CN108981115A - Air purifier based on machine learning and control method - Google Patents
Air purifier based on machine learning and control method Download PDFInfo
- Publication number
- CN108981115A CN108981115A CN201810811912.5A CN201810811912A CN108981115A CN 108981115 A CN108981115 A CN 108981115A CN 201810811912 A CN201810811912 A CN 201810811912A CN 108981115 A CN108981115 A CN 108981115A
- Authority
- CN
- China
- Prior art keywords
- air purifier
- user
- machine learning
- module
- sensor
- 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 38
- 238000010801 machine learning Methods 0.000 title claims abstract description 32
- 238000000746 purification Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims description 17
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 claims description 12
- 230000001815 facial effect Effects 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 11
- 230000000007 visual effect Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000001228 spectrum Methods 0.000 claims description 4
- 238000012512 characterization method Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000010365 information processing Effects 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 235000019645 odor Nutrition 0.000 claims description 2
- 238000004887 air purification Methods 0.000 abstract 1
- 230000003993 interaction Effects 0.000 abstract 1
- 238000004140 cleaning Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005282 brightening Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000007958 sleep Effects 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 230000005059 dormancy Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000005416 organic matter Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/89—Arrangement or mounting of control or safety devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to the technical field of air purification equipment, in particular to an air purifier based on machine learning and a control method. The air purifier includes: the air purifier comprises a data acquisition module, an identification module, a matching module, a semantic processing module, a control module, a purification module and a mode server. The air purifier can be conveniently controlled by different users, and personalized customization of different users can be realized. The air purifier can be controlled by identifying different users through images or voices in a voice interaction mode, and even if different users send the same voice instruction content, the air purifier can also identify the user identity through voice. Matching the optimal running states of different users based on a machine learning method; and automatically generating the running state of the optimal user according to the feedback conclusion of the machine learning method. The requirements of people on automatic and intelligent household appliances are met.
Description
Technical field
The present invention relates to air cleaning facility technical field more particularly to a kind of air purifiers based on machine learning.
Background technique
Air purifier is mainly used for removing the pollutant of the forms such as dust, gaseous state, the bacterium in air.Market in recent years
Although upper some Intelligent air purifiers occur, personalized customization cannot achieve, such as customizing mode, personalized air quantity
Deng, that is to say, that although air purifier sets different stalls for user demand, for different users, even
Identical gear, user A are different with the user B experience felt.That is different user is for same mode
Definition may be different from, such as: user A is more sensitive for noise, lamplight brightness, and therefore, it is desirable to sleep gears or quiet
The revolving speed of blower is more lower under sound shelves, light is more darker, and user B is then to noise, lamplight brightness and insensitive, it is desirable to sleep
The revolving speed of blower is relatively higher under dormancy shelves or mute file, light is brighter.
The adjusting of air quality is carried out additionally by air purifier is manually controlled, it is inconvenient, it is intelligent lower, it is empty
Gas purifier intelligent can not carry out air cleaning for user and indoor environment, not be able to satisfy people to automation, intelligence
The demand of household electrical appliance.
Summary of the invention
In view of two problems set forth above, the present invention proposes a kind of air purifier and controlling party based on machine learning
Method, traditional air purifier meet user demand by setting different stalls, and gear is this mostly between 1-5 grades
Scheme can not identify different user, reduce user demand, fetter the ability of air purifier；The present invention is quasi- to pass through engineering
Habit scheme is identified different user types, is cooperated by multiple sensors, air purifier is put by supervision/unsupervised learning
De- routine gear limitation, is realized " intelligence ".Pass through air purifier autonomous learning, constantly adjustment blower, noise, the shapes such as light
State, to independently reach user demand.
According to an aspect of an embodiment of the present invention, a kind of air purifier particular technique based on machine learning is provided
Scheme is as follows: including data acquisition module, identification module, matching module, schema server, control module, semantic processes mould
Block.
Further, the data acquisition module includes visual sensor, body-sensing sensor, CO2Sensor, language pass
It is any one or more than one in sensor.
Further, the visual sensor obtains the facial image information of kinsfolk, extracts the face of kinsfolk
Feature.
Further, the body-sensing sensor is used to obtain the sendible temperature feature of kinsfolk.
Further, the CO2Sensor is for obtaining room air CO2Concentration；
Further, the language sensor is used to obtain the acoustic information of kinsfolk.
Further, the identification module, for collected user images and sound to be carried out information identification.
Further, to image be identified by visual sensor collect image information by removal noise, enhancing,
It restores, segmentation, the processing for extracting feature, obtains the facial characteristics of kinsfolk, for identification with characterization domestic consumer member's
Identity.
Further, language sensor is identified by collected sound wave spectrum to sound, is sampled, is measured
Change, encoding and decoding, frequency-domain analysis, feature extraction processing, obtain the sound characteristic of kinsfolk, for identification with characterize it is home-use
The identity of family member.
Further, the schema server is stored with the mode data that user uses air purifier, including user's
Sound, characteristics of image, and the one or more air purifier use pattern being arranged under the user.
Further, the use pattern includes the operation characteristic parameter of one or more air purifiers, including
But it is not limited to, rotation speed of fan, display backlight or lamplight brightness, sensor, gear parameter information.
Further, the operation characteristic parameter can be by user by directly logging in the schema server, according to service
Device instruction sets these characteristic parameters；Or in the operational process of air purifier, the user is collected automatically in various situations
The various characteristic parameters of use pattern.
Further, the matching module is the state and user's progress of the air purifier operation for selecting user
Match.
Further, the schema server handles the received matched and searched request from matching module, searches specific
The use pattern data of user generate user's use pattern feature according to the user's use pattern data for being stored in schema server
Control instruction.
Further, user's use pattern character control instruction control air is net based on the received for the control module
Change the operation of device.
Further, semantic processes module can carry out semantics recognition to the acoustic information received, by the nature of user
The language construction that language translation is understood that at schema server can carry out semantics recognition to multilingual, including but unlimited
In Chinese, English, French, Russian.
It further, further include purification function module, the purification function module includes that blower and one or more are net
Change unit.
Further, the blower includes grade speed-changing draught fan and variable speed blower.
Further, the clean unit includes removal Particulate Pollution unit, removes odors unit, negative oxygen ion generation
It is any one or more than one in unit.
Further, also packet air purifier further includes air environment sensor, and the air environment sensor includes temperature
Spend sensor, humidity sensor, PM10 sensor, PM2.5 sensor, CO2In sensor, formaldehyde sensor and VOC sensor
It is any one or more than one.
Other side according to an embodiment of the present invention additionally provides a kind of air purifier based on machine learning and control
Method processed, it is specific as follows: a kind of control method of air purifier, comprising:
Open air purifier, the image and acoustic information of the data collecting module collected user in clarifier；
Collected user images and sound are subjected to information processing by identification module and identify identity；
Matching module carries out the user data in image processed in identification module and acoustic information and schema server
Match；
Schema server handles the received matched and searched request from matching module, searches the use pattern number of specific user
According to according to the user's use pattern data generation for being stored in schema server user's use pattern character control instruction；
Control module receives the operation of user's use pattern character control instruction control air purifier.
Further, when first used, schema server records mode selected by user and user at this time to user；
Sound, characteristics of image including user, and the one or more air purifier being arranged under the user use
Mode.
Further, the sound issued for user carries out semantics recognition by semantic processes module, by the nature of user
The language construction that language translation is understood that at schema server is generated according to the user's use pattern data for being stored in server
User's use pattern character control instruction, and it is transmitted to the control module, so that it is net to control air by control module
Change the operation of device.
The beneficial effects of the invention are as follows can identify different user types；And it is based on machine learning method, matching is different
User's optimal operational condition；According to the feedback conclusion of machine learning method, the operating status at most suitably used family is automatically generated.Meet people
Demand to automation, intelligent household electrical appliance.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 traditional filtering formula air purifier using process diagram；
The composition schematic diagram of air purifier Fig. 2 of the invention；
Air purifier control method schematic diagram Fig. 3 of the invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
Embodiment 1
Below in conjunction with attached drawing and specific implementation method, the present invention will be described in detail, in exemplary embodiment and description of the invention
For explaining the present invention, but it is not as a limitation of the invention.
Traditional filtering formula air purifier is broadly divided into three steps using operational process, as shown in Figure 1:
Firstly, when kinsfolk needs in use, opening air purifier power supply, prepares to begin to use；
Then, it is determined that required gear, this gear includes: the revolving speed of blower, the brightness of light, the size of noise；
Finally, the air output of blower, light, noise just immobilizes after gear determines.
Conventional air cleaners can not identify different user types；Different user optimal operational condition can not be matched, it can not
Automatically generate the operating status for being most suitable for user.It is unable to satisfy demand of the people to automation, intelligent household electrical appliance.
For this purpose, a kind of air purifier based on machine learning proposed by the invention, as shown in Fig. 2, this kind of novel air
Gas purifier changes the operational mode of conventional air cleaners, specific as follows:
Air purifier includes data acquisition module, (audiovideo) identification module, matching module, semantic processes module, control
Module, cleaning module, schema server.Data acquisition module acquires data by various function sensors, specifically includes, vision
Sensor, body-sensing sensor, CO2Sensor, language sensor are constituted.
Visual sensor obtains the facial image information of kinsfolk, extracts the facial characteristics of kinsfolk；Body-sensing sensing
Device is used to obtain the sendible temperature feature of kinsfolk；CO2Sensor is for obtaining room air CO2Concentration；Language sensor
For obtaining the acoustic information of kinsfolk.
Air purifier passes through vision, body-sensing, CO2, speech transducer, acquisition different home member facial characteristics, body-sensing
Temperature profile, CO2Concentration data, the use data of phonetic feature will use the air cleaning by supervision/unsupervised classification
The user data of device is classified by different kinsfolks, and is recorded corresponding data and be saved in.
(audiovideo) identification module, the identification module are used to collected user images and sound carrying out information knowledge
Not.Image information is collected by removal noise, enhancing, recovery, segmentation, extraction to the visual sensor that is identified by of image
The method of the processing such as feature, finally obtains the facial characteristics of kinsfolk, the facial characteristics of any two people be all it is discrepant,
It can be used to identify and characterize the identity of domestic consumer member；Identification to sound is the carrying speech letter that electricity consumption acoustic instrument is shown
The sound wave spectrum of breath samples the user voice received, is quantified, encoding and decoding, frequency-domain analysis, feature extraction etc., thus
Generate processed voiceprint.The sound map of any two people is all variant, can be used for characterizing and identifying the body of user
Part.It wherein, include image recognition chip and sound identification chip in identification module.
Matching module is that the state for the air purifier operation for selecting user is matched with user；User makes for the first time
Used time, air purifier independently adjust rotation speed of fan from small to large, and brightness is gradually by secretly brightening, position of the sound-insulating member apart from air port
Set that close (sound-insulating member is closer apart from air port, and noise is smaller, and air quantity is smaller, while clean-up effect slightly reduces by far becoming；Difference is used
There is oneself receptible noise level of institute at family in use, therefore passes through position of the adjust automatically sound-insulating member apart from air port
It sets, reaches the most suitable state of user).After user feels the degree for reaching the most comfortable, user by voice (e.g., " can with ",
" Yes " etc.) air purifier is fed back to, schema server records mode selected by user and user at this time.Work as user
When reusing the air purifier, subscriber station is near the air purifier (at 0.1~2 meter) or user's sending sound
Sound, matching module receive the information for coming from (audiovideo) identification module, and after recognizing the user, search pattern server is looked for
To the use pattern data of the user.
Schema server handles the received matched and searched request from matching module, searches the use pattern of specific user
Data generate user's use pattern character control according to the user's use pattern data for being stored in schema server and instruct.
Schema server is stored with the mode data that user uses air purifier, and sound, image including user are special
Sign, and one or more air purifier use patterns of the setting under user (sound, characteristics of image).Every kind of use
Mode includes the operation characteristic parameter of one or more air purifiers, including but not limited to, rotation speed of fan, display backlight or
The parameter informations such as lamplight brightness, sensor, gear.It can be set by directly logging in the server according to server instruction by user
These fixed parameters, come the one or more air purifier use pattern characteristic parameters established under the user.It can also pass through
In the operational process of air purifier, collect automatically the user in various situations use pattern various characteristic parameters (packet
It includes but is not limited to, rotation speed of fan, display backlight or lamplight brightness, sensor, gear etc.), to be built automatically in server end
Found one or more air purifier use pattern characteristic parameters under the user.
Semantic processes module can carry out semantics recognition to the acoustic information received, by the natural language translation of user
At schema server it is understood that language construction, generate the user according to the user's use pattern data for being stored in server
The instruction of use pattern character control, and user's use pattern character control instruction is transmitted to the control module, thus
The operation of air purifier is controlled by control module.
User's use pattern character control instruction include air purifier operation various parameters, as rotation speed of fan setting,
Display backlight or lamplight brightness control, the setting of working sensor mode etc..The natural language processing that the server has
(NLP) module includes multilingual engine, can carry out semantics recognition to multilingual, including but not limited to, Chinese, English, method
Text, Russian etc..
Control module, user's use pattern character control instruction control air is net based on the received for the control module
Change the operation of device；
Air purifier further includes purification function module, and the purification function module may include that blower and one or more are net
Change unit, various blowers and clean unit known in the art can be used.The blower may include step speed change blower and
Variable speed blower.Preferably, it is variable speed blower for the blower of the application, appoints this is because user can according to need
Meaning selects suitable fan speed, and the noise of blower is controllable.The clean unit includes removal Particulate Pollution unit, removal
One or more of peculiar smell unit, negative oxygen ion generating unit.
Air purifier further includes air environment sensor, and the air environment sensor includes temperature sensor, humidity
Sensor, PM10 sensor, PM2.5 sensor, CO2In sensor, formaldehyde sensor and VOC (volatile organic matter) sensor
One or more, for detecting the air parameter in air purifier use environment, including but not limited to, temperature, humidity,
PM2.5 concentration, PM10 concentration, CO2Concentration, concentration of formaldehyde and VOC concentration etc..The air environment sensor is also electric with control module
Connection, the data that sensor will test are transmitted to control module, and the data of control module receiving sensor transmission are located
Reason, while controlling the operation of air purifier.
Embodiment 2
According to embodiments of the present invention, a kind of control method of air purifier is provided, it should be noted that show in the present embodiment
Out the step of, can execute in a computer system such as a set of computer executable instructions, although also, in the present embodiment
In show logical order, but in some cases, shown or described step can be executed with the sequence for being different from herein
Suddenly.
The invention also includes a kind of control methods of air purifier, and the method includes following:
User opens air purifier, the image and acoustic information of the data collecting module collected user in clarifier.
Identification module is used to collected user images and sound carrying out information processing to identify identity.
Specifically, image information will be collected to the visual sensor of image being identified by identification module to pass through
Noise, enhancing, recovery, segmentation, the method for extracting the processing such as feature are removed, the facial characteristics of kinsfolk is finally obtained, it is any
The facial characteristics of two people be all it is discrepant, can be used to identify and characterize the identity of domestic consumer member；Identification to sound
It is the sound wave spectrum for the carrying verbal information that electricity consumption acoustic instrument is shown, the user voice received is sampled, quantify, is compiled
Decoding, frequency-domain analysis, feature extraction etc., to generate processed acoustic information.The sound map of any two people has difference
It is different, it can be used for characterizing and identifying the identity of user.
Matching module by the user data in image processed in identification module and acoustic information and schema server into
Row matching.
It is used for the first time if it is user, matching module necessarily can not find the user in schema server, and air is net at this time
Change device and independently adjust rotation speed of fan from small to large, brightness is also gradually by secretly brightening, and position of the sound-insulating member apart from air port is by far becoming
Closely, after user feels to reach most suitable degree, it is net that user can feed back to air by voice (e.g., " can with ", " Yes " etc.)
Change device, air purifier can also be fed back to by way of manual key.Schema server record user at this time and
Mode selected by user.When user reuses the air purifier, subscriber station 0.1 near the air purifier~
At 2 meters or user makes a sound, and the received information from (audiovideo) identification module of matching module recognizes the user
Afterwards, search pattern server finds the use pattern data of the user.
Schema server handles the received matched and searched request from matching module, searches the use pattern of specific user
Data generate user's use pattern character control according to the user's use pattern data for being stored in schema server and instruct.
It can be by the operational process of air purifier, collecting user use pattern in various situations automatically
Various characteristic parameters.It can also be indicated to set these parameters according to server by directly logging in the schema server by user,
Come the one or more air purifier use pattern characteristic parameters established under the user.(including but not limited to, blower turns
Fast, display backlight or lamplight brightness, sensor, gear etc.), to establish one under the user in server end automatically
Or multiple air purifier use pattern characteristic parameters.After receipt to multiple user data, in schema server formed with
User member is the ordered sample collection of unit, as shown in Figure 3.
Control module, the instruction of user's use pattern character control controls the operation of the air purifier based on the received.
If user is made a sound during using air purifier, semantic processes module can be to the sound received
Message breath carries out semantics recognition, the language construction that the natural language translation of user is understood that at schema server, according to depositing
The user's use pattern data stored up in server generate user's use pattern character control instruction, and the user is used
Pattern feature control instruction is transmitted to the control module, to control the operation of air purifier by control module.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
In the above embodiment of the invention, it all emphasizes particularly on different fields to the description of each embodiment, does not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided by the present invention, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the module, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple module or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, defeated as module
Component out may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In module or unit.Some or all of unit therein or module can be selected to realize the present embodiment according to the actual needs
The purpose of scheme.
In addition, each functional unit block in each embodiment of the present invention can integrate in one processing unit,
It can be each unit module to physically exist alone, module can also be integrated in one unit with two or more unit modules
In.Above-mentioned integrated unit module both can take the form of hardware realization, can also use the shape of SFU software functional unit module
Formula is realized.
If the integrated unit module be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in computer (or mobile phone) read/write memory medium.Based on this understanding, skill of the invention
Substantially all or part of the part that contributes to existing technology or the technical solution can be with soft in other words for art scheme
The form of part product embodies, which is stored in a storage medium, including some instructions are to make
It obtains a computer equipment (can be personal computer, server, mobile phone, network equipment etc.) and executes each embodiment institute of the present invention
State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. are various
It can store the medium of program code.
The foregoing is only a preferred embodiment of the present invention, only it is to be understood that, these specific embodiment parties
Formula is only the illustrative explanations to the application, does not constitute any restrictions to the protection scope of the application.Protection model of the invention
Enclose and be not limited thereto, anyone skilled in the art in the technical scope disclosed by the present invention, according to this hair
Bright technical solution and its inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (23)
1. a kind of air purifier based on machine learning characterized by comprising data acquisition module, identification module, matching
Module, schema server, control module, semantic processes module.
2. a kind of air purifier based on machine learning according to claim 1, which is characterized in that the data acquisition
Module includes visual sensor, body-sensing sensor, CO2It is any one or more than one in sensor, language sensor.
3. a kind of air purifier based on machine learning according to claim 2, which is characterized in that the visual sensing
Device obtains the facial image information of kinsfolk, extracts the facial characteristics of kinsfolk.
4. a kind of air purifier based on machine learning according to claim 2, which is characterized in that the body-sensing sensing
Device is used to obtain the sendible temperature feature of kinsfolk.
5. a kind of air purifier based on machine learning according to claim 2, which is characterized in that the CO2Sensor
For obtaining room air CO2Concentration.
6. a kind of air purifier based on machine learning according to claim 2, which is characterized in that the language sensing
Device is used to obtain the acoustic information of kinsfolk.
7. a kind of air purifier based on machine learning according to claim 1, which is characterized in that the identification mould
Block, for collected user images and sound to be carried out information identification.
8. a kind of air purifier based on machine learning according to claim 7, which is characterized in that the identification to image
It is to collect image information by visual sensor by removal noise, enhancing, recovery, segmentation, the processing for extracting feature, obtains
The facial characteristics of kinsfolk, for identification with characterization domestic consumer member identity.
9. a kind of air purifier based on machine learning according to claim 7, which is characterized in that the identification to sound
Be collected sound wave spectrum is sampled by language sensor, is quantified, the place of encoding and decoding, frequency-domain analysis, feature extraction
Reason, obtain the sound characteristic of kinsfolk, for identification with characterization domestic consumer member identity.
10. a kind of air purifier based on machine learning according to claim 1, which is characterized in that the mode clothes
Business device is stored with the mode data that user uses air purifier, sound, characteristics of image including user, and is arranged at this
One or more air purifier use pattern under user.
11. a kind of air purifier based on machine learning according to claim 10, which is characterized in that described to use mould
Formula includes the operation characteristic parameter of one or more air purifiers, including but not limited to, rotation speed of fan, display backlight
Or lamplight brightness, sensor, gear parameter information.
12. a kind of air purifier based on machine learning according to claim 11, which is characterized in that the operation is special
Sign parameter can indicate to set these characteristic parameters according to server by user by directly logging in the schema server；Or
In the operational process of air purifier, the various characteristic parameters of user use pattern in various situations are collected automatically.
13. a kind of air purifier based on machine learning according to claim 1, which is characterized in that the matching mould
Block is that the state for the air purifier operation for selecting user is matched with user.
14. a kind of air purifier based on machine learning according to claim 1, which is characterized in that the mode clothes
Business device handles the received matched and searched request from matching module, the use pattern data of specific user is searched, according to storage
The instruction of user's use pattern character control is generated in user's use pattern data of schema server.
15. a kind of air purifier based on machine learning according to claim 1, which is characterized in that the control mould
User's use pattern character control instructs the operation for controlling air purifier to block based on the received.
16. a kind of air purifier based on machine learning according to claim 1, which is characterized in that semantic processes mould
Block can carry out semantics recognition to the acoustic information received, the natural language translation of user can be managed at schema server
The language construction of solution can carry out semantics recognition, including but not limited to, Chinese, English, French, Russian to multilingual.
17. a kind of air purifier based on machine learning according to claim 1, which is characterized in that further include purification
Functional module, the purification function module include blower and one or more clean units.
18. a kind of air purifier based on machine learning according to claim 17, which is characterized in that the blower packet
Include step speed change blower and variable speed blower.
19. a kind of air purifier based on machine learning according to claim 17, which is characterized in that the purification is single
Member includes removal Particulate Pollution unit, removes odors unit, is in negative oxygen ion generating unit any one or more than one.
20. a kind of air purifier based on machine learning according to claim 1, which is characterized in that also packet air is net
Changing device further includes air environment sensor, and the air environment sensor includes temperature sensor, humidity sensor, PM10 sensing
Device, PM2.5 sensor, CO2It is any one or more than one in sensor, formaldehyde sensor and VOC sensor.
21. a kind of control method of air purifier, which is characterized in that include the following:
Open air purifier, the image and acoustic information of the data collecting module collected user in clarifier；
Collected user images and sound are subjected to information processing by identification module and identify identity；
Matching module carries out the user data in image processed in identification module and acoustic information and schema server
Match；
Schema server handles the received matched and searched request from matching module, searches the use pattern number of specific user
According to according to the user's use pattern data generation for being stored in schema server user's use pattern character control instruction；
Control module receives the operation of user's use pattern character control instruction control air purifier.
22. a kind of control method of air purifier, which is characterized in that when first used, schema server records this to user
When user and user selected by mode；Sound, characteristics of image including user, and be arranged under the user one
Or more than one air purifier use pattern.
23. a kind of control method of air purifier, which is characterized in that for the sound that user issues, pass through semantic processes mould
Block carries out semantics recognition, the language construction that the natural language translation of user is understood that at schema server, according to being stored in
User's use pattern data of server generate user's use pattern character control instruction, and are transmitted to the control mould
Block, to control the operation of air purifier by control module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810811912.5A CN108981115A (en) | 2018-07-23 | 2018-07-23 | Air purifier based on machine learning and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810811912.5A CN108981115A (en) | 2018-07-23 | 2018-07-23 | Air purifier based on machine learning and control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108981115A true CN108981115A (en) | 2018-12-11 |
Family
ID=64549340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810811912.5A Pending CN108981115A (en) | 2018-07-23 | 2018-07-23 | Air purifier based on machine learning and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108981115A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110056991A (en) * | 2019-03-25 | 2019-07-26 | 杭州懋天科技有限公司 | Air purifying robot and air purification method |
| CN111637607A (en) * | 2020-05-26 | 2020-09-08 | 北京海林节能科技股份有限公司 | Method and system for improving air quality |
| CN111795448A (en) * | 2020-07-20 | 2020-10-20 | 东江环保股份有限公司 | Intelligent air disinfection and purification system for closed space |
| CN114216226A (en) * | 2021-12-13 | 2022-03-22 | 珠海格力电器股份有限公司 | Control method and device of purifying equipment, purifying equipment and readable storage medium |
| WO2023093388A1 (en) * | 2021-11-26 | 2023-06-01 | 深圳市愚公科技有限公司 | Air purifier adjusting method based on reinforcement learning model, and air purifier |
| CN117398817A (en) * | 2023-11-30 | 2024-01-16 | 中山市凌宇机械有限公司 | Intensive compressed air purification system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1589295A3 (en) * | 2004-04-20 | 2006-08-23 | Lg Electronics Inc. | Air conditioner |
| CN203102365U (en) * | 2012-12-28 | 2013-07-31 | 国民技术股份有限公司 | Terminal and authentication apparatus |
| CN106123209A (en) * | 2016-06-23 | 2016-11-16 | 青岛海尔空调器有限总公司 | Air quality control method based on voice interactive air conditioner |
| 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 |
| CN107856505A (en) * | 2017-11-21 | 2018-03-30 | 北京三五二环保科技有限公司 | A kind of Intelligent air purifier system, Intelligent air purifier and operating method |
-
2018
- 2018-07-23 CN CN201810811912.5A patent/CN108981115A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1589295A3 (en) * | 2004-04-20 | 2006-08-23 | Lg Electronics Inc. | Air conditioner |
| CN203102365U (en) * | 2012-12-28 | 2013-07-31 | 国民技术股份有限公司 | Terminal and authentication apparatus |
| CN106123209A (en) * | 2016-06-23 | 2016-11-16 | 青岛海尔空调器有限总公司 | Air quality control method based on voice interactive air conditioner |
| 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 |
| CN107856505A (en) * | 2017-11-21 | 2018-03-30 | 北京三五二环保科技有限公司 | A kind of Intelligent air purifier system, Intelligent air purifier and operating method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110056991A (en) * | 2019-03-25 | 2019-07-26 | 杭州懋天科技有限公司 | Air purifying robot and air purification method |
| CN111637607A (en) * | 2020-05-26 | 2020-09-08 | 北京海林节能科技股份有限公司 | Method and system for improving air quality |
| CN111795448A (en) * | 2020-07-20 | 2020-10-20 | 东江环保股份有限公司 | Intelligent air disinfection and purification system for closed space |
| WO2023093388A1 (en) * | 2021-11-26 | 2023-06-01 | 深圳市愚公科技有限公司 | Air purifier adjusting method based on reinforcement learning model, and air purifier |
| CN114216226A (en) * | 2021-12-13 | 2022-03-22 | 珠海格力电器股份有限公司 | Control method and device of purifying equipment, purifying equipment and readable storage medium |
| CN117398817A (en) * | 2023-11-30 | 2024-01-16 | 中山市凌宇机械有限公司 | Intensive compressed air purification system and method |
| CN117398817B (en) * | 2023-11-30 | 2024-04-30 | 中山市凌宇机械有限公司 | Intensive compressed air purification system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108981115A (en) | Air purifier based on machine learning and control method | |
| CN108153158A (en) | Switching method, device, storage medium and the server of household scene | |
| WO2019141028A1 (en) | Control method, device and system for electrical device | |
| CN107464568A (en) | Based on the unrelated method for distinguishing speek person of Three dimensional convolution neutral net text and system | |
| KR20190103098A (en) | Method and device for recommending cloth coordinating information | |
| CN112051743A (en) | Device control method, conflict processing method, corresponding devices and electronic device | |
| CN106873773A (en) | Robot interactive control method, server and robot | |
| CN106773820B (en) | Robot interactive approach, device and robot | |
| CN101149950A (en) | Media player for implementing classified playing and classified playing method | |
| CN107856505A (en) | A kind of Intelligent air purifier system, Intelligent air purifier and operating method | |
| CN206117701U (en) | Domestic appliance and control system thereof | |
| CN107305549A (en) | Language data processing method, device and the device for language data processing | |
| CN112201233A (en) | Voice control method, system and device of intelligent household equipment and computer storage medium | |
| CN111197841A (en) | Control method, control device, remote control terminal, air conditioner, server and storage medium | |
| CN108758989A (en) | A kind of air-conditioning and its application method | |
| CN111413877A (en) | Method and device for controlling household appliance | |
| CN109429416A (en) | Illumination control method, apparatus and system for multi-user scene | |
| CN104103272A (en) | Voice recognition method and device and blue-tooth earphone | |
| CN106228989A (en) | A kind of interactive voice identification control method | |
| CN106251871A (en) | A kind of Voice command music this locality playing device | |
| CN117762032B (en) | Intelligent equipment control system and method based on scene adaptation and artificial intelligence | |
| CN114078472A (en) | Training method and device for keyword calculation model with low false awakening rate | |
| CN108833229A (en) | A kind of intelligent home control system of speech identifying function | |
| CN110989390A (en) | Smart home control method and device | |
| CN111105798B (en) | Equipment control method based on voice recognition |
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 |
Application publication date: 20181211 |
|
| RJ01 | Rejection of invention patent application after publication |