4, establishing model hair, the specific method is as follows:
The User Status identification model is using machine learning algorithm, by carrying out machine learning calculation to marker samples data
What method was handled.Wherein, establish machine learning algorithm used in the User Status identification model can for regression algorithm, with
One of machine forest decision Tree algorithms, convolutional neural networks learning algorithm, support vector machines scheduling algorithm, the present invention is for user
The machine learning algorithm that state recognition model uses is without limitation.For that clearer can understand building for User Status identification model
It is vertical, below by taking deep learning algorithm as an example, illustrate the establishment process of User Status identification model:
Firstly, obtaining a large amount of history using big data technology enters and leaves location drawing picture, and corresponding user is demarcated for it and is entered and left
Obtained history is entered and left location drawing picture as input training sample data, the user of calibration is entered and left state and is determined as by state
Export training sample data;Secondly, training sample will be inputted after obtaining input training sample data and exporting sample data
Data and output sample data make vectorization processing, obtain the corresponding input feature value of input training sample data, and output
The corresponding reference characteristic vector value of sample data;Then, input feature value and reference characteristic vector are input to initial depth
Learning training is carried out in learning network model, obtains User Status identification model.
Fig. 5 shows the block diagram of the intelligent home control device of one embodiment of the present of invention.
As shown in figure 5, the embodiment of the invention provides a kind of intelligent home control devices 500, comprising: image acquisition unit
502, for obtaining the discrepancy location drawing picture in the space that smart home is acted on;State recognition unit 504 is entered and left, being used for will be described
It enters and leaves location drawing picture input user and enters and leaves state recognition model, export corresponding user and enter and leave state;Execution unit 506, is used for
State is entered and left according to the user, it is determined whether adjusts the running parameter of the smart home.
In the above embodiment of the present invention, optionally, further includes: history image acquiring unit, for being obtained in described image
Before taking unit 502 to obtain the discrepancy location drawing picture, the history for obtaining the space enters and leaves location drawing picture;Operation information detection
Unit, for detecting whether the smart home obtains in the first scheduled duration after obtaining the history and entering and leaving location drawing picture
Get user's operation information;Status determining unit is entered and left, for being that the smart home gets the user in testing result
In the case where operation information, determine that the history enters and leaves the corresponding user of location drawing picture and enters and leaves state to there is user to enter institute
Space is stated, in the case where testing result is that the user's operation information has not been obtained in the smart home, determines the history
Entering and leaving the corresponding user of location drawing picture and entering and leaving state is that no user enters the space;Model training unit is used for institute
It states history and enters and leaves location drawing picture as input, the history is entered and left into the corresponding user of location drawing picture and enters and leaves state as defeated
Out, training obtains the user and enters and leaves state recognition model.
In the above embodiment of the present invention, optionally, further includes: history image acquiring unit, for being obtained in described image
Before taking unit 502 to obtain the discrepancy location drawing picture, the history for obtaining the space enters and leaves location drawing picture;History image judgement
Unit, for judging the history enters and leaves in location drawing picture whether have personage and whether the personage is towards the space;Out
Enter status determining unit, in the case where judging result, which is, is, determining that the history enters and leaves the corresponding institute of location drawing picture
Stating user and entering and leaving state is to have user to enter the space, otherwise, it determines the history enters and leaves the corresponding use of location drawing picture
It is that no user enters the space that family, which enters and leaves state,;Model training unit, for the history to be entered and left location drawing picture as defeated
Enter, the history is entered and left into the corresponding user of location drawing picture and enters and leaves state as output, training obtains the user and enters and leaves
State recognition model.
In the above embodiment of the present invention, optionally, history image acquiring unit, in described image acquiring unit
Before 502 obtain the discrepancy location drawing picture, the history for obtaining the space enters and leaves location drawing picture;Incude result acquiring unit,
For in the second scheduled duration after obtaining the history and entering and leaving location drawing picture, obtaining the first sense of the first gravity sensing device
Answer the second induction result of result and the second gravity sensing device, wherein first gravity sensing device is located at the space
Outside, the outside of the discrepancy position in the space is set, and second gravity sensing device is located in the space, is arranged in institute
State the inside of the discrepancy position in space;Result judging unit is incuded, for judging it is described whether the second induction result is later than
First induction result obtains, and the difference of the second induction result and the first induction result is less than predetermined value;Enter and leave shape
State determination unit, in the case where judging result, which is, is, determining that the history enters and leaves the corresponding use of location drawing picture
It is to have user to enter the space that family, which enters and leaves state, is gone out otherwise, it determines the history enters and leaves the corresponding user of location drawing picture
Entering state is that no user enters the space;Model training unit is used for using history discrepancy location drawing picture as input, will
The history enters and leaves the corresponding user's discrepancy state of location drawing picture as output, and training obtains the user and enters and leaves state knowledge
Other model.
In the above embodiment of the present invention, optionally, described image acquiring unit 502 is used for: obtaining the intelligence in real time
The discrepancy location drawing picture in the space of family's shelter effect;Or it every third scheduled duration, obtains the smart home and is made
The discrepancy location drawing picture in space.
The intelligent home control device 500 is using scheme described in any one of embodiment shown in Fig. 1 to Fig. 4, therefore,
With above-mentioned all technical effects, details are not described herein.
Fig. 6 shows the block diagram of the electronic equipment of one embodiment of the present of invention.
As shown in fig. 6, the electronic equipment 600 of one embodiment of the present of invention, including at least one processor 602;And
With the processor 604 of at least one processor 602 communication connection;Wherein, the memory be stored with can by it is described at least
The instruction that one processor 604 executes, described instruction are arranged to be used for executing any one of above-mentioned Fig. 1 to Fig. 4 embodiment institute
The scheme stated.Therefore, which has and the identical technical effect of any one of Fig. 1 to Fig. 4 embodiment, herein not
It repeats again.
The electronic equipment of the embodiment of the present invention exists in a variety of forms, including but not limited to:
(1) mobile communication equipment: the characteristics of this kind of equipment is that have mobile communication function, and to provide speech, data
Communication is main target.This Terminal Type includes: smart phone (such as iPhone), multimedia handset, functional mobile phone and low
Hold mobile phone etc..
(2) super mobile personal computer equipment: this kind of equipment belongs to the scope of personal computer, there is calculating and processing function
Can, generally also have mobile Internet access characteristic.This Terminal Type includes: PDA, MID and UMPC equipment etc., such as iPad.
(3) portable entertainment device: this kind of equipment can show and play multimedia content.Such equipment include: audio,
Video player (such as iPod), handheld device, e-book and intelligent toy and portable car-mounted navigation equipment.
(4) server: providing the equipment of the service of calculating, and the composition of server includes that processor, hard disk, memory, system are total
Line etc., server is similar with general computer architecture, but due to needing to provide highly reliable service, in processing energy
Power, stability, reliability, safety, scalability, manageability etc. are more demanding.
(5) other electronic devices with data interaction function.
In addition, computer executable instructions are stored with the embodiment of the invention provides a kind of non-transient storage media, it is described
Computer executable instructions are for executing method flow described in any one of above-mentioned Fig. 1 to Fig. 4 embodiment.
The technical scheme of the present invention has been explained in detail above with reference to the attached drawings, according to the technical solution of the present invention, with depth
The mode of habit establishes the model detected whether into space, detects closer to user in real life than simple algorithm
Use habit so that smart home switch more adapt to user use demand, the user experience is improved.
It should be appreciated that term "and/or" used herein is only a kind of incidence relation for describing affiliated partner, indicate
There may be three kinds of relationships, for example, A and/or B, can indicate: individualism A, exist simultaneously A and B, individualism B these three
Situation.In addition, character "/" herein, typicallys represent the relationship that forward-backward correlation object is a kind of "or".
It will be appreciated that though scheduled duration may be described in embodiments of the present invention using term first, second etc., but
These scheduled durations should not necessarily be limited by these terms.These terms are only used to for scheduled duration being distinguished from each other out.For example, not departing from
In the case where range of embodiment of the invention, the first scheduled duration can also be referred to as the second scheduled duration, and similarly, second is predetermined
Duration can also be referred to as the first scheduled duration.
Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination " or " in response to detection ".Similarly, depend on context, phrase " if it is determined that " or " if detection
(condition or event of statement) " can be construed to " when determining " or " in response to determination " or " when the detection (condition of statement
Or event) when " or " in response to detection (condition or event of statement) ".
In several embodiments provided by the present invention, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or group
Part can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown
Or the mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, device or unit it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
It is each that device (can be personal computer, server or network equipment etc.) or processor (Processor) execute the present invention
The part steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. it is various
It can store the medium of program code.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.
Claims (10)
1. a kind of intelligent home furnishing control method characterized by comprising
Obtain the discrepancy location drawing picture in the space that smart home is acted on;
Discrepancy location drawing picture input user is entered and left into state recognition model, corresponding user is exported and enters and leaves state;
State is entered and left according to the user, it is determined whether adjusts the running parameter of the smart home.
2. intelligent home furnishing control method according to claim 1, which is characterized in that acted in the acquisition smart home
Space discrepancy location drawing picture the step of before, further includes:
The history for obtaining the space enters and leaves location drawing picture;
In the first scheduled duration after obtaining the history and entering and leaving location drawing picture, detect whether the smart home gets use
Family operation information;
In the case where testing result is that the smart home gets the user's operation information, determine that the history enters and leaves position
Setting the corresponding user of image and entering and leaving state is to have user to enter the space;
In the case where testing result is that the user's operation information has not been obtained in the smart home, determine that the history enters and leaves
It is that no user enters the space that the corresponding user of location drawing picture, which enters and leaves state,;
The history is entered and left into location drawing picture as input, the history is entered and left into the corresponding user of location drawing picture and enters and leaves shape
State obtains the user and enters and leaves state recognition model as output, training.
3. intelligent home furnishing control method according to claim 1, which is characterized in that acted in the acquisition smart home
Space discrepancy location drawing picture the step of before, further includes:
The history for obtaining the space enters and leaves location drawing picture;
Judge that whether there is personage in the history discrepancy location drawing picture and whether the personage is towards the space;
In the case where judging result, which is, is, determine that the history enters and leaves the corresponding user's discrepancy state of location drawing picture and is
There is user to enter the space, otherwise, it determines it is useless that the history, which enters and leaves the corresponding user of location drawing picture to enter and leave state,
Family enters the space;
The history is entered and left into location drawing picture as input, the history is entered and left into the corresponding user of location drawing picture and enters and leaves shape
State obtains the user and enters and leaves state recognition model as output, training.
4. intelligent home furnishing control method according to claim 1, which is characterized in that acted in the acquisition smart home
Space discrepancy location drawing picture the step of before, further includes:
The history for obtaining the space enters and leaves location drawing picture;
In the second scheduled duration after obtaining the history and entering and leaving location drawing picture, the first sense of the first gravity sensing device is obtained
Answer the second induction result of result and the second gravity sensing device, wherein first gravity sensing device is located at the space
Outside, the outside of the discrepancy position in the space is set, and second gravity sensing device is located in the space, is arranged in institute
State the inside of the discrepancy position in space;
Judge it is described second induction result whether be later than it is described first induction result obtain, and it is described second induction result with it is described
The difference of first induction result is less than predetermined value;
In the case where judging result, which is, is, determine that the history enters and leaves the corresponding user's discrepancy state of location drawing picture and is
There is user to enter the space, otherwise, it determines it is useless that the history, which enters and leaves the corresponding user of location drawing picture to enter and leave state,
Family enters the space;
The history is entered and left into location drawing picture as input, the history is entered and left into the corresponding user of location drawing picture and enters and leaves shape
State obtains the user and enters and leaves state recognition model as output, training.
5. intelligent home furnishing control method according to any one of claim 1 to 3, which is characterized in that the acquisition intelligence
It the step of discrepancy location drawing picture in the space of family's shelter effect, specifically includes:
The discrepancy location drawing picture in the space that the smart home is acted on is obtained in real time;Or
Every third scheduled duration, the discrepancy location drawing picture in the space that the smart home is acted on is obtained.
6. a kind of intelligent home control device characterized by comprising
Image acquisition unit, for obtaining the discrepancy location drawing picture in the space that smart home is acted on;
State recognition unit is entered and left, for discrepancy location drawing picture input user to be entered and left state recognition model, output is corresponded to
User enter and leave state;
Execution unit, for entering and leaving state according to the user, it is determined whether adjust the running parameter of the smart home.
7. intelligent home control device according to claim 6, which is characterized in that further include:
History image acquiring unit is used for before described image acquiring unit obtains the discrepancy location drawing picture, described in acquisition
The history in space enters and leaves location drawing picture;
Operation information detection unit, for detecting institute in the first scheduled duration after obtaining the history and entering and leaving location drawing picture
State whether smart home gets user's operation information;
Status determining unit is entered and left, for being the case where smart home gets the user's operation information in testing result
Under, determining that the history enters and leaves the corresponding user of location drawing picture to enter and leave state is to have user to enter the space, is being detected
As a result in the case where the user's operation information having not been obtained for the smart home, determine that the history enters and leaves location drawing picture pair
It is that no user enters the space that the user answered, which enters and leaves state,;
The history is entered and left location drawing picture pair for the history to be entered and left location drawing picture as input by model training unit
The user answered enters and leaves state as output, and training obtains the user and enters and leaves state recognition model.
8. intelligent home control device according to claim 6, which is characterized in that further include:
History image acquiring unit is used for before described image acquiring unit obtains the discrepancy location drawing picture, described in acquisition
The history in space enters and leaves location drawing picture;
History image judging unit, for judging the history enters and leaves in location drawing picture whether have personage and the personage
Towards the space;
Status determining unit is entered and left, in the case where judging result, which is, is, determining that the history enters and leaves location drawing picture pair
It is to have user to enter the space that the user answered, which enters and leaves state, otherwise, it determines history discrepancy location drawing picture is corresponding
It is that no user enters the space that the user, which enters and leaves state,;
The history is entered and left location drawing picture pair for the history to be entered and left location drawing picture as input by model training unit
The user answered enters and leaves state as output, and training obtains the user and enters and leaves state recognition model.
9. a kind of electronic equipment characterized by comprising at least one processor;And it is logical at least one described processor
Believe the memory of connection;
Wherein, the memory is stored with the instruction that can be executed by least one described processor, and described instruction is arranged to use
Method described in any one of execution the claims 1 to 5.
10. a kind of non-transient storage media, which is characterized in that be stored with computer executable instructions, the computer is executable
Instruction is for executing the method flow as described in any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910525188.4A CN110427801A (en) | 2019-06-18 | 2019-06-18 | Intelligent home furnishing control method and device, electronic equipment and non-transient storage media |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910525188.4A CN110427801A (en) | 2019-06-18 | 2019-06-18 | Intelligent home furnishing control method and device, electronic equipment and non-transient storage media |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110427801A true CN110427801A (en) | 2019-11-08 |
Family
ID=68407745
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910525188.4A Pending CN110427801A (en) | 2019-06-18 | 2019-06-18 | Intelligent home furnishing control method and device, electronic equipment and non-transient storage media |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110427801A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112686112A (en) * | 2020-12-23 | 2021-04-20 | 泰州国安医疗用品有限公司 | Energy-saving heating operation control platform |
CN114005210A (en) * | 2021-09-24 | 2022-02-01 | 珠海格力电器股份有限公司 | Safety protection method and safety protection device |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105068515A (en) * | 2015-07-16 | 2015-11-18 | 华南理工大学 | Intelligent household equipment voice control method based on self-learning algorithm |
WO2016201790A1 (en) * | 2015-06-19 | 2016-12-22 | 宇龙计算机通信科技(深圳)有限公司 | Control method, apparatus, and system, and smart home control center device and terminal |
-
2019
- 2019-06-18 CN CN201910525188.4A patent/CN110427801A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016201790A1 (en) * | 2015-06-19 | 2016-12-22 | 宇龙计算机通信科技(深圳)有限公司 | Control method, apparatus, and system, and smart home control center device and terminal |
CN105068515A (en) * | 2015-07-16 | 2015-11-18 | 华南理工大学 | Intelligent household equipment voice control method based on self-learning algorithm |
Non-Patent Citations (1)
Title |
---|
杨连池;林春婷;: "自动适配多种设备的智能遥控器设计与实现", 物联网技术, no. 12 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112686112A (en) * | 2020-12-23 | 2021-04-20 | 泰州国安医疗用品有限公司 | Energy-saving heating operation control platform |
CN112686112B (en) * | 2020-12-23 | 2021-10-26 | 陈荣坤 | Energy-saving heating operation control platform |
CN114005210A (en) * | 2021-09-24 | 2022-02-01 | 珠海格力电器股份有限公司 | Safety protection method and safety protection device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110291489B (en) | Computationally efficient human identification intelligent assistant computer | |
KR101803081B1 (en) | Robot for store management | |
CN103109244B (en) | For object tracking and the method and apparatus of identification | |
CN107527615B (en) | Information processing method, device, equipment, system and server | |
CN110176226A (en) | A kind of speech recognition and speech recognition modeling training method and device | |
CN107728482A (en) | Control system, control process method and device | |
Dorfan et al. | Tree-based recursive expectation-maximization algorithm for localization of acoustic sources | |
CN110489952A (en) | Identity authentication method, device and user equipment | |
CN110741387B (en) | Face recognition method and device, storage medium and electronic equipment | |
EP3671441A1 (en) | Application management method and apparatus, storage medium, and electronic device | |
CN109977731A (en) | A kind of recognition methods of scene, identification equipment and terminal device | |
CN109741747B (en) | Voice scene recognition method and device, voice control method and device and air conditioner | |
CN107360157A (en) | A kind of user registering method, device and intelligent air conditioner | |
CN105429969A (en) | User identity verification method and equipment | |
CN110930987B (en) | Audio processing method, device and storage medium | |
CN111240217B (en) | State detection method and device, electronic equipment and storage medium | |
CN110427801A (en) | Intelligent home furnishing control method and device, electronic equipment and non-transient storage media | |
CN108536027B (en) | Intelligent home control method and device and server | |
CN111930336A (en) | Volume adjusting method and device of audio device and storage medium | |
CN110908340A (en) | Smart home control method and device | |
CN109994112A (en) | Control method, server, speech recognition apparatus and the medium of speech recognition apparatus | |
CN113611318A (en) | Audio data enhancement method and related equipment | |
CN108959889A (en) | A kind of Accreditation System and method of intelligent appliance | |
CN114859749A (en) | Intelligent home management method and system based on Internet of things | |
CN105848061B (en) | Control method and electronic equipment |
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 |