CN106016892A - Control method and system of intelligent refrigerator - Google Patents
Control method and system of intelligent refrigerator Download PDFInfo
- Publication number
- CN106016892A CN106016892A CN201610352737.9A CN201610352737A CN106016892A CN 106016892 A CN106016892 A CN 106016892A CN 201610352737 A CN201610352737 A CN 201610352737A CN 106016892 A CN106016892 A CN 106016892A
- Authority
- CN
- China
- Prior art keywords
- identification information
- refrigerator
- article
- information
- image information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D11/00—Self-contained movable devices, e.g. domestic refrigerators
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
- F25D29/003—Arrangement or mounting of control or safety devices for movable devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
- F25D29/005—Mounting of control devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D2700/00—Means for sensing or measuring; Sensors therefor
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Thermal Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Cold Air Circulating Systems And Constructional Details In Refrigerators (AREA)
Abstract
The invention discloses a control method and system of an intelligent refrigerator. The method comprises the following steps: receiving first identifying information, sent by the refrigerator, of an object to be recognized, through the network; receiving image information, sent by the refrigerator, of the object to be recognized, through the network; querying in a network database based on the received image information of the object to be recognized so as to obtain the matched second identifying information matched; if the first identifying information and the second identifying information are the same, directly sending one of the first identifying information and the second identifying information to the refrigerator through the network, so as to display through a display interface of the refrigerator; if the first identifying information and the second identifying information are different, matching the first identifying information with the second identifying information, and sending the matching result to the refrigerator through the network, so as to display through the display interface of the refrigerator. According to the control method of the intelligent refrigerator, the data stored in the network database can be increased according to the data fed back by the user end refrigerator, thus the recognizing accuracy of background foods can be ensured, and the experience of a user can be further improved.
Description
Technical field
The present invention relates to household appliance technical field, particularly relate to a kind of intelligent refrigerator control method and control system thereof.
Background technology
Internet of Things is another global tide of IT application after computer, the Internet and mobile communication, is the new stage of global IT application development, and along with the rise of Internet of Things concept, household electric appliances product accelerates intellectuality, releases a series of intelligent refrigerator.
Existing intelligent refrigerator, generally uses its interior item pictures of camera collection, according to the article mark that item pictures is corresponding, classifies article, and then the temperature controlling refrigerator carries out the operations such as fresh-keeping to article.
During article being identified by photographic head, need to pre-set a data base and picture and the respective identification of article are kept.
In current refrigerator identification system, the foundation of data base generally uses following method:
Before refrigerator dispatches from the factory, a large amount of food materials are taken pictures by tester for several times, definition, labelling, afterwards the data of acquisition are uploaded to data base, and further this data base is implanted in the refrigerator of client, in order to ensure the accuracy that the later stage identifies, the Item Information needing storage in this data base is the hugest, so, need substantial amounts of manpower, material resources build this data base, further, after refrigerator dispatches from the factory, this data base i.e. remains constant, so, progress along with science and technology, when increasing foreign peoples's article occur, the accuracy rate of article identification also can be substantially reduced by photographic head.
Summary of the invention
It is an object of the invention to provide a kind of intelligent refrigerator control method and control system thereof and method.
One of for achieving the above object, an embodiment of the present invention provides a kind of intelligent refrigerator control method, and described method includes: received the first identification information of the article to be identified that refrigerator sends by network;
The image information of the article to be identified that refrigerator sends is received by network;
The image information inquiry network data base of the article to be identified to receive, obtains the second matched identification information;
If the first identification information and the second identification information are identical, then directly by the first identification information or the second identification information, one of them is sent to refrigerator by network, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and matching result is sent to refrigerator by network, to be shown by the display interface of refrigerator.
As the further improvement of an embodiment of the present invention, the image information inquiry network data base of the article to be identified to receive, after obtaining the second matched identification information, described method also includes:
If the first identification information and the second identification information are identical, then directly the image information of the first identification information or the second identification information one of them and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and the image information of matching result and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator.
As the further improvement of an embodiment of the present invention, described method also includes:
The information correspondence shown by refrigerator display interface is updated to described network data base.
As the further improvement of an embodiment of the present invention, described method also includes:
If described first identification information and the second identification information are different, then directly the matching result of described first identification information of confirmation and described second identification information is the first identification information, and described first identification information is mated with described image information, shown by the display interface of refrigerator, meanwhile, its correspondence is updated to described network data base.
As the further improvement of an embodiment of the present invention, described method also includes:
If described first identification information and the second identification information are different,
Then with network data base described in the first identification information-enquiry of reception, obtain matched image information sets;
The image information currently obtained and described image information sets are carried out similarity comparison, obtain similarity ratio, when described similarity ratio is more than systemic presupposition similarity threshold, confirm that the first identification information and the second identification information match result are the first identification information
And image information and first identification information of described article to be identified are shown by the display interface of refrigerator, meanwhile, its correspondence is updated to described network data base.
One of for achieving the above object, an embodiment of the present invention provides a kind of intelligent refrigerator control system, and data acquisition module, for receiving the first identification information of the article to be identified that refrigerator sends by network;
The image information of the article to be identified that refrigerator sends is received by network;
Query processing module, the image information inquiry network data base of the article to be identified to receive, obtain the second matched identification information;
If the first identification information and the second identification information are identical, then directly by the first identification information or the second identification information, one of them is sent to refrigerator by network, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and matching result is sent to refrigerator by network, to be shown by the display interface of refrigerator.
As the further improvement of an embodiment of the present invention, described query processing module is additionally operable to:
If the first identification information and the second identification information are identical, then directly the image information of the first identification information or the second identification information one of them and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and the image information of matching result and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator.
As the further improvement of an embodiment of the present invention, described system also includes: database update module, and described database update module is used for: the information correspondence shown by refrigerator display interface is updated to described network data base.
As the further improvement of an embodiment of the present invention, described query processing module is additionally operable to:
If described first identification information and the second identification information are different, then directly the matching result of described first identification information of confirmation and described second identification information is the first identification information, and described first identification information is mated with described image information, shown by the display interface of refrigerator, meanwhile, it is updated to described network data base by described database update module by corresponding with described image information for described first identification information.
As the further improvement of an embodiment of the present invention, described query processing module is additionally operable to:
If described first identification information and the second identification information are different,
Then with network data base described in the first identification information-enquiry of reception, obtain matched image information sets;
The image information currently obtained and described image information sets are carried out similarity comparison, obtain similarity ratio, when described similarity ratio is more than systemic presupposition similarity threshold, confirm that the first identification information and the second identification information match result are the first identification information
And image information and first identification information of described article to be identified are shown by the display interface of refrigerator, meanwhile, it is updated to described network data base by described database update module by corresponding with described image information for described first identification information.
Relative to prior art, the method have technical effect that: the intelligent refrigerator control method of the present invention and control system, image informations based on Network Recognition article to be identified, and it is mated;Further, the accuracy of the matching result obtained with image information is verified for querying condition by the bar code identifying device in refrigerator, and the data produced during further using use update network data base, when again producing new image information, i.e. according to the network data base after updating, it can be processed, so, data by user side refrigerator feedback, increase the data of storage in described network data base, ensure the accuracy of backstage food identification, and promote Consumer's Experience sense further.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of intelligent refrigerator control method in an embodiment of the present invention;
Fig. 2 is the module diagram of intelligent refrigerator control system in an embodiment of the present invention.
Detailed description of the invention
Describe the present invention below with reference to detailed description of the invention shown in the drawings.But these embodiments are not limiting as the present invention, structure, method or conversion functionally that those of ordinary skill in the art is made according to these embodiments are all contained in protection scope of the present invention.
Shown in Fig. 1, the present invention provides a kind of intelligent refrigerator control method, and described method includes:
S1, the first identification information of the article to be identified sent by network reception refrigerator;The image information of the article to be identified that refrigerator sends is received by network;
The image information of described article to be identified, for storing the image information of article in refrigerator, it is generally obtained, such as by the image collecting device arranged in refrigerator: photographic head.
Described first identification information is usually the Item Title of article to be identified, and it is generally obtained, such as by the bar code identifying device arranged in refrigerator: Quick Response Code, multidimensional code etc. identify transposition, RFID harvester etc..
Certainly, it is thus achieved that the precondition of the first identification information is: pre-sets multidimensional code label or RFID label tag etc. on article to be identified, is not described in detail at this.
In the preferred embodiment for the present invention, described bar code identifying device is RFID harvester, RFID, its English full name is: Radio Frequency Identification, Chinese radio frequency identification, it is a kind of communication technology, can pass through radio signals identification specific objective and read and write related data, it is not necessary to and between specific objective, set up machinery or optical contact.
The most important advantage of radio-frequency recognition system is contactless identification, it can penetrate the adverse circumstances label reading that snow, mist, ice, coating, dust and dirt and bar code cannot use, and reading speed is exceedingly fast, in most cases less than 100 milliseconds, so, this RFID acquisition technique is more suitable for refrigerator inside, the first identification information needed for gathering.
In order to prevent refrigerator maloperation; generally also set up some control knobs outside described refrigerator, when corresponding control knob starts, be considered as sending identification signal; start to start photographic head and RFID harvester, refrigerator preserves the image information of article to identify and to obtain and represents information 1.Certainly, in other embodiments of the present invention, it is also possible to arrange the equipment such as sensor on refrigerator, it is used for sending identification signal.In the present invention one preferred implementation, after opening refrigerator doors, i.e. it is considered as sending identification signal, is not described in detail at this.
It is understandable that, every time during image collecting device work, according to its installation site and the change of the shading value of light, its quantity obtaining article and color all may be different, such as: in its item pictures obtained, there may be a kind of article, also likely to be present multiple different article, be not described in detail at this.
The connected mode of described network is not specifically limited, such as: the connected modes such as RFID, bluetooth, WIFI, Internet, LAN.
Further, in an embodiment of the present invention, described method also includes:
S2, with receive article to be identified image information inquiry network data base, obtain the second matched identification information;
Described network data base includes: the attribute information of article and the second identification information of correspondence.
Described network data base can be stored on high in the clouds or single server, and the refrigerator of user side is attached by network and this network data base and is carried out data exchange.
The operation of its client refrigerator can be updated by the data of described network data library storage according to user, and so, the primary data of described network data library storage is not required for the hugest, and then saves the human and material resources cost building storehouse, below will be discussed in detail.
Described second identification information is similarly Item Title.
In the present invention one preferred implementation, described step S2 specifically includes:
Using contour detecting technology and background segmentation techniques that image information is carried out pretreatment, to obtain the characteristic vector group of image information, described characteristic vector group includes: the shape of article, color, texture etc..
Search described network data base, from multiple characteristic vector apoplexy due to endogenous wind of the most corresponding different article, select the characteristic vector class between the characteristic vector corresponding to image information of described article to be identified with maximum relation degree;
The image information that described article to be measured are corresponding is given by the second identification information corresponding to the described characteristic vector class with maximum relation degree.
Under normal circumstances, each characteristic vector class includes many stack features vector.
Described similarity can use numeric representation;The meansigma methods of the similarity of its each characteristic vector can being characterized in Vector Groups, intermediate value, weighted mean etc..
Such as: represent with the meansigma methods of the similarity of each characteristic vector in similarity employing characteristic vector group,
Assume that the characteristic vector group of the image information by article to be identified and the characteristic vector class in described network data base are compared after search, with the comparison result of the characteristic vector class 1 in described network data base it is: the similarity of color is 90%, shape similarity is 96%, texture similarity is 93%, then the value of described similarity is (90%+96%+93%)/3=93%;With the comparison result of the characteristic vector class 2 in described network data base it is: the similarity of color is 50%, shape similarity is 40%, texture similarity is 60%, the value of the most described similarity is (50%+40%+60%)/3=50%, further, by described, there is maximum relation degree, similarity be 93% the second identification information corresponding to characteristic vector class 1 image information corresponding to described article to be measured give, be not described in detail at this.
Further, in an embodiment of the present invention, described method also includes:
If S3 the first identification information and the second identification information are identical, then directly the first identification information is sent to refrigerator by network, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and matching result is sent to refrigerator by network, to be shown by the display interface of refrigerator.
In present embodiment, in order to avoid refrigerator and network data base interaction produce more data, when, after the image information recognizing article, described image information being transmitted directly to network data base and resolves, meanwhile, the display interface being sent to refrigerator shows;Further, only will be after network data base resolve, the matching result of described first identification information and described second identification information returns to refrigerator, and the further display interface at refrigerator shows.
In another embodiment of the present invention, if the first identification information and the second identification information are identical, then directly the image information of the first identification information and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and the image information of matching result and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator.Accordingly, on the display interface of refrigerator, in the viewing area of image information, the first identification information described in simultaneous display and the matching result of described second identification information;Or in the form of a list, carry out coupling one by one and show described image information and described first identification information of its correspondence and the matching result of described second identification information, so, when the image information that image information is multiple article received, user can be more easy to observe image information and described first identification information and the matching relationship of the matching result of described second identification information, is not described in detail at this.
Certainly, display mode has multiple, such as: subregion shows, list shows, is not described in detail at this.
Further, in an embodiment of the present invention, described method also includes:
S4, the information correspondence shown by refrigerator display interface are updated to described network data base.
After receiving image information again by network, i.e. according to the network data base after updating, it can be processed, so, by the data of client feeds back, increase the data of storage in described network data base, it is ensured that the accuracy of backstage food identification.
In an embodiment of the present invention, if described first identification information and the second identification information are identical, then directly the first identification information or the second identification information one of them and image information are updated to described network data base.
In an embodiment of the present invention, if described first identification information and the second identification information are different, then directly the matching result of described first identification information of confirmation and described second identification information is the first identification information, and described first identification information is mated with described image information, shown by the display interface of refrigerator, meanwhile, its correspondence is updated to described network data base.
In an embodiment of the present invention, if described first identification information and the second identification information are different,
Then with network data base described in the first identification information-enquiry of reception, obtain matched image information sets;
The image information currently obtained and described image information sets are carried out similarity comparison, obtain similarity ratio, when described similarity ratio is more than systemic presupposition similarity threshold, confirm that the first identification information and the second identification information match result are the first identification information, and image information and first identification information of described article to be identified are shown by the display interface of refrigerator, meanwhile, its correspondence is updated to described network data base.
In this embodiment, with network data base described in described first identification information-enquiry, obtain unique features vector class corresponding with described first identification information in described network data base;The image information of described article to be identified is compared with described characteristic vector class, and determines described first identification information and the matching result of described second identification information by comparison result.
In the concrete example of the present invention, content described in integrating step S2, can use contour detecting technology and background segmentation techniques that the image information of described article to be identified is carried out pretreatment equally, to obtain the characteristic vector group of the image information of described article to be identified, described characteristic vector group includes: the shape of article, color, texture etc..
One similarity threshold is set, when the similarity of characteristic vector class known in characteristic vector group and the described network data base of the image information of described article to be identified is more than described similarity threshold, confirm that the first identification information and the second identification information match result are the first identification information, further, image information and first identification information of described article to be identified are shown by the display interface of refrigerator, meanwhile, its correspondence is updated to described network data base.
Described similarity threshold is a fixed numbers, and its span is generally between 50% to 100%.
Understanding for convenience, explained below one concrete example is used for understanding the present invention.
Assume that similarity threshold is 70%, after network data base described in the first identification information-enquiry of described article to be identified, obtain unique features vector class, after characteristic vector class known in the characteristic vector group of the image information of described article to be identified and described network data base is compared, its similarity is 90%, it is more than similarity threshold 70%, so, then confirm that the first identification information and the second identification information match result are the first identification information, and further, image information and first identification information of described article to be identified are shown by the display interface of refrigerator, simultaneously, its correspondence is updated to described network data base.So, by the refrigerator operation of user side, actively expand the data of storage in described network data base, and then save the human and material resources cost building storehouse.
In order to make it easy to understand, herein below is enumerated the concrete application example of an intelligent refrigerator control method.
Scene 1 time:
Such as: article to be identified are " Fructus Citri tangerinae ", the first identification information received by network is " Fructus Citri tangerinae ", when being received the image information of " Fructus Citri tangerinae " by network, after inquiry network data base, identify the second identification information corresponding to these article for " Fructus Citri tangerinae ", so, by the image information of " Fructus Citri tangerinae " and the first identification information of coupling or the second identification information, one of them is sent to refrigerator, to be shown by the display interface of refrigerator;Meanwhile, network data base will be updated to when the first identification information of article to be identified time obtained or the second identification information one of them and image information.
Scene 2 times:
Such as: article to be identified are " Fructus Citri tangerinae ", the first identification information received by network is " Fructus Citri tangerinae ", when being received the image information of " Fructus Citri tangerinae " by network, after inquiry network data base, the factors such as the light and shade change due to light, the image information gathered out is after inquiry data base, the second identification information identifying these article corresponding is mistaken as " Fructus Citri junoris ", , under this scene, first identification information and the second identification information are different, the matching result then confirming the first identification information " Fructus Citri tangerinae " and the second identification information " Fructus Citri junoris " is the first identification information, further, image information and first identification information of " Fructus Citri tangerinae " are sent to refrigerator, to be shown by the display interface of refrigerator;Meanwhile, by when time image information of the article to be identified of acquisition and the first update of identification information are to network data base.
Scene 3 times:
Such as: article to be identified are " Fructus Citri tangerinae ", the first identification information received by network is " Fructus Citri tangerinae ", when being received the image information of " Fructus Citri tangerinae " by network, after inquiry network data base, the factors such as the light and shade change due to light, the image information gathered out is after inquiry data base, the second identification information identifying these article corresponding is mistaken as " Fructus Citri junoris ", under this scene, first identification information and the second identification information are different, then inquire about described network data base with the first identification information " Fructus Citri tangerinae " received, obtain matched image information sets;The image information currently obtained and described image information sets are carried out similarity comparison, obtain similarity ratio, more than systemic presupposition similarity threshold, now, confirm that the first identification information and the second identification information match result are the first identification information, further, image information and first identification information of " Fructus Citri tangerinae " are sent to refrigerator, to be shown by the display interface of refrigerator;Meanwhile, by when time image information of the article to be identified of acquisition and the first update of identification information are to network data base.
Above-mentioned scene 3 times, when similarity ratio is less than systemic presupposition similarity threshold, is not updated described network data base, is not described in detail at this.
In other embodiments of the present invention, can be in the way of further by human assistance, by user by correct image information and update of identification information extremely described network data base, certainly, described network data base can also investigate the data of renewal by the way of human assistance, is not described in detail at this.
It addition, in the technical field of the present invention, by image comparison, it is judged that the accuracy of data also has various ways, do not enumerating at this.In other preferred implementations of the present invention, for Reduction Computation amount, it is also possible to arrange the update cycle of network data base, such as: 1 hour, 1 day, one week etc., can also there is manager's regular update as desired of network data base, after network data base receives corresponding more fresh information, first corresponding more fresh information is stored, afterwards under the update cycle set, data are updated by unification, so, Reduction Computation amount, it is not described in detail at this.
Further, in an embodiment of the present invention, after described network data base receives the data that user side is uploaded, it is also possible to assisted detection to upload the effectiveness of data by the manager of described network data base, update operation the most accordingly, be not described in detail at this.
It is understood that the network data base of the present invention, it is managed by network is unified, so, can give and preferably service according to the demand of client, push content at the same time it can also be increased by the refrigerator that network data base is user side, it is simple to unified management.
Shown in Fig. 2, in an embodiment of the present invention, intelligent refrigerator control system includes: user side and carry out the server end of network connection therewith;Described user side includes: image capture module 100, for gathering the image information of article, identifies acquisition module 200, for gathering the first identification information of article;
Described server end includes: data acquisition module 300, query processing module 400, network data base 500, database update module 600.
Data acquisition module 300 receives the first identification information of the article to be identified that image capture module 100 sends by network;The image information of the article to be identified that mark acquisition module 200 sends is received by network;
The image information of described article to be identified, for refrigerator stores the image information of article, image capture module 100 such as: be arranged at the photographic head in described refrigerator.
Described first identification information is usually the Item Title of article to be identified, identifies acquisition module 200 such as: in refrigerator, the Quick Response Code of setting, multidimensional code etc. identify transposition, RFID harvester etc..
Certainly, it is thus achieved that the precondition of the first identification information is: pre-sets multidimensional code label or RFID label tag etc. on article to be identified, is not described in detail at this.
In the preferred embodiment for the present invention, mark acquisition module 200 is RFID harvester.
In order to prevent refrigerator maloperation; generally also set up some control knobs outside described refrigerator, when corresponding control knob starts, be considered as sending identification signal; start to start image capture module 100 and mark acquisition module 200, refrigerator preserves the image information of article to identify and to obtain and represents information 1.Certainly, in other embodiments of the present invention, it is also possible to arrange the equipment such as sensor on refrigerator, it is used for sending identification signal.In the present invention one preferred implementation, after opening refrigerator doors, i.e. it is considered as sending identification signal, is not described in detail at this.
It is understandable that, every time during image collecting device work, according to its installation site and the change of the shading value of light, its quantity obtaining article and color all may be different, such as: in its item pictures obtained, there may be a kind of article, also likely to be present multiple different article, be not described in detail at this.
The connected mode of described network is not specifically limited, such as: the connected modes such as RFID, bluetooth, WIFI, Internet, LAN.
Further, in an embodiment of the present invention, query processing module 300 is used for: the image information inquiry network data base of the article to be identified to receive, and obtains the second matched identification information;
Network data base 500 includes: the attribute information of article and the second identification information of correspondence.
Network data base 500 can be stored on high in the clouds or single server, and the refrigerator of user side is attached by network and this network data base and is carried out data exchange.
The operation of its client refrigerator can be updated by the data of network data base 500 storage according to user, and so, the primary data of network data base 500 storage is not required for the hugest, and then saves the human and material resources cost building storehouse, below will be discussed in detail.
Described second identification information is similarly Item Title.
In the present invention one preferred implementation, query processing module 400 specifically for: use contour detecting technology and background segmentation techniques that image information is carried out pretreatment, to obtain the characteristic vector group of image information, described characteristic vector group includes: the shape of article, color, texture etc..
Network Search data base 500, from multiple characteristic vector apoplexy due to endogenous wind of the most corresponding different article, selects the characteristic vector class between the characteristic vector corresponding to image information of described article to be identified with maximum relation degree;
The image information that described article to be measured are corresponding is given by the second identification information corresponding to the described characteristic vector class with maximum relation degree.
Under normal circumstances, each characteristic vector class includes many stack features vector.
Described similarity can use numeric representation;The meansigma methods of the similarity of its each characteristic vector can being characterized in Vector Groups, intermediate value, weighted mean etc..
Such as: represent with the meansigma methods of the similarity of each characteristic vector in similarity employing characteristic vector group,
Assume that the characteristic vector group of the image information by article to be identified and the characteristic vector class in network data base 500 are compared after search, with the comparison result of the characteristic vector class 1 in network data base 500 it is: the similarity of color is 90%, shape similarity is 96%, texture similarity is 93%, then the value of described similarity is (90%+96%+93%)/3=93%;With the comparison result of the characteristic vector class 2 in network data base 500 it is: the similarity of color is 50%, shape similarity is 40%, texture similarity is 60%, the value of the most described similarity is (50%+40%+60%)/3=50%, further, by described, there is maximum relation degree, similarity be 93% the second identification information corresponding to characteristic vector class 1 image information corresponding to described article to be measured give, be not described in detail at this.
Further, in an embodiment of the present invention, query processing module 400 is additionally operable to:
If the first identification information and the second identification information are identical, then directly the first identification information is sent to refrigerator by network, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and matching result is sent to refrigerator by network, to be shown by the display interface of refrigerator.
In present embodiment, in order to avoid refrigerator and network data base interaction produce more data, when, after the image information recognizing article, described image information is transmitted directly to network data base and resolves by query processing module 400, meanwhile, the display interface being sent to refrigerator shows;Further, only will be after network data base resolve, the matching result of described first identification information and described second identification information returns to refrigerator, and the further display interface at refrigerator shows.
In another embodiment of the present invention, query processing module 400 is additionally operable to: if the first identification information and the second identification information are identical, then directly the image information of the first identification information and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and the image information of matching result and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator.
Accordingly, on the display interface of refrigerator, in the viewing area of image information, the first identification information described in simultaneous display and the matching result of described second identification information;Or in the form of a list, carry out coupling one by one and show described image information and described first identification information of its correspondence and the matching result of described second identification information, so, when the image information that image information is multiple article received, user can be more easy to observe image information and described first identification information and the matching relationship of the matching result of described second identification information, is not described in detail at this.
Certainly, display mode has multiple, such as: subregion shows, list shows, is not described in detail at this.
Further, in an embodiment of the present invention, database update module 600 is used for:
The information correspondence shown by refrigerator display interface is updated to network data base 500.
After receiving image information again by network, i.e. according to the network data base after updating, it can be processed, so, by the data of client feeds back, increase the data of storage in network data base 500, it is ensured that the accuracy of backstage food identification.
In an embodiment of the present invention, if described first identification information and the second identification information are identical, the first identification information or the second identification information one of them and image information are then directly updated to network data base 500 by database update module 600.
In an embodiment of the present invention, if described first identification information and the second identification information are different, query processing module 400 then directly confirms that the matching result of described first identification information and described second identification information is the first identification information, and described first identification information is mated with described image information, shown by the display interface of refrigerator, meanwhile, its correspondence is updated to network data base 500 by database update module 600.
In an embodiment of the present invention, if described first identification information and the second identification information are different, query processing module 400, then with the first identification information-enquiry network data base 500 received, obtain matched image information sets;
The image information currently obtained and described image information sets are carried out similarity comparison, obtain similarity ratio, when described similarity ratio is more than systemic presupposition similarity threshold, confirm that the first identification information and the second identification information match result are the first identification information, and image information and first identification information of described article to be identified are shown by the display interface of refrigerator, meanwhile, its correspondence is updated to network data base 500 by database update module 600.
In this embodiment, query processing module 400, with described first identification information-enquiry network data base 500, obtains unique features vector class corresponding with described first identification information in network data base 500;The image information of described article to be identified is compared with described characteristic vector class, and determines described first identification information and the matching result of described second identification information by comparison result.
In the concrete example of the present invention, query processing module 400 can use contour detecting technology and background segmentation techniques that the image information of described article to be identified is carried out pretreatment equally, to obtain the characteristic vector group of the image information of described article to be identified, described characteristic vector group includes: the shape of article, color, texture etc..
One similarity threshold is set, when the similarity of characteristic vector class known in characteristic vector group and the network data base 500 of the image information of described article to be identified is more than described similarity threshold, confirm that the first identification information and the second identification information match result are the first identification information, further, image information and first identification information of described article to be identified are shown by the display interface of refrigerator, meanwhile, its correspondence is updated to network data base 500.
Described similarity threshold is a fixed numbers, and its span is generally between 50% to 100%.
Understanding for convenience, explained below one concrete example is used for understanding the present invention.
Assume that similarity threshold is 70%, after query processing module 400 is with the first identification information-enquiry network data base 500 of described article to be identified, obtain unique features vector class, after characteristic vector class known in the characteristic vector group of the image information of described article to be identified and network data base 500 is compared, its similarity is 90%, it is more than similarity threshold 70%, so, then confirm that the first identification information and the second identification information match result are the first identification information, and further, image information and first identification information of described article to be identified are shown by the display interface of refrigerator, simultaneously, its correspondence is updated to network data base 500 by database update module 600.So, by the refrigerator operation of user side, the actively data of storage in extended network data base 500, and then save the human and material resources cost building storehouse.
In other embodiments of the present invention, can be in the way of further by human assistance, by user by correct image information and update of identification information to network data base 500, certainly, network data base 500 can also investigate the data of renewal by the way of human assistance, is not described in detail at this.
It addition, in the technical field of the present invention, by image comparison, it is judged that the accuracy of data also has various ways, do not enumerating at this.In other preferred implementations of the present invention, for Reduction Computation amount, it is also possible to arrange the update cycle of network data base, such as: 1 hour, 1 day, one week etc., can also there is manager's regular update as desired of network data base, after network data base receives corresponding more fresh information, first corresponding more fresh information is stored, afterwards under the update cycle set, data are updated by unification, so, Reduction Computation amount, it is not described in detail at this.
Further, in an embodiment of the present invention, after network data base 500 receives the data that user side is uploaded, it is also possible to assisted detection to upload the effectiveness of data by the manager of network data base 500, update operation the most accordingly, be not described in detail at this.
It is understood that the network data base of the present invention, it is managed by network is unified, so, can give and preferably service according to the demand of client, push content at the same time it can also be increased by the refrigerator that network data base is user side, it is simple to unified management.
Those skilled in the art is it can be understood that arrive, for convenience and simplicity of description, the specific works process of the module of foregoing description, it is referred to the corresponding process in preceding method embodiment, does not repeats them here.
In sum, the intelligent refrigerator control method of the present invention and control system, image informations based on Network Recognition article to be identified, and it is mated;Further, the accuracy of the matching result obtained with image information is verified for querying condition by the bar code identifying device in refrigerator, and the data produced during further using use update network data base, when again producing new image information, i.e. according to the network data base after updating, it can be processed, so, data by user side refrigerator feedback, increase the data of storage in described network data base, ensure the accuracy of backstage food identification, and promote Consumer's Experience sense further.
In several embodiments provided by the present invention, should be understood that, the embodiment of structure, system and method described above is only schematically, such as, the division of described module, it is only a kind of logic function and divides, actual can have other dividing mode when realizing, the most multiple modules or assembly can in conjunction with or be desirably integrated into another device, or some features can be ignored, or does not performs.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be the INDIRECT COUPLING by some interfaces, device or module or communication connection, can be electrical, machinery or other form.
The described module illustrated as separating component can be or may not be physically separate, and the parts shown as module can be or may not be physical module, i.e. may be located at a place, or can also be distributed on multiple mixed-media network modules mixed-media.Some or all of module therein can be selected according to the actual needs to realize the purpose of present embodiment scheme.
It addition, each functional module in each embodiment of the present invention can be integrated in a processing module, it is also possible to be that modules is individually physically present, it is also possible to 2 or 2 are integrated in a module with upper module.Above-mentioned integrated module both can realize to use the form of hardware, it would however also be possible to employ hardware adds the form of software function module and realizes.
Last it is noted that embodiment of above is only in order to illustrate technical scheme, it is not intended to limit;Although the present invention being described in detail with reference to aforementioned embodiments, it will be understood by those within the art that: the technical scheme described in aforementioned each embodiment still can be modified by it, or wherein portion of techniques feature is carried out equivalent;And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of the present invention each embodiment technical scheme.
Claims (10)
1. an intelligent refrigerator control method, it is characterised in that described method includes:
The first identification information of the article to be identified that refrigerator sends is received by network;
The image information of the article to be identified that refrigerator sends is received by network;
The image information inquiry network data base of the article to be identified to receive, obtains the second matched identification information;
If the first identification information and the second identification information are identical, then directly by the first identification information or the second identification information, one of them is sent to refrigerator by network, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and matching result is sent to refrigerator by network, to be shown by the display interface of refrigerator.
Intelligent refrigerator control method the most according to claim 1, it is characterised in that
The image information inquiry network data base of the article to be identified to receive, after obtaining the second matched identification information, described method also includes:
If the first identification information and the second identification information are identical, then directly the image information of the first identification information or the second identification information one of them and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and the image information of matching result and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator.
Intelligent refrigerator control method the most according to claim 1 and 2, it is characterised in that described method also includes:
The information correspondence shown by refrigerator display interface is updated to described network data base.
Intelligent refrigerator control method the most according to claim 3, it is characterised in that described method also includes:
If described first identification information and the second identification information are different, then directly the matching result of described first identification information of confirmation and described second identification information is the first identification information, and described first identification information is mated with described image information, shown by the display interface of refrigerator, meanwhile, its correspondence is updated to described network data base.
Intelligent refrigerator control method the most according to claim 3, it is characterised in that described method also includes:
If described first identification information and the second identification information are different,
Then with network data base described in the first identification information-enquiry of reception, obtain matched image information sets;
The image information currently obtained and described image information sets are carried out similarity comparison, obtain similarity ratio, when described similarity ratio is more than systemic presupposition similarity threshold, confirm that the first identification information and the second identification information match result are the first identification information
And image information and first identification information of described article to be identified are shown by the display interface of refrigerator, meanwhile, its correspondence is updated to described network data base.
6. an intelligent refrigerator control system, it is characterised in that including:
Data acquisition module, for receiving the first identification information of the article to be identified that refrigerator sends by network;
The image information of the article to be identified that refrigerator sends is received by network;
Query processing module, the image information inquiry network data base of the article to be identified to receive, obtain the second matched identification information;
If the first identification information and the second identification information are identical, then directly by the first identification information or the second identification information, one of them is sent to refrigerator by network, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and matching result is sent to refrigerator by network, to be shown by the display interface of refrigerator.
Intelligent refrigerator control system the most according to claim 6, it is characterised in that described query processing module is additionally operable to:
If the first identification information and the second identification information are identical, then directly the image information of the first identification information or the second identification information one of them and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator;
If the first identification information and the second identification information are different, then the first identification information and the second identification information are mated, and the image information of matching result and described article to be identified is matched one by one, and sent to refrigerator by Network Synchronization, to be shown by the display interface of refrigerator.
8. according to the intelligent refrigerator control system described in claim 6 or 7, it is characterised in that described system also includes: database update module,
Described database update module is used for: the information correspondence shown by refrigerator display interface is updated to described network data base.
Intelligent refrigerator control system the most according to claim 8, it is characterised in that described query processing module is additionally operable to:
If described first identification information and the second identification information are different, then directly the matching result of described first identification information of confirmation and described second identification information is the first identification information, and described first identification information is mated with described image information, shown by the display interface of refrigerator, meanwhile, it is updated to described network data base by described database update module by corresponding with described image information for described first identification information.
Intelligent refrigerator control system the most according to claim 8, it is characterised in that described query processing module is additionally operable to:
If described first identification information and the second identification information are different,
Then with network data base described in the first identification information-enquiry of reception, obtain matched image information sets;
The image information currently obtained and described image information sets are carried out similarity comparison, obtain similarity ratio, when described similarity ratio is more than systemic presupposition similarity threshold, confirm that the first identification information and the second identification information match result are the first identification information
And image information and first identification information of described article to be identified are shown by the display interface of refrigerator, meanwhile, it is updated to described network data base by described database update module by corresponding with described image information for described first identification information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610352737.9A CN106016892B (en) | 2016-05-24 | 2016-05-24 | Intelligent refrigerator control method and its control system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610352737.9A CN106016892B (en) | 2016-05-24 | 2016-05-24 | Intelligent refrigerator control method and its control system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106016892A true CN106016892A (en) | 2016-10-12 |
CN106016892B CN106016892B (en) | 2018-11-16 |
Family
ID=57094892
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610352737.9A Active CN106016892B (en) | 2016-05-24 | 2016-05-24 | Intelligent refrigerator control method and its control system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106016892B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017190518A1 (en) * | 2016-05-06 | 2017-11-09 | 青岛海尔股份有限公司 | Intelligent refrigerator and control method and control system thereof |
CN113124633A (en) * | 2019-12-31 | 2021-07-16 | 海信集团有限公司 | Refrigerator with a door |
CN113465251A (en) * | 2020-05-28 | 2021-10-01 | 海信集团有限公司 | Intelligent refrigerator and food material identification method |
-
2016
- 2016-05-24 CN CN201610352737.9A patent/CN106016892B/en active Active
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017190518A1 (en) * | 2016-05-06 | 2017-11-09 | 青岛海尔股份有限公司 | Intelligent refrigerator and control method and control system thereof |
CN113124633A (en) * | 2019-12-31 | 2021-07-16 | 海信集团有限公司 | Refrigerator with a door |
CN113465251A (en) * | 2020-05-28 | 2021-10-01 | 海信集团有限公司 | Intelligent refrigerator and food material identification method |
Also Published As
Publication number | Publication date |
---|---|
CN106016892B (en) | 2018-11-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105953520B (en) | Intelligent refrigerator control method and its control system | |
US10586177B1 (en) | Training a mathematical model for a device using a smart plug | |
CN102414956B (en) | The system and method using for electric power facility, monitor and manage | |
US20130179436A1 (en) | Display apparatus, remote control apparatus, and searching methods thereof | |
CN105022811A (en) | Menu generating method and terminal | |
CN104061749A (en) | Refrigerator food storage position recording method, device and terminal and refrigerator | |
CN104426841A (en) | Method for arranging background image, and correlation server and system | |
CN104061748A (en) | Refrigerator food storage position recording method, device and terminal and refrigerator | |
CN106016892A (en) | Control method and system of intelligent refrigerator | |
CN104597759A (en) | Network video based household control method and system and intelligent household management system | |
CN106249835A (en) | The method being applicable to power management, system, user terminal and device | |
CN105446295A (en) | Electric appliance identification method and apparatus | |
CN107666398B (en) | Group notification method, system and storage medium based on user behavior | |
CN109451752A (en) | Mode control method, device, readable storage medium storing program for executing and electronic equipment | |
US20200394939A1 (en) | Electronic label management apparatus and method | |
CN115524990A (en) | Intelligent household control method, device, system and medium based on digital twins | |
CN111479163A (en) | Image processing method applied to E-commerce live broadcast and user terminal | |
CN102905008A (en) | Data processing method and communication terminal | |
CN117830998A (en) | Point cloud cluster labeling method and device, storage medium and electronic device | |
CN113961735A (en) | Method and device for establishing mapping relation, storage medium and electronic device | |
CN111242149A (en) | Smart home control method and device, storage medium, processor and smart home | |
CN117710739A (en) | Device distribution network method, device, storage medium, program product and household appliance | |
CN115689806A (en) | Clothes cleaning management method, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |