CN110288643A - Cooking apparatus, cooking methods and computer readable storage medium - Google Patents
Cooking apparatus, cooking methods and computer readable storage medium Download PDFInfo
- Publication number
- CN110288643A CN110288643A CN201810218136.8A CN201810218136A CN110288643A CN 110288643 A CN110288643 A CN 110288643A CN 201810218136 A CN201810218136 A CN 201810218136A CN 110288643 A CN110288643 A CN 110288643A
- Authority
- CN
- China
- Prior art keywords
- prediction model
- image
- cooking
- culinary art
- 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.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47J—KITCHEN EQUIPMENT; COFFEE MILLS; SPICE MILLS; APPARATUS FOR MAKING BEVERAGES
- A47J27/00—Cooking-vessels
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47J—KITCHEN EQUIPMENT; COFFEE MILLS; SPICE MILLS; APPARATUS FOR MAKING BEVERAGES
- A47J27/00—Cooking-vessels
- A47J27/56—Preventing boiling over, e.g. of milk
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47J—KITCHEN EQUIPMENT; COFFEE MILLS; SPICE MILLS; APPARATUS FOR MAKING BEVERAGES
- A47J36/00—Parts, details or accessories of cooking-vessels
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47J—KITCHEN EQUIPMENT; COFFEE MILLS; SPICE MILLS; APPARATUS FOR MAKING BEVERAGES
- A47J36/00—Parts, details or accessories of cooking-vessels
- A47J36/32—Time-controlled igniting mechanisms or alarm devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Food Science & Technology (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of cooking apparatus, cooking methods and computer readable storage mediums, wherein cooking apparatus includes: receiving portion, for holding material；Scale marker, set on the inner sidewall of receiving portion；Image collection assembly, the inner sidewall set on scale marker opposite side, for acquiring the image of scale marker；Cook control assembly, it is connected to image collection assembly, for analyze and determine according to image of first prediction model to scale marker the amount of storage of material, and the corresponding default culinary art parameter of material is determined according to amount of storage, wherein, the first prediction model is the prediction model result recorded by machine learning training history amount of storage.According to the technical solution of the present invention, be conducive to advanced optimize cooking process, reduce user's operating procedure during the cooking process and waiting time, meanwhile, improve the eating mouth feel of culinary art food materials.
Description
Technical field
The present invention relates to field of cooking techniques, in particular to a kind of cooking apparatus, a kind of cooking methods and a kind of meter
Calculation machine readable storage medium storing program for executing.
Background technique
With the development of technology of Internet of things, cooking apparatus is developed a variety of intelligence as one of most important intelligent appliance
Scheme can be cooked.
So-called intelligent cooking scheme is usually that the image of material to be cooked is uploaded to server by cooking apparatus, for clothes
Business device determines the corresponding culinary art parameter of above-mentioned material by images match, still, can not be counted with cooking apparatus in server
When occurring according to situations such as interaction or network communication quality be poor or network time delay is big, cooking apparatus can not adjust culinary art in time
Parameter, or even cannot achieve automatic cooking process, this can seriously affect the culinary art experience of user.
Summary of the invention
The present invention is directed to solve at least one of the technical problems existing in the prior art or related technologies.
For this purpose, it is an object of the present invention to provide a kind of cooking apparatus.
It is another object of the present invention to provide a kind of cooking methods.
It is another object of the present invention to provide a kind of computer readable storage mediums.
To achieve the goals above, according to the embodiment of the first aspect of the invention, a kind of cooking apparatus is provided, is wrapped
It includes: receiving portion, for holding material；Scale marker, set on the inner sidewall of receiving portion；Image collection assembly is set to scale marker
The inner sidewall of opposite side, for acquiring the image of scale marker；Control assembly is cooked, image collection assembly is connected to, is used for basis
First prediction model analyze and determine to the image of scale marker the amount of storage of material, and determines material according to amount of storage
Corresponding default culinary art parameter, wherein the first prediction model is pre- to be recorded by machine learning training history amount of storage
Survey model result.
In the technical scheme, by the way that scale marker and image collection assembly is arranged with matching on the inside of receiving portion, into
And the amount of storage of material is determined to the analysis of the image of scale marker by the first prediction model, and continue to determine corresponding pre-
If cooking parameter, local image analysis is realized, limitation of the network communication quality to cooking process is overcome, reduces network
Influence of the time delay to cooking process.
In addition, since the first prediction model is recorded by machine learning training history amount of storage, its essence is
The a large amount of historical sample data being locally stored trains the first prediction model, and then to guarantee that the first prediction model has relatively accurate
Estimated performance, therefore, the first prediction model has higher reliability and accuracy, meanwhile, do not need yet and server into
Row remote interaction just can determine that the culinary art parameter of material.
Preferably, the first prediction model can use neural network model, and the first prediction mode can be according to predetermined period
Circulating machine learning is carried out, or carries out machine learning when detecting that history amount of storage record updates.
Wherein, scale marker may include the mark scale of multiple numerical switches along plumb line genesis analysis, and image is adopted
The image of acquisition means acquisition can be infrared image or visible images, can be used in the image analysis of the first prediction model
Journey can carry out image preprocessing to the image of acquisition, for example, image to further enhance the accuracy of model prediction
Enhancing processing and binaryzation calculation process etc..
In any of the above-described technical solution, it is preferable that image collection assembly is also used to: acquiring the image of material；Culinary art control
Component processed is also used to: it is analyzed according to image of second prediction model to material, to determine the attribute information of material, and according to
The default culinary art parameter of attribute information adjustment, wherein the second prediction model is to be obtained by machine learning training historical status information
Prediction model as a result, attribute information includes at least one of the type of material, the quality of material and distributed areas of material.
In the technical scheme, by acquiring the image of material, and by the second prediction model to the image of material into
Row analyzes the attribute information to determine material, is conducive to further optimize cooking process, for example, detecting that material is big
When rice, long grain rice, beans or wheaten food, it is separately adjusted to angularly the corresponding culinary art process of material variety, is improving culinary art effect as much as possible
While rate, spilling is reduced to the greatest extent.
In addition, analyzing the distributed areas for determining material by the second prediction model, be conducive to promote culinary art safety, example
Such as, it when the second prediction model determines that the material in receiving portion is unevenly distributed, issues the user with prompt or automatic vibration accommodates
Portion is occurred with reducing the half-cooked situation of food, for another example, when the second prediction model determines that the distribution of the material in receiving portion is less,
Without cooking heating process, generation the case where to reduce cooking apparatus dry combustion method, for another example, cooking apparatus are generally configured with reservation culinary art
Function, if subscription time is more than 6 hours, therefore the material impregnated bacterium easy to breed is analyzed by the second prediction model
The image of material can remind user to stop cooking process when detecting materials quality exception, to improve food hygiene peace
Entirely.
Preferably, the second prediction model can also use neural network model, and the second prediction mode can be according to default week
Phase carries out circulating machine learning, or machine learning is carried out when detecting that historical status information updates.
In any of the above-described technical solution, it is preferable that the second prediction model includes multiple relationship type submodels, each relationship
Type submodel is respectively used to train a kind of historical status information of material, and the renewal process between any two relationship type submodels
It is independent from each other.
In the technical scheme, by the way that multiple relationship type submodels are arranged in the second prediction model, and renewal process is
It is mutually independent, it can be avoided repetition training model namely each relationship type submodel be respectively used to predict a kind of attribute information,
Since same attribute information is generally configured with identical dimension, it is therefore not necessary to be normalized at process and cumbersome filtering noise reduction
Reason, a relationship type submodel only carry out model training, relationship type submodel when corresponding historical status information updates
Specific aim is stronger when predicting attribute information, and reliability is higher.
Wherein, any material is stored as root node, it is multiple that the second prediction model is laid out in the form of tree-like branch
Relationship type submodel.
In any of the above-described technical solution, it is preferable that culinary art control assembly is also used to: the environment map in acquisition receiving portion
Picture；Culinary art control assembly is also used to: being analyzed according to third prediction model the ambient image in receiving portion, to determine material
Real-time cooking information, and combine attribute information and the default culinary art parameter of real-time cooking information adjustment, wherein third prediction model
Prediction model to be obtained by machine learning training history cooking information includes culinary art heating function as a result, presetting culinary art parameter
Rate, culinary art at least one of duration and cooking temp.
In the technical scheme, by the ambient image in acquisition receiving portion, low delay the real-time of material can be determined
Cooking information, and then attribute information and the default culinary art parameter of real-time cooking information adjustment are combined, for example, material is in cleaning rank
Section, water suction stage, heating with full power stage, boiling stage and holding stage etc., come in conjunction with real-time cooking information and attribute information
The culinary art parameter of adjustment either phase in real time.
Preferably, third prediction model can also use neural network model, and third prediction mode can be according to default week
Phase carries out circulating machine learning, or machine learning is carried out when detecting that history cooking information updates.
In any of the above-described technical solution, it is preferable that further include: man-machine interaction panel, set on the lateral wall of cooking apparatus
And/or side wall, it is connected to culinary art control assembly, for showing relevant to material prompt information, wherein prompt information includes
Based on attribute information determine fresh keeping time information, based on amount of storage determine additive amount information and based in real time culinary art parameter it is true
At least one of fixed culinary art progress information.
In the technical scheme, by the way that human-computer interaction interface is arranged, more intuitively the cooking status of material can be mentioned
Show to user, and then promote the culinary art experience of user in all directions, such as the amount of storage deficiency of prompt material needs to add, for another example
The resting period for prompting material is more than fresh-keeping duration, prompts material to keep the temperature etc. after cooked for another example.
Technical solution according to the second aspect of the invention provides a kind of cooking methods, comprising: in acquisition cooking apparatus
Scale marker image；Analyze and determine according to image of first prediction model to scale marker the amount of storage of material,
And the corresponding default culinary art parameter of material is determined according to amount of storage, wherein the first prediction model is by machine learning training
The prediction model result that history amount of storage records.
In the technical scheme, by the way that scale marker and image collection assembly is arranged with matching on the inside of receiving portion, into
And the amount of storage of material is determined to the analysis of the image of scale marker by the first prediction model, and continue to determine corresponding pre-
If cooking parameter, local image analysis is realized, limitation of the network communication quality to cooking process is overcome, reduces network
Influence of the time delay to cooking process.
In addition, since the first prediction model is recorded by machine learning training history amount of storage, its essence is
The a large amount of historical sample data being locally stored trains the first prediction model, and then to guarantee that the first prediction model has relatively accurate
Estimated performance, therefore, the first prediction model has higher reliability and accuracy, meanwhile, do not need yet and server into
Row remote interaction just can determine that the culinary art parameter of material.
Preferably, the first prediction model can use neural network model, and the first prediction mode can be according to predetermined period
Circulating machine learning is carried out, or carries out machine learning when detecting that history amount of storage record updates.
Wherein, scale marker may include the mark scale of multiple numerical switches along plumb line genesis analysis, and image is adopted
The image of acquisition means acquisition can be infrared image or visible images, can be used in the image analysis of the first prediction model
Journey can carry out image preprocessing to the image of acquisition, for example, image to further enhance the accuracy of model prediction
Enhancing processing and binaryzation calculation process etc..
In any of the above-described technical solution, it is preferable that further include: acquire the image of material；According to the second prediction model pair
The image of material is analyzed, and to determine the attribute information of material, and adjusts default culinary art parameter according to attribute information, wherein
Second prediction model is by the obtained prediction model of machine learning training historical status information as a result, attribute information includes material
At least one of type, the quality of material and the distributed areas of material.
In the technical scheme, by acquiring the image of material, and by the second prediction model to the image of material into
Row analyzes the attribute information to determine material, is conducive to further optimize cooking process, for example, detecting that material is big
When rice, long grain rice, beans or wheaten food, it is separately adjusted to angularly the corresponding culinary art process of material variety, is improving culinary art effect as much as possible
While rate, spilling is reduced to the greatest extent.
In addition, analyzing the distributed areas for determining material by the second prediction model, be conducive to promote culinary art safety, example
Such as, it when the second prediction model determines that the material in receiving portion is unevenly distributed, issues the user with prompt or automatic vibration accommodates
Portion is occurred with reducing the half-cooked situation of food, for another example, when the second prediction model determines that the distribution of the material in receiving portion is less,
Without cooking heating process, generation the case where to reduce cooking apparatus dry combustion method, for another example, cooking apparatus are generally configured with reservation culinary art
Function, if subscription time is more than 6 hours, therefore the material impregnated bacterium easy to breed is analyzed by the second prediction model
The image of material can remind user to stop cooking process when detecting materials quality exception, to improve food hygiene peace
Entirely.
Preferably, the second prediction model can also use neural network model, and the second prediction mode can be according to default week
Phase carries out circulating machine learning, or machine learning is carried out when detecting that historical status information updates.
In any of the above-described technical solution, it is preferable that further include: the ambient image in acquisition receiving portion；It is pre- according to third
Model is surveyed to analyze the ambient image in receiving portion, to determine the real-time cooking information of material, and combine attribute information and
The real-time default culinary art parameter of cooking information adjustment, wherein third prediction model is by machine learning training history cooking information
Obtained prediction model is as a result, default culinary art parameter includes at least one cooked in heating power, culinary art duration and cooking temp
Kind.
In the technical scheme, by the ambient image in acquisition receiving portion, low delay the real-time of material can be determined
Cooking information, and then attribute information and the default culinary art parameter of real-time cooking information adjustment are combined, for example, material is in cleaning rank
Section, water suction stage, heating with full power stage, boiling stage and holding stage etc., come in conjunction with real-time cooking information and attribute information
The culinary art parameter of adjustment either phase in real time.
Preferably, third prediction model can also use neural network model, and third prediction mode can be according to default week
Phase carries out circulating machine learning, or machine learning is carried out when detecting that history cooking information updates.
In any of the above-described technical solution, it is preferable that further include: display prompt information relevant to material, wherein prompt
Information includes the fresh keeping time information determined based on attribute information, the additive amount information determined based on amount of storage and based on cooking in real time
At least one of the culinary art progress information that parameter of preparing food determines.
It in the technical scheme, can more intuitively cooking material by showing relevant to material prompt information
Condition prompting prepare food to user, and then promotes the culinary art experience of user in all directions, such as the amount of storage deficiency of prompt material needs
Addition, for another example prompting the resting period of material is more than fresh-keeping duration, prompts material to keep the temperature etc. after cooked for another example.
Technical solution according to the third aspect of the invention we provides a kind of computer readable storage medium, stores thereon
There is computer program, above-mentioned computer program is performed the culinary art side for realizing and limiting such as any one of second aspect technical solution
Method.
Additional aspect and advantage of the invention will provide in following description section, will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
Fig. 1 shows the schematic diagram of cooking apparatus according to an embodiment of the invention；
Fig. 2 shows the schematic flow diagrams of cooking methods according to an embodiment of the invention；
Fig. 3 shows the schematic flow diagram of cooking methods according to another embodiment of the invention；
Fig. 4 shows the schematic flow diagram of cooking methods according to another embodiment of the invention；
Fig. 5 shows the schematic diagram of the machine learning in cooking methods according to an embodiment of the invention；
Fig. 6 shows the schematic diagram of the machine learning in cooking methods according to another embodiment of the invention.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention is further described in detail.It should be noted that in the absence of conflict, the implementation of the application
Feature in example and embodiment can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used also
To be implemented using other than the one described here other modes, therefore, protection scope of the present invention is not by described below
Specific embodiment limitation.
Fig. 1 shows the schematic diagram of cooking apparatus 100 according to an embodiment of the invention.
As shown in Figure 1, cooking apparatus 100 according to an embodiment of the invention, comprising: receiving portion 102, for holding
Material；Scale marker 104, the inner sidewall set on 106 opposite side of image collection assembly；Image collection assembly 106 is set to receiving portion
102 inner sidewall, for acquiring the image of scale marker 104；Control assembly is cooked, image collection assembly 106 is connected to, is used for
Analyze and determine according to image of first prediction model to scale marker 104 amount of storage of material, and according to amount of storage
Determine the corresponding default culinary art parameter of material, wherein the first prediction model is by machine learning training history amount of storage record
Obtained prediction model result.
In the technical scheme, by the way that scale marker 104 and Image Acquisition group is arranged with matching on the inside of receiving portion 102
Part 106, and then the amount of storage of material is determined to the analysis of the image of scale marker 104 by the first prediction model, and continue
It determines corresponding default culinary art parameter, realizes local image analysis, overcome network communication quality to the limit of cooking process
System reduces influence of the network time delay to cooking process.
In addition, since the first prediction model is recorded by machine learning training history amount of storage, its essence is
The a large amount of historical sample data being locally stored trains the first prediction model, and then to guarantee that the first prediction model has relatively accurate
Estimated performance, therefore, the first prediction model has higher reliability and accuracy, meanwhile, do not need yet and server into
Row remote interaction just can determine that the culinary art parameter of material.
Preferably, the first prediction model can use neural network model, and the first prediction mode can be according to predetermined period
Circulating machine learning is carried out, or carries out machine learning when detecting that history amount of storage record updates.
Wherein, scale marker 104 may include the mark scale of multiple numerical switches along plumb line genesis analysis, such as scheme
" 0.5L ", " 1.0L " shown in 1, " 1.5L ", " 2.0L ", " 2.5L " and " 3.0L ", the image that image collection assembly 106 acquires can
To be infrared image or visible images, it can be used in the image analysis process of the first prediction model, in order to further increase
The accuracy of strong model prediction, can carry out image preprocessing to the image of acquisition, for example, image enhancement processing and binaryzation fortune
Calculation processing etc..
In any of the above-described technical solution, it is preferable that image collection assembly 106 is also used to: acquiring the image of material；Culinary art
Control assembly is also used to: being analyzed according to image of second prediction model to material, to determine the attribute information of material, and root
Default culinary art parameter is adjusted according to attribute information, wherein the second prediction model is to obtain by machine learning training historical status information
To prediction model as a result, attribute information includes at least one in the distributed areas of the type of material, the quality of material and material
Kind.
In the technical scheme, by acquiring the image of material, and by the second prediction model to the image of material into
Row analyzes the attribute information to determine material, is conducive to further optimize cooking process, for example, detecting that material is big
When rice, long grain rice, beans or wheaten food, it is separately adjusted to angularly the corresponding culinary art process of material variety, is improving culinary art effect as much as possible
While rate, spilling is reduced to the greatest extent.
In addition, analyzing the distributed areas for determining material by the second prediction model, be conducive to promote culinary art safety, example
Such as, when the second prediction model determines that the material in receiving portion 102 is unevenly distributed, prompt or automatic vibration are issued the user with
Receiving portion 102 is occurred with reducing the half-cooked situation of food, for another example, determines the material in receiving portion 102 point in the second prediction model
When cloth is less, without cooking heating process, generation the case where to reduce 100 dry combustion method of cooking apparatus, for another example, cooking apparatus 100
It is generally configured with reservation cooking function, if subscription time is more than 6 hours, therefore the material impregnated bacterium easy to breed passes through
Second prediction model analyzes the image of material, user can be reminded to stop cooking process when detecting materials quality exception, with
Improve food hygiene and safety.
Preferably, the second prediction model can also use neural network model, and the second prediction mode can be according to default week
Phase carries out circulating machine learning, or machine learning is carried out when detecting that historical status information updates.
In any of the above-described technical solution, it is preferable that the second prediction model includes multiple relationship type submodels, each relationship
Type submodel is respectively used to train a kind of historical status information of material, and the renewal process between any two relationship type submodels
It is independent from each other.
In the technical scheme, by the way that multiple relationship type submodels are arranged in the second prediction model, and renewal process is
It is mutually independent, it can be avoided repetition training model namely each relationship type submodel be respectively used to predict a kind of attribute information,
Since same attribute information is generally configured with identical dimension, it is therefore not necessary to be normalized at process and cumbersome filtering noise reduction
Reason, a relationship type submodel only carry out model training, relationship type submodel when corresponding historical status information updates
Specific aim is stronger when predicting attribute information, and reliability is higher.
Wherein, any material is stored as root node, it is multiple that the second prediction model is laid out in the form of tree-like branch
Relationship type submodel.
In any of the above-described technical solution, it is preferable that culinary art control assembly is also used to: the environment in acquisition receiving portion 102
Image；Culinary art control assembly is also used to: being analyzed according to third prediction model the ambient image in receiving portion 102, with true
The real-time cooking information of earnest material, and combine attribute information and the default culinary art parameter of real-time cooking information adjustment, wherein third is pre-
Surveying model is the prediction model for training history cooking information to obtain by machine learning as a result, default culinary art parameter includes that culinary art adds
Thermal power, culinary art at least one of duration and cooking temp.
In the technical scheme, by the ambient image in acquisition receiving portion 102, the reality of material can be determined to low delay
When cooking information, and then combine attribute information and the default culinary art parameter of real-time cooking information adjustment, for example, material is in cleaning rank
Section, water suction stage, heating with full power stage, boiling stage and holding stage etc., come in conjunction with real-time cooking information and attribute information
The culinary art parameter of adjustment either phase in real time.
Preferably, third prediction model can also use neural network model, and third prediction mode can be according to default week
Phase carries out circulating machine learning, or machine learning is carried out when detecting that history cooking information updates.
In any of the above-described technical solution, it is preferable that further include: man-machine interaction panel, set on the outside of cooking apparatus 100
Wall and/or side wall 108, are connected to culinary art control assembly, for showing prompt information relevant to material, wherein prompt letter
Breath includes the fresh keeping time information determined based on attribute information, based on the determining additive amount information of amount of storage and based on culinary art in real time
At least one of the culinary art progress information that parameter determines.
In the technical scheme, by the way that human-computer interaction interface is arranged, more intuitively the cooking status of material can be mentioned
Show to user, and then promote the culinary art experience of user in all directions, such as the amount of storage deficiency of prompt material needs to add, for another example
The resting period for prompting material is more than fresh-keeping duration, prompts material to keep the temperature etc. after cooked for another example.
Fig. 2 shows the schematic flow diagrams of cooking methods according to an embodiment of the invention.
As shown in Fig. 2, cooking methods according to an embodiment of the invention, comprising: step S202 acquires cooking apparatus
The image of interior scale marker；Step S204 analyze according to image of first prediction model to scale marker and is determined object
The amount of storage of material, and the corresponding default culinary art parameter of material is determined according to amount of storage, wherein the first prediction model is to pass through machine
The prediction model result that device learning training history amount of storage records.
In the technical scheme, by the way that scale marker and image collection assembly is arranged with matching on the inside of receiving portion, into
And the amount of storage of material is determined to the analysis of the image of scale marker by the first prediction model, and continue to determine corresponding pre-
If cooking parameter, local image analysis is realized, limitation of the network communication quality to cooking process is overcome, reduces network
Influence of the time delay to cooking process.
In addition, since the first prediction model is recorded by machine learning training history amount of storage, its essence is
The a large amount of historical sample data being locally stored trains the first prediction model, and then to guarantee that the first prediction model has relatively accurate
Estimated performance, therefore, the first prediction model has higher reliability and accuracy, meanwhile, do not need yet and server into
Row remote interaction just can determine that the culinary art parameter of material.
Preferably, the first prediction model can use neural network model, and the first prediction mode can be according to predetermined period
Circulating machine learning is carried out, or carries out machine learning when detecting that history amount of storage record updates.
Wherein, scale marker may include the mark scale of multiple numerical switches along plumb line genesis analysis, and image is adopted
The image of acquisition means acquisition can be infrared image or visible images, can be used in the image analysis of the first prediction model
Journey can carry out image preprocessing to the image of acquisition, for example, image to further enhance the accuracy of model prediction
Enhancing processing and binaryzation calculation process etc..
In any of the above-described technical solution, it is preferable that further include: acquire the image of material；According to the second prediction model pair
The image of material is analyzed, and to determine the attribute information of material, and adjusts default culinary art parameter according to attribute information, wherein
Second prediction model is by the obtained prediction model of machine learning training historical status information as a result, attribute information includes material
At least one of type, the quality of material and the distributed areas of material.
In the technical scheme, by acquiring the image of material, and by the second prediction model to the image of material into
Row analyzes the attribute information to determine material, is conducive to further optimize cooking process, for example, detecting that material is big
When rice, long grain rice, beans or wheaten food, it is separately adjusted to angularly the corresponding culinary art process of material variety, is improving culinary art effect as much as possible
While rate, spilling is reduced to the greatest extent.
In addition, analyzing the distributed areas for determining material by the second prediction model, be conducive to promote culinary art safety, example
Such as, it when the second prediction model determines that the material in receiving portion is unevenly distributed, issues the user with prompt or automatic vibration accommodates
Portion is occurred with reducing the half-cooked situation of food, for another example, when the second prediction model determines that the distribution of the material in receiving portion is less,
Without cooking heating process, generation the case where to reduce cooking apparatus dry combustion method, for another example, cooking apparatus are generally configured with reservation culinary art
Function, if subscription time is more than 6 hours, therefore the material impregnated bacterium easy to breed is analyzed by the second prediction model
The image of material can remind user to stop cooking process when detecting materials quality exception, to improve food hygiene peace
Entirely.
Preferably, the second prediction model can also use neural network model, and the second prediction mode can be according to default week
Phase carries out circulating machine learning, or machine learning is carried out when detecting that historical status information updates.
In any of the above-described technical solution, it is preferable that further include: the ambient image in acquisition receiving portion；It is pre- according to third
Model is surveyed to analyze the ambient image in receiving portion, to determine the real-time cooking information of material, and combine attribute information and
The real-time default culinary art parameter of cooking information adjustment, wherein third prediction model is by machine learning training history cooking information
Obtained prediction model is as a result, default culinary art parameter includes at least one cooked in heating power, culinary art duration and cooking temp
Kind.
In the technical scheme, by the ambient image in acquisition receiving portion, low delay the real-time of material can be determined
Cooking information, and then attribute information and the default culinary art parameter of real-time cooking information adjustment are combined, for example, material is in cleaning rank
Section, water suction stage, heating with full power stage, boiling stage and holding stage etc., come in conjunction with real-time cooking information and attribute information
The culinary art parameter of adjustment either phase in real time.
Preferably, third prediction model can also use neural network model, and third prediction mode can be according to default week
Phase carries out circulating machine learning, or machine learning is carried out when detecting that history cooking information updates.
In any of the above-described technical solution, it is preferable that further include: display prompt information relevant to material, wherein prompt
Information includes the fresh keeping time information determined based on attribute information, the additive amount information determined based on amount of storage and based on cooking in real time
At least one of the culinary art progress information that parameter of preparing food determines.
It in the technical scheme, can more intuitively cooking material by showing relevant to material prompt information
Condition prompting prepare food to user, and then promotes the culinary art experience of user in all directions, such as the amount of storage deficiency of prompt material needs
Addition, for another example prompting the resting period of material is more than fresh-keeping duration, prompts material to keep the temperature etc. after cooked for another example.
Fig. 3 shows the schematic flow diagram of cooking methods according to another embodiment of the invention.
As shown in figure 3, cooking methods according to another embodiment of the invention, specifically include:
(1) image data of acquisition is pre-processed, wherein preprocessing function realizes in pattern recognition device, in advance
Processing includes the image processing algorithms such as image enhancement and binaryzation operation.
Wherein, image collecting device has following characteristics:
(1.1) Linux, Android system are supported
(1.2) application program includes the function of an image preprocessing.
(1.3) image identification function is the application program run in system.
(1.4) application program includes a trained deep learning model and result tag along sort.
(1.5) after obtaining image recognition result, the fitting of culinary art control instruction is carried out using image recognition result.
(2) pattern recognition device, the image that pattern recognition device is run will be sent to by pretreated image data
Classification script is mainly used for carrying out image classification label and neural network model.
Specifically, image classification script includes trained pattern classification model neural network based and needs
The image classification label to be identified.
Attribute information of data inclusion material in image classification label, such as northeast rice, long grain rice and rice etc..
Wherein, pattern recognition device supports linux or Android system, to support image recognition program to run.
(3) after identifying image classification result, order is sent to control unit and obtains the current cooking stage of heating device,
According to current cooking stage, fitting heating curves, Xiang Jiare are obtained in conjunction with image recognition result and a benchmark culinary art curve
Device sends control command, includes 3 heating power, temperature and time parameters.
For example: the current generation is the water suction stage, and object is long grain rice, obtains 3 parameters in fitting water suction stage: power
45 degree of temperature of 1200W, 5 minutes time and control.Then this 3 parameters are sent to heating device by control command.
Wherein, the heating curves being fitted can be stored, in case culinary art uses next time.
In addition, energy between any two devices in image collecting device, pattern recognition device, control unit and heating device
Enough it is based on SPI (Serial Peripheral Interface, high-speed synchronous are serial), I2C (Inter-Integrated
Circuit, serial communication bus) and UART (Universal AsynchronousReceiver/Transmitter, it is general different
Step transceiver) agreement communicated.
Fig. 4 shows the schematic flow diagram of cooking methods according to another embodiment of the invention.
As shown in figure 4, cooking methods according to another embodiment of the invention, comprising: step S402, image recognition dress
It sets to image collecting device and sends acquisition；Step S404, the multiple image data that image collecting device will acquire return to
Pattern recognition device；Step S406 carries out merging algorithm for images processing；Step S408 carries out enhancing calculation to spliced image
Method processing, to protrude the character pixel of image；Step S410, by image (the jpg format, jpeg format after enhancing algorithm process
Or png format etc.) base64 format is converted to, and execute image recognition program；Step S412, output recognition result, and according to
Recognition result fitting culinary art curve；Step S414, real-time determination culinary art parameter corresponding with cooking stage, as power, temperature and
Time etc..
Fig. 5 shows the schematic diagram of the machine learning in cooking methods according to an embodiment of the invention.
As shown in figure 5, the machine learning frame of the cooking methods of embodiment according to the present invention is single mode training framework, tool
Body is divided into terminal and server end two sides.
(5.1) terminal includes hardware data collection terminal and embedded system, wherein hardware data collection terminal includes: camera shooting
Head image capture module.Embedded system includes: operating system, human-computer interaction APP, image recognition model (local runtime nerve
Network model predicts food program), model automatically updates, program upgrades automatically and network service etc..
(5.2) server end includes network service module and data set, wherein the step of network service module executes is wrapped
It includes: being connected to the network, respond request, the image data of collection material, detection model changes state and makes automatic push decision etc..
Data set includes: image data set, deep learning frame and identification model, and network service module is sent after saving image data
To image data set, and it is input to deep learning frame as data, according to model output and model modification is determining and material pair
The culinary art parameter answered.
Wherein, terminal is based on existing communication protocol to server end sends network connection, transmission asks summed data to upload
Etc. uplinks signaling, server end be based on existing communication protocol to terminal feedback model automatic push.
In addition, above-mentioned single mode training framework can be according to carrying out image training, or according to going through on the basis of existing model
History data carry out mode trained since source, finally obtain a comprehensive image training pattern.
Fig. 6 shows the schematic diagram of the machine learning in cooking methods according to another embodiment of the invention.
As shown in fig. 6, the machine learning frame of the cooking methods of embodiment according to the present invention is multimode training framework, tool
Body is divided into terminal and server end two sides.
(6.1) terminal includes hardware data collection terminal and embedded system, wherein hardware data collection terminal includes: camera shooting
Head image capture module.Embedded system includes: operating system, human-computer interaction APP, image recognition model (local runtime nerve
Network model predicts food program), model automatically updates, program upgrades automatically and network service etc..
(6.2) server end includes network service module and data set, wherein the step of network service module executes is wrapped
It includes: being connected to the network, respond request, the image data of collection material, detection model changes state and makes automatic push decision etc..
Data set includes: that multiple images data set, deep learning frame and multiple identification models, network service module protect image data
It is sent to image data set after depositing, and is input to deep learning frame as data, is determined according to model output and model modification
Culinary art parameter corresponding with material.
Wherein, terminal is based on existing communication protocol to server end sends network connection, transmission asks summed data to upload
Etc. uplinks signaling, server end be based on existing communication protocol to terminal feedback model automatic push.
In addition, above-mentioned multimode training framework, which can and be deposited cash, model and new model, after server end receives new data,
The carry out new data training for capableing of timing obtains new model, and new model can be automatically pushed to terminal device.This push
Scheme can be avoided repetition training model, and pushes pressure process and also reduce and (only need to push the n-th identification of update
Model can obtain the more new model more directly against property).
According to an embodiment of the invention, also proposed a kind of computer readable storage medium, it is stored thereon with computer journey
Sequence, above-mentioned computer program are performed the image for performing the steps of the scale marker in acquisition cooking apparatus；According to first
Prediction model analyze and determine to the image of scale marker the amount of storage of material, and determines that material is corresponding according to amount of storage
Default culinary art parameter, wherein the first prediction model is by the prediction mould that records of machine learning training history amount of storage
Type result.
In the technical scheme, by the way that scale marker and image collection assembly is arranged with matching on the inside of receiving portion, into
And the amount of storage of material is determined to the analysis of the image of scale marker by the first prediction model, and continue to determine corresponding pre-
If cooking parameter, local image analysis is realized, limitation of the network communication quality to cooking process is overcome, reduces network
Influence of the time delay to cooking process.
In addition, since the first prediction model is recorded by machine learning training history amount of storage, its essence is
The a large amount of historical sample data being locally stored trains the first prediction model, and then to guarantee that the first prediction model has relatively accurate
Estimated performance, therefore, the first prediction model has higher reliability and accuracy, meanwhile, do not need yet and server into
Row remote interaction just can determine that the culinary art parameter of material.
Preferably, the first prediction model can use neural network model, and the first prediction mode can be according to predetermined period
Circulating machine learning is carried out, or carries out machine learning when detecting that history amount of storage record updates.
Wherein, scale marker may include the mark scale of multiple numerical switches along plumb line genesis analysis, and image is adopted
The image of acquisition means acquisition can be infrared image or visible images, can be used in the image analysis of the first prediction model
Journey can carry out image preprocessing to the image of acquisition, for example, image to further enhance the accuracy of model prediction
Enhancing processing and binaryzation calculation process etc..
In any of the above-described technical solution, it is preferable that further include: acquire the image of material；According to the second prediction model pair
The image of material is analyzed, and to determine the attribute information of material, and adjusts default culinary art parameter according to attribute information, wherein
Second prediction model is by the obtained prediction model of machine learning training historical status information as a result, attribute information includes material
At least one of type, the quality of material and the distributed areas of material.
In the technical scheme, by acquiring the image of material, and by the second prediction model to the image of material into
Row analyzes the attribute information to determine material, is conducive to further optimize cooking process, for example, detecting that material is big
When rice, long grain rice, beans or wheaten food, it is separately adjusted to angularly the corresponding culinary art process of material variety, is improving culinary art effect as much as possible
While rate, spilling is reduced to the greatest extent.
In addition, analyzing the distributed areas for determining material by the second prediction model, be conducive to promote culinary art safety, example
Such as, it when the second prediction model determines that the material in receiving portion is unevenly distributed, issues the user with prompt or automatic vibration accommodates
Portion is occurred with reducing the half-cooked situation of food, for another example, when the second prediction model determines that the distribution of the material in receiving portion is less,
Without cooking heating process, generation the case where to reduce cooking apparatus dry combustion method, for another example, cooking apparatus are generally configured with reservation culinary art
Function, if subscription time is more than 6 hours, therefore the material impregnated bacterium easy to breed is analyzed by the second prediction model
The image of material can remind user to stop cooking process when detecting materials quality exception, to improve food hygiene peace
Entirely.
Preferably, the second prediction model can also use neural network model, and the second prediction mode can be according to default week
Phase carries out circulating machine learning, or machine learning is carried out when detecting that historical status information updates.
In any of the above-described technical solution, it is preferable that further include: the ambient image in acquisition receiving portion；It is pre- according to third
Model is surveyed to analyze the ambient image in receiving portion, to determine the real-time cooking information of material, and combine attribute information and
The real-time default culinary art parameter of cooking information adjustment, wherein third prediction model is by machine learning training history cooking information
Obtained prediction model is as a result, default culinary art parameter includes at least one cooked in heating power, culinary art duration and cooking temp
Kind.
In the technical scheme, by the ambient image in acquisition receiving portion, low delay the real-time of material can be determined
Cooking information, and then attribute information and the default culinary art parameter of real-time cooking information adjustment are combined, for example, material is in cleaning rank
Section, water suction stage, heating with full power stage, boiling stage and holding stage etc., come in conjunction with real-time cooking information and attribute information
The culinary art parameter of adjustment either phase in real time.
Preferably, third prediction model can also use neural network model, and third prediction mode can be according to default week
Phase carries out circulating machine learning, or machine learning is carried out when detecting that history cooking information updates.
In any of the above-described technical solution, it is preferable that further include: display prompt information relevant to material, wherein prompt
Information includes the fresh keeping time information determined based on attribute information, the additive amount information determined based on amount of storage and based on cooking in real time
At least one of the culinary art progress information that parameter of preparing food determines.
It in the technical scheme, can more intuitively cooking material by showing relevant to material prompt information
Condition prompting prepare food to user, and then promotes the culinary art experience of user in all directions, such as the amount of storage deficiency of prompt material needs
Addition, for another example prompting the resting period of material is more than fresh-keeping duration, prompts material to keep the temperature etc. after cooked for another example.
The technical scheme of the present invention has been explained in detail above with reference to the attached drawings, and the present invention provides a kind of cooking apparatus, culinary art
Method and computer readable storage medium, by the way that scale marker and image collection assembly is arranged with matching on the inside of receiving portion,
And then the amount of storage of material is determined to the analysis of the image of scale marker by the first prediction model, and continue to determine corresponding
Default culinary art parameter, realizes local image analysis, overcomes limitation of the network communication quality to cooking process, reduce net
Influence of the network time delay to cooking process.
Step in the method for the present invention can be sequentially adjusted, combined, and deleted according to actual needs.
Unit in cooking methods of the present invention can be combined, divided, and deleted according to actual needs.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium include read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read Only Memory, EPROM), disposable programmable read-only memory (One-
Time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only memory
(Electrically-Erasable Programmable Read-OnlyMemory, EEPROM), CD-ROM (Compact
Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic tape storage or can
For carrying or any other computer-readable medium of storing data.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of cooking apparatus characterized by comprising
Receiving portion, for holding material；
Scale marker, the inner sidewall set on described accommodation section；
Image collection assembly, the inner sidewall set on the scale marker opposite side, for acquiring the image of the scale marker；
Cook control assembly, be connected to described image acquisition component, for according to the first prediction model to the scale marker
Image analyze and determine the amount of storage of the material, and determines that corresponding preset of the material is cooked according to the amount of storage
It prepares food parameter,
Wherein, first prediction model is the prediction model result recorded by machine learning training history amount of storage.
2. cooking apparatus according to claim 1, which is characterized in that
Described image acquisition component is also used to: acquiring the image of the material；
The culinary art control assembly is also used to: being analyzed according to image of second prediction model to the material, to determine
The attribute information of material is stated, and the default culinary art parameter is adjusted according to the attribute information,
Wherein, second prediction model for by the obtained prediction model of machine learning training historical status information as a result, institute
State at least one of quality and the distributed areas of the material of type, the material that attribute information includes the material.
3. cooking apparatus according to claim 2, which is characterized in that
Second prediction model includes multiple relationship type submodels, and each relationship type submodel is respectively used to described in training
A kind of historical status information of material, and the renewal process between any two described relationship type submodels is mutually indepedent
's.
4. cooking apparatus according to claim 2, which is characterized in that
The culinary art control assembly is also used to: the ambient image in acquisition described accommodation section；
The culinary art control assembly is also used to: the ambient image in described accommodation section analyzed according to third prediction model,
With the real-time cooking information of the determination material, and it is described default in conjunction with the attribute information and the real-time cooking information adjustment
Parameter is cooked,
Wherein, the third prediction model for by the obtained prediction model of machine learning training history cooking information as a result, institute
Stating default culinary art parameter includes culinary art heating power, culinary art at least one of duration and cooking temp.
5. according to right want 4 described in cooking apparatus, which is characterized in that further include:
Man-machine interaction panel is connected to the culinary art control assembly set on the lateral wall and/or side wall of the cooking apparatus,
For showing prompt information relevant to the material,
Wherein, the prompt information include based on the attribute information determine fresh keeping time information, based on the amount of storage it is true
Fixed additive amount information and at least one of the culinary art progress information determined based on the real-time culinary art parameter.
6. a kind of cooking methods, suitable for the cooking apparatus as described in any one of claims 1 to 5, which is characterized in that described
Cooking methods include:
Acquire the image of the scale marker in the cooking apparatus；
Analyze and determine according to image of first prediction model to the scale marker amount of storage of material, and according to institute
It states amount of storage and determines the corresponding default culinary art parameter of the material,
Wherein, first prediction model is the prediction model result recorded by machine learning training history amount of storage.
7. cooking methods according to claim 6, which is characterized in that further include:
Acquire the image of the material；
It is analyzed according to image of second prediction model to the material, with the attribute information of the determination material, and according to
The attribute information adjusts the default culinary art parameter,
Wherein, second prediction model for by the obtained prediction model of machine learning training historical status information as a result, institute
State at least one of quality and the distributed areas of the material of type, the material that attribute information includes the material.
8. cooking methods according to claim 7, which is characterized in that further include:
Acquire the ambient image in described accommodation section；
The ambient image in described accommodation section is analyzed according to third prediction model, with the real-time culinary art of the determination material
Information, and the default culinary art parameter is adjusted in conjunction with the attribute information and the real-time cooking information,
Wherein, the third prediction model for by the obtained prediction model of machine learning training history cooking information as a result, institute
Stating default culinary art parameter includes culinary art heating power, culinary art at least one of duration and cooking temp.
9. cooking methods according to claim 7, which is characterized in that further include:
Show prompt information relevant to the material,
Wherein, the prompt information include based on the attribute information determine fresh keeping time information, based on the amount of storage it is true
Fixed additive amount information and at least one of the culinary art progress information determined based on the real-time culinary art parameter.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of being performed, realizing the cooking control method as described in any one of claim 6 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810218136.8A CN110288643A (en) | 2018-03-16 | 2018-03-16 | Cooking apparatus, cooking methods and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810218136.8A CN110288643A (en) | 2018-03-16 | 2018-03-16 | Cooking apparatus, cooking methods and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110288643A true CN110288643A (en) | 2019-09-27 |
Family
ID=68000989
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810218136.8A Pending CN110288643A (en) | 2018-03-16 | 2018-03-16 | Cooking apparatus, cooking methods and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288643A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111142394A (en) * | 2019-12-25 | 2020-05-12 | 珠海格力电器股份有限公司 | Control method, device and equipment of cooking equipment and computer readable medium |
| CN111507148A (en) * | 2019-12-31 | 2020-08-07 | 浙江苏泊尔家电制造有限公司 | Control system and control method of rice storage device |
| CN111671315A (en) * | 2020-05-08 | 2020-09-18 | 华帝股份有限公司 | Method for detecting humidity control abnormity of cooking equipment |
| CN111784718A (en) * | 2020-07-11 | 2020-10-16 | 吉林大学 | Intelligent online prediction device and prediction method for discrete material accumulation state |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206252342U (en) * | 2016-10-20 | 2017-06-16 | 佛山市顺德区美的电热电器制造有限公司 | Article-storage device and cooking utensils |
| CN206565745U (en) * | 2016-10-20 | 2017-10-20 | 佛山市顺德区美的电热电器制造有限公司 | Article-storage device and cooking apparatus |
| CN107361627A (en) * | 2017-04-11 | 2017-11-21 | 浙江苏泊尔家电制造有限公司 | Cooking apparatus and the method cooked using cooking apparatus |
| CN107536436A (en) * | 2016-06-24 | 2018-01-05 | 九阳股份有限公司 | A kind of intelligent electric cooker and intelligent cooking system with picture recognition module |
| CN107595102A (en) * | 2017-09-28 | 2018-01-19 | 珠海格力电器股份有限公司 | The control method of cooking apparatus, device and system, storage medium, processor |
-
2018
- 2018-03-16 CN CN201810218136.8A patent/CN110288643A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107536436A (en) * | 2016-06-24 | 2018-01-05 | 九阳股份有限公司 | A kind of intelligent electric cooker and intelligent cooking system with picture recognition module |
| CN206252342U (en) * | 2016-10-20 | 2017-06-16 | 佛山市顺德区美的电热电器制造有限公司 | Article-storage device and cooking utensils |
| CN206565745U (en) * | 2016-10-20 | 2017-10-20 | 佛山市顺德区美的电热电器制造有限公司 | Article-storage device and cooking apparatus |
| CN107361627A (en) * | 2017-04-11 | 2017-11-21 | 浙江苏泊尔家电制造有限公司 | Cooking apparatus and the method cooked using cooking apparatus |
| CN107595102A (en) * | 2017-09-28 | 2018-01-19 | 珠海格力电器股份有限公司 | The control method of cooking apparatus, device and system, storage medium, processor |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111142394A (en) * | 2019-12-25 | 2020-05-12 | 珠海格力电器股份有限公司 | Control method, device and equipment of cooking equipment and computer readable medium |
| CN111142394B (en) * | 2019-12-25 | 2021-12-07 | 珠海格力电器股份有限公司 | Control method, device and equipment of cooking equipment and computer readable medium |
| CN111507148A (en) * | 2019-12-31 | 2020-08-07 | 浙江苏泊尔家电制造有限公司 | Control system and control method of rice storage device |
| CN111507148B (en) * | 2019-12-31 | 2023-10-24 | 浙江苏泊尔家电制造有限公司 | Control system and control method of rice storage device |
| CN111671315A (en) * | 2020-05-08 | 2020-09-18 | 华帝股份有限公司 | Method for detecting humidity control abnormity of cooking equipment |
| CN111784718A (en) * | 2020-07-11 | 2020-10-16 | 吉林大学 | Intelligent online prediction device and prediction method for discrete material accumulation state |
| CN111784718B (en) * | 2020-07-11 | 2021-09-10 | 吉林大学 | Intelligent online prediction device and prediction method for discrete material accumulation state |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288643A (en) | Cooking apparatus, cooking methods and computer readable storage medium | |
| US11506395B2 (en) | Tailored food preparation with an oven | |
| CN109818839B (en) | Personalized behavior prediction method, device and system applied to smart home | |
| US10852930B2 (en) | Control method, storage medium, and information providing method | |
| CN104482715B (en) | The management method of food and refrigerator in refrigerator | |
| CN109344908A (en) | Method and apparatus for generating model | |
| KR102400018B1 (en) | Method and apparatus for auto cooking | |
| WO2017177903A1 (en) | Online verification method and system for real-time gesture detection | |
| CN110009955A (en) | A kind of intelligent tutoring cooking system and its method of automatic lead learning culinary art | |
| WO2019000988A1 (en) | Recipe recommendation method, device and system, storage medium and computer device | |
| CN108846376A (en) | Food method of state management, device, system, computer equipment and storage medium | |
| CN110488696A (en) | A kind of intelligent dry-combustion-proof method and system | |
| CN107909037A (en) | Information output method and device | |
| CN110503151A (en) | A kind of processing method and system of image | |
| WO2019196488A1 (en) | Method and device for controlling household appliance to execute control instruction | |
| KR20240027521A (en) | Method and device for obtaining meat properties information | |
| CN113206774A (en) | Control method and device of intelligent household equipment based on indoor positioning information | |
| CN113925356A (en) | Cooking control method and device, electronic equipment and storage medium | |
| CN113591512A (en) | Method, device and equipment for hair identification | |
| CN114771442A (en) | Vehicle personalized setting method and vehicle | |
| CN112784641A (en) | Food material feeding method and device and cooking machine | |
| CN114442697B (en) | Temperature control method, equipment, medium and product | |
| CN105825195A (en) | Intelligent cooking behavior identification device and method | |
| CN112013441A (en) | Range hood and cooking control method based on range hood | |
| KR102398006B1 (en) | Self improving object recognition method and system through image capture |
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 |