CN107680278A - Control method and device of purifier - Google Patents
Control method and device of purifier Download PDFInfo
- Publication number
- CN107680278A CN107680278A CN201710868776.9A CN201710868776A CN107680278A CN 107680278 A CN107680278 A CN 107680278A CN 201710868776 A CN201710868776 A CN 201710868776A CN 107680278 A CN107680278 A CN 107680278A
- Authority
- CN
- China
- Prior art keywords
- clarifier
- photo
- pattern information
- human
- predeterminable area
- 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 61
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 238000003860 storage Methods 0.000 claims description 21
- 238000001514 detection method Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 abstract description 11
- 230000000694 effects Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000004590 computer program Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000746 purification Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000006213 oxygenation reaction Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a control method and a control device of a purifier. The method comprises the following steps: photographing a target object to obtain a picture, wherein the target object is an object using a purifier; analyzing the photo by using a first model, and determining mode information corresponding to a target object on the photo, wherein the mode information is information of an operation mode of a purifier when the target object uses the purifier, the first model is trained by machine learning by using multiple groups of data, and each group of data in the multiple groups of data at least comprises: a picture of the object and mode information corresponding to the object; and the purifier is controlled to operate based on the mode information corresponding to the target object, so that the problems that the control mode of the purifier in the related technology is single in function and the user experience degree is low are solved, the control mode of the purifier is enriched, and the effect of the user experience degree is improved.
Description
Technical field
The application is related to cleaning equipment field, in particular to the control method and device of a kind of clarifier.
Background technology
At present, as the change of surrounding air, increasing clarifier enter into the life of people, generally, clarifier
Mode of operation is set in advance, is run according to the pattern of the selection of user, however, the control mode function is single, is used
Family Experience Degree is relatively low.
It is single for the control mode function of clarifier in correlation technique, the problem of user experience is relatively low, at present not yet
It is proposed effective solution.
The content of the invention
The main purpose of the application is to provide a kind of control method of clarifier, to solve clarifier in correlation technique
The problem of control mode function is single, and user experience is relatively low.
To achieve these goals, according to the one side of the application, there is provided a kind of control method of clarifier.The party
Method includes：Destination object is taken pictures to obtain photo, wherein, destination object is the object using clarifier；Use the first mould
Type is analyzed photo, determines pattern information corresponding to destination object on photo, wherein, pattern information is that destination object uses
The information of clarifier operational mode during clarifier, the first model is trained using multi-group data by machine learning, multigroup
Every group of data in data comprise at least：Pattern information corresponding to the photo and object of object；And based on destination object pair
The pattern information control clarifier operation answered.
Further, analyzed using the first model comparison piece, determine that pattern corresponding to destination object is believed on photo
Before breath, this method also includes：The human body biological characteristics of multiple objects are gathered, wherein, each object in multiple objects is to make
With the object of clarifier, comprised at least in human body biological characteristics：Face information；Identified by the human body biological characteristics of each object
Age stratum belonging to the object；The pattern information selected when gathering each object using clarifier；To including each object
Belonging to the photo of human body biological characteristics, the object age stratum with the object using clarifier when the pattern information that selects pass through
Machine learning is trained, and creates the first model.
Further, after based on pattern information control clarifier operation corresponding to destination object, this method also includes：
Currently it whether there is human object in detection predeterminable area, wherein, predeterminable area is the region that air is purified when clarifier is run；
If detecting and human object being there is currently no in predeterminable area, control clarifier is out of service.
Further, after currently whether there is human object in detection predeterminable area, this method also includes：If detection
Human object is there is currently in predeterminable area, the human object in predeterminable area is taken pictures, obtains current photo；Ought
Preceding photo is analyzed with photo, judges whether include destination object in the human object in current preset region；If preset areas
Do not include destination object in human object in domain, current photo is analyzed using the first model, determined in current photo
Human object corresponding to pattern information；And clarifier is controlled based on pattern information corresponding to the human object in current photo
Operation.
Further, if the human object in current photo is multiple objects, multiple objects include the first object and the
Two objects, wherein, the priority level of the first object is higher than the priority level of the second object, if in the human object in predeterminable area
Do not include destination object, current photo is analyzed using the first model, determine corresponding to the human object in current photo
Pattern information includes：The first object in current photo is analyzed using the first model, determines in current photo first pair
As corresponding pattern information；Included based on pattern information control clarifier operation corresponding to object in current photo：Based on current
Pattern information control clarifier operation corresponding to first object in photo.
To achieve these goals, according to the another aspect of the application, there is provided a kind of control device of clarifier.The dress
Put including：Acquiring unit, for being taken pictures to obtain photo to destination object, wherein, destination object is pair using clarifier
As；Analytic unit, for being analyzed using the first model comparison piece, pattern information corresponding to destination object on photo is determined,
Wherein, pattern information is the information of clarifier operational mode when destination object uses clarifier, and the first model is to use multigroup number
According to what is trained by machine learning, every group of data in multi-group data comprise at least：Corresponding to the photo and object of object
Pattern information；And first control unit, for based on pattern information control clarifier operation corresponding to destination object.
Further, the device also includes：First collecting unit, for gathering the human body biological characteristics of multiple objects, its
In, each object in multiple objects is the object using clarifier, is comprised at least in human body biological characteristics：Face information；Know
Other unit, for identifying the age stratum belonging to the object by the human body biological characteristics of each object；Second collecting unit, use
The pattern information selected when each object is gathered using clarifier；Training unit, for being given birth to the human body including each object
Belonging to the photo of thing feature, the object age stratum with the object using clarifier when the pattern information that selects pass through engineering
Habit is trained, and creates the first model.
Further, the device also includes：Detection unit, currently it whether there is human body pair for detecting in predeterminable area
As, wherein, predeterminable area is the region that air is purified when clarifier is run；Second control unit, if for detecting preset areas
Human object is there is currently no in domain, control clarifier is out of service.
To achieve these goals, according to the another aspect of the application, there is provided a kind of storage medium, it is characterised in that
Storage medium includes the program of storage, wherein, program performs the control method of the clarifier of above-mentioned any one.
To achieve these goals, according to the another aspect of the application, there is provided a kind of processor, it is characterised in that place
Reason device is used for operation program, wherein, program performs the control method of the clarifier of above-mentioned any one when running.
By the application, using following steps：Destination object is taken pictures to obtain photo, wherein, destination object is to make
With the object of clarifier；Analyzed using the first model comparison piece, determine pattern information corresponding to destination object on photo, its
In, pattern information is the information of clarifier operational mode when destination object uses clarifier, and the first model is to use multi-group data
Trained by machine learning, every group of data in multi-group data comprise at least：Mould corresponding to the photo and object of object
Formula information；And based on pattern information control clarifier operation corresponding to destination object, solves clarifier in correlation technique
The problem of control mode function is single, and user experience is relatively low.The application uses the first mould by being taken pictures to destination object
Type is analyzed photo, pattern information corresponding to destination object on photo is determined, based on pattern information corresponding to destination object
Clarifier operation is controlled, has reached abundant clarifier control mode, has lifted the effect of user experience.
Brief description of the drawings
The accompanying drawing for forming the part of the application is used for providing further understanding of the present application, the schematic reality of the application
Apply example and its illustrate to be used to explain the application, do not form the improper restriction to the application.In the accompanying drawings：
Fig. 1 is the flow chart of the control method of the clarifier provided according to the embodiment of the present application；And
Fig. 2 is the schematic diagram of the control device of the clarifier provided according to the embodiment of the present application.
Embodiment
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
In order that those skilled in the art more fully understand application scheme, below in conjunction with the embodiment of the present application
Accompanying drawing, the technical scheme in the embodiment of the present application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application part, rather than whole embodiments.Based on the embodiment in the application, ordinary skill people
The every other embodiment that member is obtained under the premise of creative work is not made, it should all belong to the model of the application protection
Enclose.
It should be noted that term " first " in the description and claims of this application and above-mentioned accompanying drawing, "
Two " etc. be for distinguishing similar object, without for describing specific order or precedence.It should be appreciated that so use
Data can exchange in the appropriate case, so as to embodiments herein described herein.In addition, term " comprising " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing series of steps or unit
Process, method, system, product or equipment are not necessarily limited to those steps clearly listed or unit, but may include without clear
It is listing to Chu or for the intrinsic other steps of these processes, method, product or equipment or unit.
According to embodiments herein, there is provided a kind of control method of clarifier.
Fig. 1 is the flow chart according to the control method of the clarifier of the embodiment of the present application.As shown in figure 1, this method includes
Following steps：
Step S101, destination object is taken pictures to obtain photo, wherein, destination object is the object using clarifier.
Optionally, in order to be taken pictures in real time to destination object, in one embodiment, mesh of the clarifier to residing space
Mark object activity region periodically take pictures, for example, carrying out once photo taking every 10 minutes.In another embodiment, purify
Whether device has destination object by infrared detection equipment come detected target object activity space, if detecting with the presence of destination object
Then taken pictures, for example, in clarifier bottom emission parallel to the yi word pattern infrared ray on ground, and examined by infrared pick-up head
Survey personnel area infrared view, in the presence of having destination object, yi word pattern infrared ray can be irradiated to destination object formed it is red
Outside line hot spot, infrared pick-up head detect that infrared ray hot spot is then judged as that clarifier is to destination object with the presence of destination object
Taken pictures.
It should be noted that destination object is optionally pre-set when using clarifier according to self-demand or hobby
The mode of operation of clarifier.
Step S102, analyzed using the first model comparison piece, determine pattern information corresponding to destination object on photo,
Wherein, pattern information is the information of clarifier operational mode when destination object uses clarifier, and the first model is to use multigroup number
According to what is trained by machine learning, every group of data in multi-group data comprise at least：Corresponding to the photo and object of object
Pattern information.
Optionally, in order to more accurately analyze photo, before the first model comparison piece is analyzed, control
Piece is pre-processed.In one embodiment, the facial image in photo is extracted, the first model is only analyzed the face in photo
Image, only analyze the information that is included of face, optionally, detect face in photo whether face clarifier, i.e., be in photo
It is no to include the face image of destination object, or judge the face image for not including destination object in photo, then clarifier is again
Destination object is taken pictures.In another embodiment, the human body information in photo is extracted, the first model is only analyzed the people in photo
The information that body is included, the information that human body is included may include height, colour of skin build and face information etc..
It should be noted that it is optional, when multiple human objects in photo be present, the nearest people of chosen distance clarifier
Body object is destination object.
Optionally, in order to create the first model, analyzed using the first model comparison piece, determine target pair on photo
Before corresponding pattern information, this method also includes：The human body biological characteristics of multiple objects are gathered, wherein, in multiple objects
Each object be object using clarifier, comprise at least in human body biological characteristics：Face information；Pass through the people of each object
Age stratum belonging to the body living things feature recognition object；The pattern information selected when gathering each object using clarifier；It is right
Belonging to the photo of human body biological characteristics including each object, the object age stratum and the object using clarifier when select
Pattern information be trained by machine learning, create the first model.
It should be noted that human body biological characteristics are the spy included in the photo used for training and creating the first model
Reference ceases, and face information can include facial contour, the shape of face and distribution, and Skin Color Information etc..Optionally, human body is given birth to
Thing feature may also include human body information in addition to face information, and human body information may include height, build, four limbs length ratio
Deng.Pattern information is the clarifier mode of operation that object selects according to self-demand, and clarifier mode of operation may include a variety of moulds
Formula, such as strong wind operational mode, small wind operational mode, automatic running pattern, humidifying mode, oxygenation pattern and negative ion mode
Deng.
Step S103, based on pattern information control clarifier operation corresponding to destination object.
Clarifier automatically selects mode of operation corresponding with destination object by judging destination object, makes clarifier can be with
In the case where user is not operated manually to clarifier, the mode of operation corresponding to active user is automatically selected, is enriched
The control mode of clarifier.
Alternatively,, should after based on pattern information control clarifier operation corresponding to destination object in order to save the energy
Method also includes：Currently it whether there is human object in detection predeterminable area, wherein, predeterminable area is that clarifier purifies when running
The region of air；If detecting and human object being there is currently no in predeterminable area, control clarifier is out of service.
It should be noted that in one embodiment, detected by analyzing the photo of clarifier collection in predeterminable area
With the presence or absence of human object, optionally, clarifier carries out periodically taking pictures to predeterminable area.In another embodiment, purify
Device detects whether predeterminable area has human object by infrared detection equipment, is controlled if detecting that no human object is present net
It is out of service to change device, for example, in clarifier bottom emission parallel to the yi word pattern infrared ray on ground, and pass through infrared pick-up head
The infrared view of predeterminable area is detected, in the presence of having human object, yi word pattern infrared ray can be irradiated to human object and be formed
Infrared ray hot spot, therefore, when in the infrared view that infrared ray camera detects predeterminable area without infrared ray hot spot exist then
It is judged as that human object is not present, control clarifier is out of service.
Alternatively, in order to select mode of operation according to destination object in time, currently whether deposited in detection predeterminable area
After human object, this method also includes：Human object is there is currently in predeterminable area if detecting, in predeterminable area
Human object is taken pictures, and obtains current photo；Current photo and photo are analyzed, judge the people in current preset region
Whether include destination object in body object；If not including destination object in the human object in predeterminable area, the first model is used
Current photo is analyzed, determines pattern information corresponding to the human object in current photo；And based in current photo
Human object corresponding to pattern information control clarifier operation.
It should be noted that judge whether the purpose for including destination object is for human object in current preset region, when
Clarifier mode of operation and after running according to target object recognition, if human body target in predeterminable area still be present, but mesh
Mark object has left predeterminable area, then the mode of operation selected before clarifier is not suitable for human body mesh present in predeterminable area
Mark, therefore when detecting that the human object in current preset region does not include destination object, then current photo is carried out again
Analysis, redefines the destination object in current photo, and selects pattern information control purification corresponding to current destination object
Device is run.
Alternatively, in order to more accurately determine destination object, if the human object in current photo is multiple objects,
Multiple objects include the first object and the second object, wherein, the priority level of the first object is higher than the priority level of the second object,
If not including destination object in the human object in predeterminable area, current photo is analyzed using the first model, it is determined that working as
Pattern information corresponding to human object in preceding photo includes：The first object in current photo is divided using the first model
Analysis, determines pattern information corresponding to the first object in current photo；Controlled based on pattern information corresponding to object in current photo
Clarifier operation includes：Based on pattern information control clarifier operation corresponding to the first object in current photo.
It should be noted that priority level determines according to specified conditions, for example, according to human object and clarifier away from
From priority level is judged, the priority level of the human object near apart from clarifier is higher than the human object remote apart from clarifier
Priority level.
The control method for the clarifier that the embodiment of the present application provides, by being taken pictures to obtain photo to destination object, its
In, destination object is the object using clarifier；Analyzed using the first model comparison piece, determine destination object pair on photo
The pattern information answered, wherein, pattern information is the information of clarifier operational mode when destination object uses clarifier, the first model
Trained using multi-group data by machine learning, every group of data in multi-group data comprise at least：The photo of object
With object corresponding to pattern information；And based on pattern information control clarifier operation corresponding to destination object, solves correlation
The problem of control mode function of clarifier is single in technology, and user experience is relatively low, and then the control of abundant clarifier
Mode, lift the effect of user experience.
It should be noted that can be in such as one group of computer executable instructions the flow of accompanying drawing illustrates the step of
Performed in computer system, although also, show logical order in flow charts, in some cases, can be with not
The order being same as herein performs shown or described step.
The embodiment of the present application additionally provides a kind of control device of clarifier, it is necessary to illustrate, the embodiment of the present application
The control device of clarifier can be used for performing the control method for clarifier that the embodiment of the present application is provided.Below to this
The control device for the clarifier that application embodiment provides is introduced.
Fig. 2 is the schematic diagram according to the control device of the clarifier of the embodiment of the present application.As shown in Fig. 2 the device includes：
Acquiring unit 10, the control unit 30 of analytic unit 20 and first.
Specifically, acquiring unit 10, for being taken pictures to obtain photo to destination object, wherein, destination object is use
The object of clarifier；Analytic unit 20, for being analyzed using the first model comparison piece, determine that destination object is corresponding on photo
Pattern information, wherein, pattern information is the information of clarifier operational mode when destination object uses clarifier, and the first model is
Trained using multi-group data by machine learning, every group of data in multi-group data comprise at least：The photo of object and
Pattern information corresponding to object；And first control unit 30, for based on pattern information control purification corresponding to destination object
Device is run.
Alternatively, the device also includes：First collecting unit, for gathering the human body biological characteristics of multiple objects, wherein,
Each object in multiple objects is the object using clarifier, is comprised at least in human body biological characteristics：Face information；Identification is single
Member, for identifying the age stratum belonging to the object by the human body biological characteristics of each object；Second collecting unit, for adopting
The pattern information selected when collecting each object using clarifier；Training unit, for special to the human-body biological including each object
Belonging to the photo of sign, the object age stratum with the object using clarifier when the pattern information that selects entered by machine learning
Row training, creates the first model.
Alternatively, the device also includes：Detection unit, currently it whether there is human object for detecting in predeterminable area,
Wherein, predeterminable area is the region that air is purified when clarifier is run；Second control unit, if for detecting in predeterminable area
Human object is there is currently no, control clarifier is out of service.
The control device for the clarifier that the embodiment of the present application provides, to destination object take pictures by acquiring unit 10
To photo, wherein, destination object is the object using clarifier；Analytic unit 20 is analyzed using the first model comparison piece,
Pattern information corresponding to destination object on photo is determined, wherein, pattern information is that clarifier is transported when destination object uses clarifier
The information of row mode, the first model are trained using multi-group data by machine learning, every group of data in multi-group data
Comprise at least：Pattern information corresponding to the photo and object of object；And first control unit 30 it is corresponding based on destination object
Pattern information control clarifier operation, it is single to solve the control mode function of clarifier in correlation technique, user experience
The problem of relatively low, and then abundant clarifier control mode, lift the effect of user experience.
The control device of clarifier includes processor and memory, and above-mentioned acquiring unit 10, analytic unit 20 and first are controlled
The grade of unit 30 processed stores in memory as program unit, by the said procedure list of computing device storage in memory
Member realizes corresponding function.
Kernel is included in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can set one
Or more, clarifier control mode is enriched by adjusting kernel parameter, lifts user experience.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/
Or the form such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM), memory includes at least one deposit
Store up chip.
The embodiments of the invention provide a kind of storage medium, program is stored thereon with, it is real when the program is executed by processor
The control method of existing clarifier.
The embodiments of the invention provide a kind of processor, processor is used for operation program, wherein, performed when program is run net
Change the control method of device.
The embodiments of the invention provide a kind of equipment, equipment includes processor, memory and storage on a memory and can
The program run on a processor, following steps are realized during computing device program：Destination object is taken pictures to obtain photo,
Wherein, destination object is the object using clarifier；Analyzed using the first model comparison piece, determine destination object on photo
Corresponding pattern information, wherein, pattern information is the information of clarifier operational mode when destination object uses clarifier, the first mould
Type is trained using multi-group data by machine learning, and every group of data in multi-group data comprise at least：The photograph of object
Pattern information corresponding to piece and object；And based on pattern information control clarifier operation corresponding to destination object.
Analyzed, determined on photo before pattern information corresponding to destination object using the first model comparison piece, should
Method also includes：The human body biological characteristics of multiple objects are gathered, wherein, each object in multiple objects is to use clarifier
Object, comprise at least in human body biological characteristics：Face information；Identified by the human body biological characteristics of each object belonging to the object
Age stratum；The pattern information selected when gathering each object using clarifier；It is special to the human-body biological including each object
Belonging to the photo of sign, the object age stratum with the object using clarifier when the pattern information that selects entered by machine learning
Row training, creates the first model.
After based on pattern information control clarifier operation corresponding to destination object, this method also includes：Detection is default
Currently it whether there is human object in region, wherein, predeterminable area is the region that air is purified when clarifier is run；If detect
Human object is there is currently no in predeterminable area, control clarifier is out of service.
After currently whether there is human object in detection predeterminable area, this method also includes：If detect preset areas
Human object is there is currently in domain, the human object in predeterminable area is taken pictures, obtains current photo；By current photo with
Photo is analyzed, and judges whether include destination object in the human object in current preset region；If the people in predeterminable area
Do not include destination object in body object, current photo is analyzed using the first model, determine the human body pair in current photo
As corresponding pattern information；And based on pattern information control clarifier operation corresponding to the human object in current photo.
If the human object in current photo is multiple objects, multiple objects include the first object and the second object, its
In, the priority level of the first object is higher than the priority level of the second object, if not including mesh in the human object in predeterminable area
Object is marked, current photo is analyzed using the first model, determines pattern information corresponding to the human object in current photo
Including：The first object in current photo is analyzed using the first model, determined in current photo corresponding to the first object
Pattern information；Included based on pattern information control clarifier operation corresponding to object in current photo：Based in current photo
Pattern information control clarifier operation corresponding to one object.Equipment herein can be server, PC, PAD, mobile phone etc..
Present invention also provides a kind of computer program product, when being performed on data processing equipment, is adapted for carrying out just
The program of beginningization there are as below methods step：Destination object is taken pictures to obtain photo, wherein, destination object is to use clarifier
Object；Analyzed using the first model comparison piece, determine pattern information corresponding to destination object on photo, wherein, pattern
Information is the information of clarifier operational mode when destination object uses clarifier, and the first model is to pass through machine using multi-group data
What learning training went out, every group of data in multi-group data comprise at least：Pattern information corresponding to the photo and object of object；With
And based on pattern information control clarifier operation corresponding to destination object.
Analyzed, determined on photo before pattern information corresponding to destination object using the first model comparison piece, should
Method also includes：The human body biological characteristics of multiple objects are gathered, wherein, each object in multiple objects is to use clarifier
Object, comprise at least in human body biological characteristics：Face information；Identified by the human body biological characteristics of each object belonging to the object
Age stratum；The pattern information selected when gathering each object using clarifier；It is special to the human-body biological including each object
Belonging to the photo of sign, the object age stratum with the object using clarifier when the pattern information that selects entered by machine learning
Row training, creates the first model.
After based on pattern information control clarifier operation corresponding to destination object, this method also includes：Detection is default
Currently it whether there is human object in region, wherein, predeterminable area is the region that air is purified when clarifier is run；If detect
Human object is there is currently no in predeterminable area, control clarifier is out of service.
After currently whether there is human object in detection predeterminable area, this method also includes：If detect preset areas
Human object is there is currently in domain, the human object in predeterminable area is taken pictures, obtains current photo；By current photo with
Photo is analyzed, and judges whether include destination object in the human object in current preset region；If the people in predeterminable area
Do not include destination object in body object, current photo is analyzed using the first model, determine the human body pair in current photo
As corresponding pattern information；And based on pattern information control clarifier operation corresponding to the human object in current photo.
If the human object in current photo is multiple objects, multiple objects include the first object and the second object, its
In, the priority level of the first object is higher than the priority level of the second object, if not including mesh in the human object in predeterminable area
Object is marked, current photo is analyzed using the first model, determines pattern information corresponding to the human object in current photo
Including：The first object in current photo is analyzed using the first model, determined in current photo corresponding to the first object
Pattern information；Included based on pattern information control clarifier operation corresponding to object in current photo：Based in current photo
Pattern information control clarifier operation corresponding to one object..
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, the application can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the application can use the computer for wherein including computer usable program code in one or more
The computer program production that usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application be with reference to according to the method, apparatus of the embodiment of the present application and the flow chart of computer program product and/or
Block diagram describes.It should be understood that can by each flow in computer program instructions implementation process figure and/or block diagram and/or
Square frame and the flow in flow chart and/or block diagram and/or the combination of square frame.These computer program instructions can be provided to arrive
All-purpose computer, special-purpose computer, the processor of Embedded Processor or other programmable data processing devices are to produce one
Machine so that produced by the instruction of computer or the computing device of other programmable data processing devices and flowed for realizing
The device for the function of being specified in one flow of journey figure or multiple flows and/or one square frame of block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and internal memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/
Or the form such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moved
State random access memory (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, the information that can be accessed by a computing device available for storage.Define, calculate according to herein
Machine computer-readable recording medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludability
Comprising so that process, method, commodity or equipment including a series of elements not only include those key elements, but also wrapping
Include the other element being not expressly set out, or also include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including key element
Other identical element in process, method, commodity or equipment also be present.
It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer program product.
Therefore, the application can be using the embodiment in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Form.Deposited moreover, the application can use to can use in one or more computers for wherein including computer usable program code
The shape for the computer program product that storage media is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
Embodiments herein is these are only, is not limited to the application.To those skilled in the art,
The application can have various modifications and variations.All any modifications made within spirit herein and principle, equivalent substitution,
Improve etc., it should be included within the scope of claims hereof.
Claims (10)
- A kind of 1. control method of clarifier, it is characterised in that including：Destination object is taken pictures to obtain photo, wherein, the destination object is the object using clarifier；The photo is analyzed using the first model, determines pattern information corresponding to destination object on the photo, wherein, The pattern information is the information of the clarifier operational mode when destination object uses the clarifier, first mould Type is trained using multi-group data by machine learning, and every group of data in the multi-group data comprise at least：Object Photo and the object corresponding to pattern information；AndThe clarifier operation is controlled based on pattern information corresponding to the destination object.
- 2. according to the method for claim 1, it is characterised in that the photo is being analyzed using the first model, really On the fixed photo before pattern information corresponding to destination object, methods described also includes：The human body biological characteristics of multiple objects are gathered, wherein, each object in the multiple object is to use the clarifier Object, comprise at least in the human body biological characteristics：Face information；The age stratum belonging to the object is identified by the human body biological characteristics of each object；The pattern information selected when gathering each object using the clarifier；Belonging to photo, the object to the human body biological characteristics including each object age stratum and the object use institute State the pattern information selected during clarifier to be trained by machine learning, create first model.
- 3. according to the method for claim 1, it is characterised in that controlled based on pattern information corresponding to the destination object After the clarifier operation, methods described also includes：Currently it whether there is human object in detection predeterminable area, wherein, the predeterminable area is that the clarifier is net when running Change the region of air；If detecting in the predeterminable area and there is currently no human object, control the clarifier out of service.
- 4. according to the method for claim 3, it is characterised in that currently whether there is human object in detection predeterminable area Afterwards, methods described also includes：If detecting in the predeterminable area and there is currently human object, the human object in the predeterminable area is clapped According to obtaining current photo；The current photo and the photo are analyzed, judge whether wrapped in the human object in presently described predeterminable area Include the destination object；If not including the destination object in the human object in the predeterminable area, using first model to described current Photo is analyzed, and determines pattern information corresponding to the human object in the current photo；AndThe clarifier operation is controlled based on pattern information corresponding to the human object in the current photo.
- 5. according to the method for claim 4, it is characterised in that if the human object in the current photo is multiple objects When, the multiple object includes the first object and the second object, wherein, the priority level of first object is higher than described second The priority level of object,If not including the destination object in the human object in the predeterminable area, using first model to described current Photo is analyzed, and determines that pattern information corresponding to the human object in the current photo includes：Use first model The first object in the current photo is analyzed, determines pattern information corresponding to the first object in the current photo；The clarifier operation is controlled to include based on pattern information corresponding to object in the current photo：Based on the current photograph Pattern information corresponding to the first object controls the clarifier operation in piece.
- A kind of 6. control device of clarifier, it is characterised in that including：Acquiring unit, for being taken pictures to obtain photo to destination object, wherein, the destination object is pair using clarifier As；Analytic unit, for being analyzed using the first model the photo, determine on the photo corresponding to destination object Pattern information, wherein, the pattern information is the clarifier operational mode when destination object uses the clarifier Information, first model are trained using multi-group data by machine learning, every group of data in the multi-group data Comprise at least：Pattern information corresponding to the photo of object and the object；AndFirst control unit, for controlling the clarifier operation based on pattern information corresponding to the destination object.
- 7. device according to claim 6, it is characterised in that described device also includes：First collecting unit, for gathering the human body biological characteristics of multiple objects, wherein, each object in the multiple object To use the object of the clarifier, comprised at least in the human body biological characteristics：Face information；Recognition unit, for identifying the age stratum belonging to the object by the human body biological characteristics of each object；Second collecting unit, the pattern information selected during for gathering each object using the clarifier；Training unit, for the age stratum belonging to the photo to the human body biological characteristics including each object, the object The pattern information selected during with the object using the clarifier is trained by machine learning, creates first model.
- 8. device according to claim 6, described device also include：Detection unit, currently it whether there is human object for detecting in predeterminable area, wherein, the predeterminable area is described net Change the region that air is purified during device operation；Second control unit, if there is currently no human object for detecting in the predeterminable area, control the clarifier It is out of service.
- A kind of 9. storage medium, it is characterised in that storage medium include storage program, wherein, program execution profit require 1 to The control method of the clarifier of any one in 5.
- A kind of 10. processor, it is characterised in that processor is used for operation program, wherein, perform claim requirement 1 when program is run The control method of the clarifier of any one into 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710868776.9A CN107680278A (en) | 2017-09-22 | 2017-09-22 | Control method and device of purifier |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710868776.9A CN107680278A (en) | 2017-09-22 | 2017-09-22 | Control method and device of purifier |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107680278A true CN107680278A (en) | 2018-02-09 |
Family
ID=61136673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710868776.9A Pending CN107680278A (en) | 2017-09-22 | 2017-09-22 | Control method and device of purifier |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107680278A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109297116A (en) * | 2018-12-04 | 2019-02-01 | 宁波锦觅网络科技有限公司 | Automate dust-falling mechanism |
| CN112614137A (en) * | 2019-10-06 | 2021-04-06 | 宋健 | Parameter regulation and control system based on object quantity |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101584575A (en) * | 2009-06-19 | 2009-11-25 | 无锡骏聿科技有限公司 | Age assessment method based on face recognition technology |
| CN104750252A (en) * | 2015-03-09 | 2015-07-01 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN105353631A (en) * | 2015-11-25 | 2016-02-24 | 小米科技有限责任公司 | Method and apparatus for adjusting working modes |
| CN105357425A (en) * | 2015-11-20 | 2016-02-24 | 小米科技有限责任公司 | Image shooting method and image shooting device |
| CN105841297A (en) * | 2016-03-29 | 2016-08-10 | 北京小米移动软件有限公司 | Method and device for controlling operation modes |
| CN105955221A (en) * | 2016-06-21 | 2016-09-21 | 北京百度网讯科技有限公司 | Electric appliance equipment control method and apparatus |
| CN106196496A (en) * | 2016-08-08 | 2016-12-07 | 合肥泰好乐电子科技有限公司 | A kind of family air conditioning control method |
| CN106247558A (en) * | 2016-08-25 | 2016-12-21 | 珠海格力电器股份有限公司 | Control method and device of air conditioner |
| CN106568169A (en) * | 2016-10-31 | 2017-04-19 | 广州华凌制冷设备有限公司 | Temperature control method and system for intelligent air conditioner as well as air conditioner |
| CN106650632A (en) * | 2016-11-28 | 2017-05-10 | 深圳超多维科技有限公司 | Identity identification method and device, and electronic equipment |
| CN106765922A (en) * | 2016-12-08 | 2017-05-31 | 广东志高空调有限公司 | A kind of air-conditioning and air conditioning control method |
| CN106871365A (en) * | 2017-03-09 | 2017-06-20 | 美的集团股份有限公司 | The progress control method of air-conditioner, device and air-conditioning system |
| CN106970552A (en) * | 2017-02-09 | 2017-07-21 | 中控智慧科技股份有限公司 | A kind of method of controlling switch, intelligent switch and mobile terminal |
| CN106996621A (en) * | 2017-04-10 | 2017-08-01 | 盐城师范学院 | Intelligent air condition control device and control method based on infrared acquisition |
| JP2017166762A (en) * | 2016-03-17 | 2017-09-21 | パナソニックＩｐマネジメント株式会社 | Air conditioner |
| CN107450450A (en) * | 2017-09-20 | 2017-12-08 | 京东方科技集团股份有限公司 | A kind of intelligent drinking machine and its control method |
-
2017
- 2017-09-22 CN CN201710868776.9A patent/CN107680278A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101584575A (en) * | 2009-06-19 | 2009-11-25 | 无锡骏聿科技有限公司 | Age assessment method based on face recognition technology |
| CN104750252A (en) * | 2015-03-09 | 2015-07-01 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN105357425A (en) * | 2015-11-20 | 2016-02-24 | 小米科技有限责任公司 | Image shooting method and image shooting device |
| CN105353631A (en) * | 2015-11-25 | 2016-02-24 | 小米科技有限责任公司 | Method and apparatus for adjusting working modes |
| JP2017166762A (en) * | 2016-03-17 | 2017-09-21 | パナソニックＩｐマネジメント株式会社 | Air conditioner |
| CN105841297A (en) * | 2016-03-29 | 2016-08-10 | 北京小米移动软件有限公司 | Method and device for controlling operation modes |
| CN105955221A (en) * | 2016-06-21 | 2016-09-21 | 北京百度网讯科技有限公司 | Electric appliance equipment control method and apparatus |
| CN106196496A (en) * | 2016-08-08 | 2016-12-07 | 合肥泰好乐电子科技有限公司 | A kind of family air conditioning control method |
| CN106247558A (en) * | 2016-08-25 | 2016-12-21 | 珠海格力电器股份有限公司 | Control method and device of air conditioner |
| CN106568169A (en) * | 2016-10-31 | 2017-04-19 | 广州华凌制冷设备有限公司 | Temperature control method and system for intelligent air conditioner as well as air conditioner |
| CN106650632A (en) * | 2016-11-28 | 2017-05-10 | 深圳超多维科技有限公司 | Identity identification method and device, and electronic equipment |
| CN106765922A (en) * | 2016-12-08 | 2017-05-31 | 广东志高空调有限公司 | A kind of air-conditioning and air conditioning control method |
| CN106970552A (en) * | 2017-02-09 | 2017-07-21 | 中控智慧科技股份有限公司 | A kind of method of controlling switch, intelligent switch and mobile terminal |
| CN106871365A (en) * | 2017-03-09 | 2017-06-20 | 美的集团股份有限公司 | The progress control method of air-conditioner, device and air-conditioning system |
| CN106996621A (en) * | 2017-04-10 | 2017-08-01 | 盐城师范学院 | Intelligent air condition control device and control method based on infrared acquisition |
| CN107450450A (en) * | 2017-09-20 | 2017-12-08 | 京东方科技集团股份有限公司 | A kind of intelligent drinking machine and its control method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109297116A (en) * | 2018-12-04 | 2019-02-01 | 宁波锦觅网络科技有限公司 | Automate dust-falling mechanism |
| CN112614137A (en) * | 2019-10-06 | 2021-04-06 | 宋健 | Parameter regulation and control system based on object quantity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102635987B1 (en) | Method, apparatus, device and storage medium for training an image semantic segmentation network | |
| US11581130B2 (en) | Internal thermal fault diagnosis method of oil-immersed transformer based on deep convolutional neural network and image segmentation | |
| Habibzadeh et al. | Soft sensing in smart cities: Handling 3Vs using recommender systems, machine intelligence, and data analytics | |
| CN104933428B (en) | A kind of face identification method and device based on tensor description | |
| CN106909870A (en) | The search method and device of facial image | |
| CN109272509A (en) | A kind of object detection method of consecutive image, device, equipment and storage medium | |
| CN107256386A (en) | Human behavior analysis method based on deep learning | |
| CN106960210A (en) | The method and apparatus of target detection | |
| Gupta et al. | Artificial plant optimization algorithm to detect infected leaves using machine learning | |
| CN109523538A (en) | A kind of people counting method and system based on generation confrontation neural network | |
| US11275970B2 (en) | Systems and methods for distributed data analytics | |
| CN107944403A (en) | Pedestrian's attribute detection method and device in a kind of image | |
| CN108363953A (en) | A kind of method and binocular monitoring device of pedestrian detection | |
| CN110781844B (en) | Security patrol monitoring method and device | |
| CN111125290B (en) | Intelligent river patrol method and device based on river growth system and storage medium | |
| CN112070071B (en) | Method and device for labeling objects in video, computer equipment and storage medium | |
| CN107680278A (en) | Control method and device of purifier | |
| CN108764203A (en) | A kind of pedestrian's quantitative analysis and display systems towards urban planning | |
| CN113780342A (en) | Intelligent detection method and device based on self-supervision pre-training and robot | |
| CN110766650A (en) | Biological detection early warning method, system, device, computer equipment and storage medium | |
| CN116958806A (en) | Pest identification model updating, pest identification method and device and electronic equipment | |
| CN107066556A (en) | Alternative answer sort method and device for artificial intelligence conversational system | |
| CN109784157A (en) | A kind of image processing method, apparatus and system | |
| CN117542082A (en) | Pedestrian detection method based on YOLOv7 | |
| CN112329550A (en) | Weak supervision learning-based disaster-stricken building rapid positioning evaluation method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180209 |