CN111603050A - Method and device for controlling cooker, storage medium and cooker - Google Patents
Method and device for controlling cooker, storage medium and cooker Download PDFInfo
- Publication number
- CN111603050A CN111603050A CN201910134074.7A CN201910134074A CN111603050A CN 111603050 A CN111603050 A CN 111603050A CN 201910134074 A CN201910134074 A CN 201910134074A CN 111603050 A CN111603050 A CN 111603050A
- Authority
- CN
- China
- Prior art keywords
- food material
- cooking
- cooked
- dish
- user
- 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
Images
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
- 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
- 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
- A47J36/00—Parts, details or accessories of cooking-vessels
- A47J36/32—Time-controlled igniting mechanisms or alarm devices
Landscapes
- Engineering & Computer Science (AREA)
- Food Science & Technology (AREA)
- General Preparation And Processing Of Foods (AREA)
Abstract
The invention provides a method and a device for controlling a cooker, a storage medium and the cooker, wherein the method comprises the following steps: acquiring first food material collocation information of dishes to be cooked in the cooker and first user diet habit data of a user to be eaten; inputting the first food material collocation information and the first user dietary habit data into a pre-established cooking parameter decision model so as to output a first cooking parameter of the cooking machine; and controlling the frying machine to cook the dish to be cooked according to the output first frying parameter of the frying machine. According to the scheme provided by the invention, the cooking parameters corresponding to the dishes to be cooked can be decided according to the food material collocation information of the dishes to be cooked and the dietary habit data of the user, so that the dish frying machine can fry the dishes suitable for the taste of the user.
Description
Technical Field
The invention relates to the field of control, in particular to a method and a device for controlling a cooker, a storage medium and a cooker.
Background
Nowadays, many people are busy on work, and do not have time to cook and fry after arriving at home, so that a frying machine capable of automatically frying becomes a demand of many people. The existing cooker can only simply carry out mechanical cooking, has single function, can not carry out intelligent cooking according to the type of dishes, the collocation of the dishes and the like, and has poor cooking effect.
Disclosure of Invention
The invention mainly aims to overcome the defects of the prior art and provides a method and a device for controlling a frying machine, a storage medium and the frying machine, so as to solve the problems that the mechanical frying of the frying machine in the prior art is single in function and can not carry out intelligent frying according to the type of dishes, the collocation of the dishes and the like.
The invention provides a control method of a cooker, which comprises the following steps: acquiring first food material collocation information of dishes to be cooked in the cooker and first user diet habit data of a user to be eaten; inputting the first food material collocation information and the first user dietary habit data into a pre-established cooking parameter decision model so as to output a first cooking parameter of the cooking machine; and controlling the frying machine to cook the dish to be cooked according to the output first frying parameter of the frying machine.
Optionally, the first food material collocation information includes: the food material types and/or food material names of food materials contained in the dishes to be cooked; and/or, the first user eating habit data comprises: the amount of salt, acid, spicy and/or sweet corresponding to the dishes to be cooked; and/or, the first cooking parameter comprises: at least one of the first frying temperature, the first heating time and the first dish color.
Optionally, the obtaining of the first food material matching information of the dishes to be cooked in the cooker includes: collecting food material images of food materials placed in the dish frying machine; and carrying out image recognition on the food material image so as to recognize first food material matching information of the dish to be cooked.
Optionally, the dish-frying parameter decision model is established by: collecting historical cooking data of the cooker; the historical cooking data includes: historically, second food material collocation information and corresponding second user eating habit data of food materials contained in different dishes cooked by the cooking machine, and second cooking parameters of the cooking machine corresponding to the second food material collocation information and the second user eating habit data; and inputting the second food material collocation information, the second user dietary habit data and the second cooking parameter as training samples into a preset neural network for model training to obtain the cooking parameter decision model.
Optionally, inputting the second food material collocation information, the second user eating habit data and the second cooking parameter as training samples into a preset neural network for model training to obtain the cooking parameter decision model, where the model comprises: generating a characteristic matrix by using the second food material collocation information, the second user eating habit data and the second cooking parameter; and inputting the generated characteristic matrix into the preset neural network for model training to obtain the cooking parameter decision model.
Optionally, the second food material collocation information includes: the food material types and/or food material names of food materials contained in different dishes; and/or, the second user eating habit data comprises: the salt content, the acid content, the spicy content and/or the sweet content corresponding to different dishes; and/or, the second cooking parameter comprises: at least one of a second frying temperature, a second heating time and a second dish color.
In another aspect, the present invention provides a cooker control device, including: the acquisition unit is used for acquiring first food material collocation information of dishes to be cooked in the cooker and first user diet habit data of a user to be eaten; the decision unit is used for inputting the first food material collocation information and the first user dietary habit data into a pre-established cooking parameter decision model so as to output a first cooking parameter of the cooking machine; and the control unit is used for controlling the frying machine to cook the dish to be cooked according to the output first frying parameter of the frying machine.
Optionally, the first food material collocation information includes: the food material types and/or food material names of food materials contained in the dishes to be cooked; and/or, the first user eating habit data comprises: the amount of salt, acid, spicy and/or sweet corresponding to the dishes to be cooked; and/or, the first cooking parameter comprises: at least one of the first frying temperature, the first heating time and the first dish color.
Optionally, the obtaining of the first food material matching information of the dishes to be cooked in the cooker includes: collecting food material images of food materials placed in the dish frying machine; and carrying out image recognition on the food material image so as to recognize first food material matching information of the dish to be cooked.
Optionally, the dish-frying parameter decision model is established by: collecting historical cooking data of the cooker; the historical cooking data includes: historically, second food material collocation information and corresponding second user eating habit data of food materials contained in different dishes cooked by the cooking machine, and second cooking parameters of the cooking machine corresponding to the second food material collocation information and the second user eating habit data; and inputting the second food material collocation information, the second user dietary habit data and the second cooking parameter as training samples into a preset neural network for model training to obtain the cooking parameter decision model.
Optionally, inputting the second food material collocation information, the second user eating habit data and the second cooking parameter as training samples into a preset neural network for model training to obtain the cooking parameter decision model, where the model comprises: generating a characteristic matrix by using the second food material collocation information, the second user eating habit data and the second cooking parameter; and inputting the generated characteristic matrix into the preset neural network for model training to obtain the cooking parameter decision model.
Optionally, the second food material collocation information includes: the food material types and/or food material names of food materials contained in different dishes; and/or, the second user eating habit data comprises: the salt content, the acid content, the spicy content and/or the sweet content corresponding to different dishes; and/or, the second cooking parameter comprises: at least one of a second frying temperature, a second heating time and a second dish color.
A further aspect of the invention provides a storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of any of the methods described above.
A further aspect of the invention provides a cooker comprising a processor, a memory and a computer program stored on the memory and operable on the processor, the processor when executing the program implementing the steps of any of the methods described above.
In a further aspect, the invention provides a cooker comprising any one of the cooker control devices.
According to the technical scheme, the acquired first food material collocation information of the dish to be cooked in the dish frying machine and the first user dietary habit data of the user to be eaten are input into the pre-established dish frying parameter decision model, the first dish frying parameter of the dish to be cooked in the current dish frying machine is output from the dish frying machine, the dish frying machine is controlled to cook the dish to be cooked according to the output first dish frying parameter, decision can be made on the dish frying parameter corresponding to the dish to be cooked according to the food material collocation information of the dish to be cooked and the user dietary habit data, so that the dish frying machine can fry dishes suitable for the taste of the user, and the user requirements can be met.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a method schematic diagram of an embodiment of a fryer control method provided by the present invention;
FIG. 2 is a schematic diagram of a neural network according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an embodiment of a cooker control device provided by the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the specific embodiments of the present invention and the accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Fig. 1 is a method schematic diagram of an embodiment of a control method of a cooker provided by the invention.
As shown in fig. 1, according to an embodiment of the present invention, the cooker control method includes at least step S110, step S120, and step S130.
Step S110, acquiring first food material collocation information of dishes to be cooked in the cooker and first user eating habit data of a user to be eaten.
In a specific embodiment, the method comprises the steps of collecting food material images of food materials placed in the cooking machine, namely food material images of food materials contained in a dish to be cooked; and carrying out image recognition on the food material image so as to recognize first food material matching information of the dish to be cooked. Specifically, an image sensor can be arranged in the cooker, the food materials placed in the cooker are shot through the image sensor arranged in the cooker, so that food material images of the food materials contained in the dish to be cooked are obtained, and the food material images are subjected to image recognition after the food material images are obtained, so that first food material matching information of the dish to be cooked is recognized. The first food material matching information may specifically include a food material type and/or a food material name of a food material included in the dish to be cooked.
The first user eating habit data may specifically include: the amount of seasoning needed for the dishes to be cooked may, for example, include the amount of salt, acid, spicy and/or sweet corresponding to the dishes to be cooked, i.e., the amount of salt, acid, spicy and/or sweet corresponding to the taste of the user to be eaten. Specifically, the dish information of the dish to be cooked, such as the name of the dish, may be determined according to the identified first food material collocation information of the dish to be cooked, and the salt amount, the acid amount, the spicy amount and/or the sweet amount corresponding to the dish to be cooked are obtained according to the dish information of the dish to be cooked. In a specific embodiment, the eating habit data of different users, that is, the corresponding relationship between different dishes of different users and the corresponding amount of required seasoning, may be pre-stored, so as to obtain the amount of required seasoning, such as the amount of salt, the amount of acid, the amount of spicy and/or the amount of sweet, corresponding to the dish to be cooked from the corresponding relationship according to the dish information of the dish to be cooked. The salt amount can be specifically the salt amount; the acid amount can be the amount of vinegar; the sweet amount can be the amount of sugar; the spicy content can be the consumption of the hot pepper. In one embodiment, the first user eating habit data may be set by the user himself, for example, the user may set the salt content, the acid content and/or the sweet content of a certain dish himself. In one embodiment, the eating habit data of the user to eat can be collected according to historical cooking parameters of the cooking machine.
After the first user eating habit data of the user to be used is obtained, when the cooking machine is controlled to cook the food material to be cooked, corresponding amount of seasonings can be added into the cooking machine according to the first user eating habit data. That is, according to the amount of the required seasoning corresponding to the dish to be cooked, the corresponding amount of seasoning is added into the cooker, for example, the corresponding amount of salt is added according to the amount of salt corresponding to the dish to be cooked, the corresponding amount of vinegar is added according to the corresponding amount of sour of the dish to be cooked, and the corresponding amount of pepper is added according to the corresponding amount of hot and/or sweet of the dish to be cooked.
Step S120, inputting the first food material collocation information and the first user dietary habit data into a pre-established cooking parameter decision model so as to output a first cooking parameter of the cooking machine.
The cooking parameter decision model is used for determining a first cooking parameter of the cooking machine, namely determining an optimal cooking parameter of the food to be cooked placed in the current cooking machine. The first cooking parameter may specifically include at least one of cooking temperature, heating time and color of the dish, and the color of the dish may be specifically shown in a picture form. Inputting the first food material collocation information and the first user dietary habit data into a pre-established cooking parameter decision model, and outputting a first cooking parameter of the food material to be cooked currently placed in the cooking machine.
Specifically, the cooking parameter decision model is established in the following way:
(1) and collecting historical cooking data of the cooker.
The historical cooking data may specifically include second food material collocation information and corresponding second user eating habit data of food materials contained in different dishes cooked by the cooking machine historically, and second cooking parameters of the cooking machine corresponding to the second food material collocation information and the second user eating habit data.
Specifically, when the cooking machine cooks, second food material collocation information of food materials contained in dishes cooked by the cooking machine and corresponding second user dietary habit data can be recorded, and corresponding second cooking parameters of the cooking machine can be recorded. The second food material matching information comprises food material types and/or food material names of food materials contained in different dishes cooked by the cooking machine historically. The second user eating habit data may specifically include the usage amount of the required seasoning corresponding to different dishes cooked by the cooker historically, for example, the usage amount includes the salt amount, the acid amount, the spicy amount and/or the sweet amount corresponding to different dishes cooked by the cooker historically. The salt amount can be specifically the salt amount; the acid amount can be the amount of vinegar; the sweet amount can be the amount of sugar; the spicy content can be the consumption of the hot pepper. In one embodiment, the second user eating habit data may be set by the user himself, for example, the user may himself set the salt content, the acid content and/or the sweet content of a certain dish. The second cooking parameter comprises at least one of cooking temperature, heating time and color of dishes. The cooking temperature and/or the heating time in the second cooking parameter can be set by a user, for example, the user can set the cooking temperature and/or the heating time according to the user's own needs, and/or the color of the dish in the second cooking parameter can be displayed by collecting an image of the dish when the cooking of the corresponding dish is completed, through the image of the dish.
(2) And inputting the second food material collocation information, the second user dietary habit data and the second cooking parameter as training samples into a preset neural network for model training to obtain the cooking parameter decision model.
Specifically, generating a feature matrix from the second food material collocation information, the second user eating habit data and the second cooking parameter; and inputting the generated characteristic matrix into the preset neural network for model training to obtain the cooking parameter decision model. More specifically, the collected second food material collocation information, the second user eating habit data and the second cooking parameter are used as data samples to be preprocessed, namely, a feature matrix is generated. For example, a feature matrix may be generated by taking data samples according to different features, each feature as a column and each sample as a row. Specific feature matrices may be found in the following table (where specific values are for illustration only):
TABLE 1
Fig. 2 is a schematic structural diagram of a neural network according to an embodiment of the present invention. As shown in fig. 2, which is a schematic structural diagram of a deep neural network, a neural network is mainly composed of three parts, namely an input layer, a hidden layer and an output layer. The input layer and the output layer are only one layer, the hidden layer can be a plurality of layers, and the deep neural network is a neural network with a plurality of hidden layers. Fig. 2 shows a neural network with two hidden layers. At the input level, each neuron x represents an input Feature (Feature), and b is a Feature-independent bias value. The input features are converted by the activation function and enter the hidden layer 1, and similarly, the result of the hidden layer 1 is converted again and enters the hidden layer 2, and finally reaches the output layer, namely the probability values of various types of y are output.
The input sample vector may be represented as X ═ (X1, X2, X3, …, xn), the corresponding class is Y ═ (Y1, Y2, …, ym), and the initialized weight matrix is W. Specifically, in the sample vector X, each component represents a feature, for example, X1 is the amount of acid, X2 is the amount of sweet, X3 is the amount of spicy, and X4 is the amount of salt. The category vector Y is a set of categories to be output, and there are several components to output several categories. For example, two categories of cooking temperature and heating time need to be output, and then the components y1 and y2 represent cooking temperature and heating time, respectively. The weight matrix W is a parameter matrix and is a set of weights of each layer of neurons in the neural network linking with the next layer of neurons, in the training process of the neural network, W is continuously adjusted and changed, when the training is finished, W tends to be a stable value, and the purpose of training the neural network is to determine the optimal weight matrix W.
Preferably, the above model training is performed by using an error Back Propagation algorithm (Back Propagation), and the activation function of the neuron selects a ReLU (linear correction unit) because the ReLU function has simple gradient calculation and fast convergence. And calculating error loss of actual output and expected output (second cooking parameter) each time, performing back propagation according to a loss result, updating the weight matrix W of each layer, finally obtaining stable weight W when the algorithm is converged, finishing algorithm training, and storing a final neural network model, namely the cooking parameter decision model, which is used for making a decision of the current first cooking parameter of the cooking machine.
Step S130, controlling the frying machine to cook the food to be cooked according to the output first frying parameter of the frying machine.
Inputting the first food material collocation information and the first user dietary habit data into a pre-established cooking parameter decision model, outputting a first cooking parameter of the cooking machine for cooking the current dish to be cooked, namely a current optimal cooking parameter, and controlling the cooking machine to cook the dish to be cooked according to the first cooking parameter. For example, when the current cooking temperature of the cooker reaches the first cooking temperature, and/or the cooker reaches the first heating time for the current cooking heating time of the dish to be cooked, and/or image acquisition is performed on the dish to be cooked in the cooker in real time, the cooking is stopped when the color of the dish to be cooked is determined to be matched with the color of the first dish according to the dish image by comparing the dish image of the dish to be cooked with the dish color image showing the color of the first dish. When the cooking machine is controlled to cook the food to be cooked, a corresponding amount of seasoning may be added to the cooking machine according to the first user eating habit data, where the first user eating habit data specifically may include: the amount of the needed seasoning corresponding to the dish to be cooked.
Fig. 3 is a schematic structural diagram of an embodiment of a cooker control device provided by the invention. As shown in fig. 3, the cooker control device 100 includes: an acquisition unit 110, a decision unit 120 and a control unit 130.
The obtaining unit 110 is configured to obtain first food material matching information of dishes to be cooked in the cooker and first user eating habit data of a user to be eaten; the decision unit 120 is configured to input the first food material matching information and the first user eating habit data into a pre-established cooking parameter decision model, so as to output a first cooking parameter of the cooker; the control unit 130 is configured to control the cooker to cook the dish to be cooked according to the output first cooking parameter of the cooker.
In a specific embodiment, the obtaining unit 110 collects food material images of food materials placed in the cooker, that is, food material images of food materials contained in dishes to be cooked; and carrying out image recognition on the food material image so as to recognize first food material matching information of the dish to be cooked. Specifically, an image sensor may be disposed in the cooker, and the obtaining unit 110 captures the food materials placed in the cooker through the image sensor disposed in the cooker to obtain food material images of the food materials contained in the dish to be cooked, and performs image recognition on the food material images after obtaining the food material images to identify the first food material matching information of the dish to be cooked. The first food material matching information may specifically include a food material type and/or a food material name of a food material included in the dish to be cooked.
The first user eating habit data may specifically include: the amount of seasoning needed for the dishes to be cooked may, for example, include the amount of salt, acid, spicy and/or sweet corresponding to the dishes to be cooked, i.e., the amount of salt, acid, spicy and/or sweet corresponding to the taste of the user to be eaten. Specifically, the dish information of the dish to be cooked, such as the name of the dish, may be determined according to the identified first food material collocation information of the dish to be cooked, and the salt amount, the acid amount, the spicy amount and/or the sweet amount corresponding to the dish to be cooked are obtained according to the dish information of the dish to be cooked. In a specific embodiment, the eating habit data of different users, that is, the corresponding relationship between different dishes of different users and the corresponding amount of required seasoning, may be pre-stored, so as to obtain the amount of required seasoning, such as the amount of salt, the amount of acid, the amount of spicy and/or the amount of sweet, corresponding to the dish to be cooked from the corresponding relationship according to the dish information of the dish to be cooked. The salt amount can be specifically the salt amount; the acid amount can be the amount of vinegar; the sweet amount can be the amount of sugar; the spicy content can be the consumption of the hot pepper. In one embodiment, the first user eating habit data may be set by the user himself, for example, the user may set the salt content, the acid content and/or the sweet content of a certain dish himself. In one embodiment, the eating habit data of the user to eat can be collected according to historical cooking parameters of the cooking machine.
After the obtaining unit 110 obtains the first user eating habit data of the user to be used, when the control unit 130 controls the cooker to cook the food material to be cooked, a corresponding amount of seasoning may be added to the cooker according to the first user eating habit data. That is, according to the amount of the required seasoning corresponding to the dish to be cooked, the corresponding amount of seasoning is added into the cooker, for example, the corresponding amount of salt is added according to the amount of salt corresponding to the dish to be cooked, the corresponding amount of vinegar is added according to the corresponding amount of sour of the dish to be cooked, and the corresponding amount of pepper is added according to the corresponding amount of hot and/or sweet of the dish to be cooked.
The decision unit 120 inputs the first food material collocation information and the first user eating habit data into a pre-established cooking parameter decision model so as to output a first cooking parameter of the cooker.
The cooking parameter decision model is used for determining a first cooking parameter of the cooking machine, namely determining an optimal cooking parameter of the food to be cooked placed in the current cooking machine. The first cooking parameter may specifically include at least one of cooking temperature, heating time and color of the dish, and the color of the dish may be specifically shown in a picture form. The decision unit 120 inputs the first food material collocation information and the first user dietary habit data into a pre-established cooking parameter decision model, and may output a first cooking parameter for the food material to be cooked currently placed in the cooker.
The fried dish parameter decision model is established in the following way:
(1) and collecting historical cooking data of the cooker.
The historical cooking data may specifically include second food material collocation information and corresponding second user eating habit data of food materials contained in different dishes cooked by the cooking machine historically, and second cooking parameters of the cooking machine corresponding to the second food material collocation information and the second user eating habit data.
Specifically, when the cooking machine cooks, second food material collocation information of food materials contained in dishes cooked by the cooking machine and corresponding second user dietary habit data can be recorded, and corresponding second cooking parameters of the cooking machine can be recorded. The second food material matching information comprises food material types and/or food material names of food materials contained in different dishes cooked by the cooking machine historically. The second user eating habit data may specifically include the usage amount of the required seasoning corresponding to different dishes cooked by the cooker historically, for example, the usage amount includes the salt amount, the acid amount, the spicy amount and/or the sweet amount corresponding to different dishes cooked by the cooker historically. The salt amount can be specifically the salt amount; the acid amount can be the amount of vinegar; the sweet amount can be the amount of sugar; the spicy content can be the consumption of the hot pepper. In one embodiment, the second user eating habit data may be set by the user himself, for example, the user may himself set the salt content, the acid content and/or the sweet content of a certain dish. The second cooking parameter comprises at least one of cooking temperature, heating time and color of dishes. The cooking temperature and/or the heating time in the second cooking parameter can be set by a user, for example, the user can set the cooking temperature and/or the heating time according to the user's own needs, and/or the color of the dish in the second cooking parameter can be displayed by collecting an image of the dish when the cooking of the corresponding dish is completed, through the image of the dish.
(2) And inputting the second food material collocation information, the second user dietary habit data and the second cooking parameter as training samples into a preset neural network for model training to obtain the cooking parameter decision model.
Specifically, generating a feature matrix from the second food material collocation information, the second user eating habit data and the second cooking parameter; and inputting the generated characteristic matrix into the preset neural network for model training to obtain the cooking parameter decision model. More specifically, the collected second food material collocation information, the second user eating habit data and the second cooking parameter are used as data samples to be preprocessed, namely, a feature matrix is generated. For example, a feature matrix may be generated by taking data samples according to different features, each feature as a column and each sample as a row. Specific feature matrices may be found in the following table (where specific values are for illustration only):
TABLE 1
Fig. 2 is a schematic structural diagram of a neural network according to an embodiment of the present invention. As shown in fig. 2, which is a schematic structural diagram of a deep neural network, a neural network is mainly composed of three parts, namely an input layer, a hidden layer and an output layer. The input layer and the output layer are only one layer, the hidden layer can be a plurality of layers, and the deep neural network is a neural network with a plurality of hidden layers. Fig. 2 shows a neural network with two hidden layers. At the input level, each neuron x represents an input Feature (Feature), and b is a Feature-independent bias value. The input features are converted by the activation function and enter the hidden layer 1, and similarly, the result of the hidden layer 1 is converted again and enters the hidden layer 2, and finally reaches the output layer, namely the probability values of various types of y are output.
The input sample vector may be represented as X ═ (X1, X2, X3, …, xn), the corresponding class is Y ═ (Y1, Y2, …, ym), and the initialized weight matrix is W. Specifically, in the sample vector X, each component represents a feature, for example, X1 is the amount of acid, X2 is the amount of sweet, X3 is the amount of spicy, and X4 is the amount of salt. The category vector Y is a set of categories to be output, and there are several components to output several categories. For example, two categories of cooking temperature and heating time need to be output, and then the components y1 and y2 represent cooking temperature and heating time, respectively. The weight matrix W is a parameter matrix and is a set of weights of each layer of neurons in the neural network linking with the next layer of neurons, in the training process of the neural network, W is continuously adjusted and changed, when the training is finished, W tends to be a stable value, and the purpose of training the neural network is to determine the optimal weight matrix W.
Preferably, the above model training is performed by using an error Back Propagation algorithm (Back Propagation), and the activation function of the neuron selects a ReLU (linear correction unit) because the ReLU function has simple gradient calculation and fast convergence. And calculating error loss of actual output and expected output (second cooking parameter) each time, performing back propagation according to a loss result, updating the weight matrix W of each layer, finally obtaining stable weight W when the algorithm is converged, finishing algorithm training, and storing a final neural network model, namely the cooking parameter decision model, which is used for making a decision of the current first cooking parameter of the cooking machine.
The control unit 130 controls the cooker to cook the food material to be cooked according to the output first cooking parameter of the cooker.
The decision unit 120 inputs the first food material collocation information and the first user eating habit data into a pre-established cooking parameter decision model, and outputs a first cooking parameter of the cooker for cooking the current dish to be cooked, that is, a current optimal cooking parameter, and then the control unit 130 may control the cooker to cook the dish to be cooked according to the first cooking parameter. For example, when the current cooking temperature of the cooker reaches the first cooking temperature, and/or the cooker reaches the first heating time for the current cooking time of the dish to be cooked, and/or image acquisition is performed on the dish to be cooked in the cooker in real time, the control unit 130 controls the cooker to stop cooking by comparing the dish image of the dish to be cooked with the dish color image showing the first dish color, and when it is determined according to the dish image that the dish color of the dish to be cooked matches the first dish color. When the control unit 130 controls the cooker to cook the food material to be cooked, a corresponding amount of seasoning may be added to the cooker according to the first user eating habit data, where the first user eating habit data specifically may include: the amount of the needed seasoning corresponding to the dish to be cooked.
The invention also provides a storage medium corresponding to the method for controlling a cooker, on which a computer program is stored, which program, when executed by a processor, carries out the steps of any of the methods described above.
The invention also provides a cooker corresponding to the cooker control method, which comprises a processor, a memory and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of any one of the methods.
The invention also provides a cooker corresponding to the cooker control device, which comprises any one of the cooker control devices.
According to the scheme provided by the invention, the acquired first food material collocation information of the dish to be cooked in the dish frying machine and the first user diet habit data of the user to be eaten are input into the pre-established dish frying parameter decision model, the first dish frying parameter of the dish to be cooked in the current dish frying machine is output by the dish frying machine, the dish frying machine is controlled to cook the dish to be cooked according to the output first dish frying parameter, and the decision on the dish frying parameter corresponding to the dish to be cooked can be carried out according to the food material collocation information of the dish to be cooked and the diet habit data of the user, so that the dish frying machine can fry the dish suitable for the taste of the user, and the user demand can be further met.
The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope and spirit of the invention and the following claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwired, or a combination of any of these. In addition, each functional unit may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and the parts serving as the control device may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The above description is only an example of the present invention, and is not intended to limit the present invention, and it is obvious to those skilled in the art that various modifications and variations can be made in the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (15)
1. A control method of a cooker is characterized by comprising the following steps:
acquiring first food material collocation information of dishes to be cooked in the cooker and first user diet habit data of a user to be eaten;
inputting the first food material collocation information and the first user dietary habit data into a pre-established cooking parameter decision model so as to output a first cooking parameter of the cooking machine;
and controlling the frying machine to cook the dish to be cooked according to the output first frying parameter of the frying machine.
2. The method of claim 1,
the first food material collocation information includes: the food material types and/or food material names of food materials contained in the dishes to be cooked;
and/or the presence of a gas in the gas,
the first user eating habit data comprises: the amount of salt, acid, spicy and/or sweet corresponding to the dishes to be cooked;
and/or the presence of a gas in the gas,
the first dish frying parameter comprises: at least one of the first frying temperature, the first heating time and the first dish color.
3. The method of claim 1 or 2, wherein obtaining first food material collocation information of the dishes to be cooked in the cooker comprises:
collecting food material images of food materials placed in the dish frying machine;
and carrying out image recognition on the food material image so as to recognize first food material matching information of the dish to be cooked.
4. The method of any of claims 1-3, wherein the fry parameter decision model is established by:
collecting historical cooking data of the cooker; the historical cooking data includes: historically, second food material collocation information and corresponding second user eating habit data of food materials contained in different dishes cooked by the cooking machine, and second cooking parameters of the cooking machine corresponding to the second food material collocation information and the second user eating habit data;
and inputting the second food material collocation information, the second user dietary habit data and the second cooking parameter as training samples into a preset neural network for model training to obtain the cooking parameter decision model.
5. The method of claim 4, wherein inputting the second food material collocation information, the second user eating habit data and the second cooking parameter as training samples into a preset neural network for model training to obtain the cooking parameter decision model comprises:
generating a characteristic matrix by using the second food material collocation information, the second user eating habit data and the second cooking parameter;
and inputting the generated characteristic matrix into the preset neural network for model training to obtain the cooking parameter decision model.
6. The method according to claim 4 or 5,
the second food material matching information includes: the food material types and/or food material names of food materials contained in different dishes;
and/or the presence of a gas in the gas,
the second user eating habit data comprises: the salt content, the acid content, the spicy content and/or the sweet content corresponding to different dishes;
and/or the presence of a gas in the gas,
the second cooking parameter comprises: at least one of a second frying temperature, a second heating time and a second dish color.
7. A cooker control device, characterized by comprising:
the acquisition unit is used for acquiring first food material collocation information of dishes to be cooked in the cooker and first user diet habit data of a user to be eaten;
the decision unit is used for inputting the first food material collocation information and the first user dietary habit data into a pre-established cooking parameter decision model so as to output a first cooking parameter of the cooking machine;
and the control unit is used for controlling the frying machine to cook the dish to be cooked according to the output first frying parameter of the frying machine.
8. The apparatus of claim 7,
the first food material collocation information includes: the food material types and/or food material names of food materials contained in the dishes to be cooked;
and/or the presence of a gas in the gas,
the first user eating habit data comprises: the amount of salt, acid, spicy and/or sweet corresponding to the dishes to be cooked;
and/or the presence of a gas in the gas,
the first dish frying parameter comprises: at least one of the first frying temperature, the first heating time and the first dish color.
9. The apparatus according to claim 7 or 8, wherein the obtaining unit obtains first food material collocation information of the dishes to be cooked in the cooker, and comprises:
collecting food material images of food materials placed in the dish frying machine;
and carrying out image recognition on the food material image so as to recognize first food material matching information of the dish to be cooked.
10. The apparatus of any of claims 7-9, wherein the cooking parameter decision model is established by:
collecting historical cooking data of the cooker; the historical cooking data includes: historically, second food material collocation information and corresponding second user eating habit data of food materials contained in different dishes cooked by the cooking machine, and second cooking parameters of the cooking machine corresponding to the second food material collocation information and the second user eating habit data;
and inputting the second food material collocation information, the second user dietary habit data and the second cooking parameter as training samples into a preset neural network for model training to obtain the cooking parameter decision model.
11. The apparatus of claim 10, wherein inputting the second food material collocation information, the second user eating habit data and the second cooking parameter as training samples into a preset neural network for model training to obtain the cooking parameter decision model comprises:
generating a characteristic matrix by using the second food material collocation information, the second user eating habit data and the second cooking parameter;
and inputting the generated characteristic matrix into the preset neural network for model training to obtain the cooking parameter decision model.
12. The apparatus of claim 10 or 11,
the second food material matching information includes: the food material types and/or food material names of food materials contained in different dishes;
and/or the presence of a gas in the gas,
the second user eating habit data comprises: the salt content, the acid content, the spicy content and/or the sweet content corresponding to different dishes;
and/or the presence of a gas in the gas,
the second cooking parameter comprises: at least one of a second frying temperature, a second heating time and a second dish color.
13. A storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
14. A cooker comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor when executing the program implementing the steps of the method of any one of claims 1 to 6.
15. A cooker comprising cooker control means as claimed in any one of claims 7 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910134074.7A CN111603050A (en) | 2019-02-22 | 2019-02-22 | Method and device for controlling cooker, storage medium and cooker |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910134074.7A CN111603050A (en) | 2019-02-22 | 2019-02-22 | Method and device for controlling cooker, storage medium and cooker |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111603050A true CN111603050A (en) | 2020-09-01 |
Family
ID=72193722
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910134074.7A Pending CN111603050A (en) | 2019-02-22 | 2019-02-22 | Method and device for controlling cooker, storage medium and cooker |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111603050A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112336172A (en) * | 2020-10-30 | 2021-02-09 | 广州富港万嘉智能科技有限公司 | Method for controlling intelligent cooking equipment to make food, storage medium and intelligent cooking equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07313342A (en) * | 1994-05-27 | 1995-12-05 | Iseki & Co Ltd | Rice cooking pot |
| CN105631519A (en) * | 2015-12-31 | 2016-06-01 | 北京工业大学 | Convolution nerve network acceleration method based on pre-deciding and system |
| CN107991939A (en) * | 2017-12-27 | 2018-05-04 | 广东美的厨房电器制造有限公司 | Cooking control method and culinary art control device, storage medium and cooking equipment |
| CN108492861A (en) * | 2018-03-23 | 2018-09-04 | 四川长虹电器股份有限公司 | Accurate diet system for prompting and method |
| CN108852023A (en) * | 2018-06-27 | 2018-11-23 | 佛山市云米电器科技有限公司 | A kind of achievable intelligent interconnection scorches equipment |
-
2019
- 2019-02-22 CN CN201910134074.7A patent/CN111603050A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07313342A (en) * | 1994-05-27 | 1995-12-05 | Iseki & Co Ltd | Rice cooking pot |
| CN105631519A (en) * | 2015-12-31 | 2016-06-01 | 北京工业大学 | Convolution nerve network acceleration method based on pre-deciding and system |
| CN107991939A (en) * | 2017-12-27 | 2018-05-04 | 广东美的厨房电器制造有限公司 | Cooking control method and culinary art control device, storage medium and cooking equipment |
| CN108492861A (en) * | 2018-03-23 | 2018-09-04 | 四川长虹电器股份有限公司 | Accurate diet system for prompting and method |
| CN108852023A (en) * | 2018-06-27 | 2018-11-23 | 佛山市云米电器科技有限公司 | A kind of achievable intelligent interconnection scorches equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112336172A (en) * | 2020-10-30 | 2021-02-09 | 广州富港万嘉智能科技有限公司 | Method for controlling intelligent cooking equipment to make food, storage medium and intelligent cooking equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111684368B (en) | Food preparation method and system based on ingredient identification | |
| US20210228022A1 (en) | System and Method for Collecting and Annotating Cooking Images for Training Smart Cooking Appliances | |
| CN106485052A (en) | A kind of intelligent cooking system and method | |
| CN113133682B (en) | Cooking equipment, cooking curve adjusting method and adjusting device | |
| WO2019033843A1 (en) | Method, apparatus and system for controlling cooking utensil | |
| CN110123149A (en) | A kind of cooking control method and cooking equipment of cooking equipment | |
| CN108133743A (en) | A kind of methods, devices and systems of information push | |
| CN109431288A (en) | A kind of electric cooker control method, device, storage medium and electric cooker | |
| CN111345665B (en) | Cooking method and cooking device | |
| CN107665198A (en) | Image-recognizing method, server, terminal and refrigerating equipment | |
| CN104112217A (en) | Taste selection information marking method and application method | |
| CN107566908A (en) | Intelligent television obtains method, intelligent television and the storage medium of menu | |
| CN107679951A (en) | A kind of method and apparatus for aiding in ordering dishes | |
| CN110222720A (en) | A kind of cooking equipment with short video acquisition function | |
| CN110858279A (en) | Food material identification method and device | |
| CN115251719A (en) | Menu entering system of intelligent cooker | |
| CN110989389A (en) | Menu adjusting method and device | |
| CN111291262A (en) | Generation method and system of catering service scheme | |
| CN111603050A (en) | Method and device for controlling cooker, storage medium and cooker | |
| CN109062277B (en) | The heating means and device of food, storage medium, processor | |
| CN108013733A (en) | Cooking control method, device and system | |
| CN111435229A (en) | Method and device for controlling cooking mode and cooking appliance | |
| CN109732615A (en) | Cooking robot and its cooking control method, device, storage medium and server | |
| CN116796078A (en) | Method and device for intelligently matching menu coefficients based on weight of food materials | |
| WO2020075418A1 (en) | Information processing device, information processing method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200901 |