CN111435229A - Method and device for controlling cooking mode and cooking appliance - Google Patents
Method and device for controlling cooking mode and cooking appliance Download PDFInfo
- Publication number
- CN111435229A CN111435229A CN201910033517.3A CN201910033517A CN111435229A CN 111435229 A CN111435229 A CN 111435229A CN 201910033517 A CN201910033517 A CN 201910033517A CN 111435229 A CN111435229 A CN 111435229A
- Authority
- CN
- China
- Prior art keywords
- food
- cooking
- cooking mode
- type
- module
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for controlling a cooking mode and a cooking appliance. Wherein, the method comprises the following steps: identifying the type of food to be cooked, and acquiring at least one type of taste data of the food customized by an operation object; determining a corresponding depth-determining policy gradient model based on the type of food; processing at least one sensory data of the food using the determined depth certainty strategy gradient model, obtaining adjustment data, wherein the adjustment data is used to adjust the cooking parameters; an adjusted cooking mode is determined based on the adjustment data. According to the scheme, the deep certainty strategy gradient algorithm of reinforcement learning is adopted, the personalized rice cooking mode is formulated according to the user requirement, and the technical problem that the cooking control method is inflexible due to the fact that the cooking mode of the cooking appliance is preset before the factory in the prior art is solved.
Description
Technical Field
The invention relates to the field of intelligent small household appliances, in particular to a method and a device for controlling a cooking mode and a cooking appliance.
Background
With the pace of life increasing, people stay in the kitchen for less and less time, and therefore, a cooking appliance which is simple and easy to operate, meets the taste of a user, and can perfectly exert the nutrition contained in food is urgently needed to be developed. The electric cooker is an essential cooking tool in life of people, and the traditional electric cooker usually adopts the same cooking mode aiming at different rice grain types, so that the taste of rice is good and bad; the control mode of the electric cooker is developed from simple mechanical control to the current microcomputer control, fuzzy control and the like, although the functions of the electric cooker are also developed from a single rice cooking function to multiple purposes and have different rice cooking modes, the cooking mode of the electric cooker is still a preset fixed mode from a factory, and the individual requirements of users cannot be fully met.
Aiming at the problem that in the prior art, a cooking mode of a cooking appliance is preset before factory installation, so that a cooking control method is inflexible, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the invention provides a method and a device for controlling a cooking mode and a cooking appliance, and at least solves the technical problem that in the prior art, the cooking mode of the cooking appliance is preset before a factory, so that the cooking control method is inflexible.
According to an aspect of an embodiment of the present invention, there is provided a method of controlling a cooking mode, including: identifying the type of food to be cooked, and acquiring at least one type of taste data of the food customized by an operation object; determining a corresponding depth-determining policy gradient model based on the type of food; processing at least one sensory data of the food using the determined depth certainty strategy gradient model, obtaining adjustment data, wherein the adjustment data is used to adjust the cooking parameters; an adjusted cooking mode is determined based on the adjustment data.
Optionally, before processing at least one of the sensory data of the food using the determined depth-deterministic policy gradient model to obtain the adjustment data, the method further comprises: different depth certainty strategy gradient models are obtained by training different kinds of food, and corresponding cooking modes are formulated according to the different depth certainty strategy gradient models.
Optionally, after identifying the type of food to be cooked, the method further comprises: judging whether an instruction for entering a cooking mode is received; if an instruction is received, entering a step of acquiring at least one type of taste data of food customized by an operation object; and if the instruction is not received, controlling the cooking appliance to work according to a preset cooking mode.
Optionally, after determining the adjusted cooking mode based on the adjustment data, the method further comprises: controlling the cooking appliance to work according to the adjusted cooking mode; and storing the association relationship between the type of the food and the corresponding cooking mode into a cooking database.
Optionally, after storing the association between the type of the food and the corresponding cooking mode, the method further includes: if the cooking appliance is detected to be put into new food, identifying the type of the new food; inquiring whether a corresponding cooking mode exists in a cooking database based on the type of the new food; if the corresponding cooking mode is inquired, controlling the cooking appliance to work according to the inquired cooking mode; and if the corresponding cooking mode is not inquired, controlling the cooking appliance to work according to the preset cooking mode.
Optionally, before controlling the cooking appliance to operate according to the queried cooking mode, the method further includes: outputting inquiry information, wherein the inquiry information comprises a voice prompt and/or a text prompt and is used for prompting an operation object to update the taste data; if the operation object inputs new taste data based on the prompt information, processing the updated taste data by using a corresponding depth certainty strategy gradient model, and acquiring updated adjustment data; and adjusting the inquired cooking mode based on the updated adjustment data.
Optionally, the cooking mode corresponding to the food in the cooking database is updated based on the adjusted cooking mode.
Optionally, identifying the type of food to be cooked includes: acquiring a food image of food to be cooked; and identifying the food image by using the convolutional neural network model, and determining the type of the food in the food image.
Optionally, identifying the food image using a convolutional neural network model, determining a type of food in the food image, comprising: segmenting the food image to obtain a plurality of sub-pictures; processing a plurality of sub-pictures by using a convolutional neural network model, and identifying food in each sub-picture; carrying out contour extraction on the sub-pictures with the recognized food, and setting the areas without the recognized food as a preset background to obtain a plurality of processed sub-pictures; and (4) splicing the plurality of processed sub-pictures to obtain a restored food picture.
Optionally, after the combining the plurality of processed sub-pictures to obtain the restored food picture, the method further includes: outputting the restored food picture, and extracting a food outline in the restored food picture; and determining the type of the food based on the food outline in the restored food picture.
According to another aspect of the embodiments of the present invention, there is also provided an apparatus for controlling a cooking mode, including: the identification module is used for identifying the type of food to be cooked and acquiring at least one type of taste data of the food customized by an operation object; a first determination module for determining a corresponding depth certainty strategy gradient model based on a category of food; a first adjusting module, configured to process at least one sensory data of the food using the determined depth certainty strategy gradient model, and obtain an adjustment data, where the adjustment data is used to adjust a cooking parameter; a second determination module for determining an adjusted cooking mode based on the adjustment data.
Optionally, the apparatus further comprises: the making module is used for training different types of food to obtain different depth certainty strategy gradient models and making corresponding cooking modes according to the different depth certainty strategy gradient models before the determined depth certainty strategy gradient models are used for processing at least one type of taste data of the food and obtaining adjustment data.
Optionally, the apparatus further comprises: the judging module is used for judging whether an instruction for entering a cooking mode is received or not after the type of food to be cooked is identified; the execution module is used for entering the step of acquiring at least one type of taste data of food customized by the operation object if the instruction is received; and if the instruction is not received, controlling the cooking appliance to work according to a preset cooking mode.
Optionally, the apparatus further comprises: the control module is used for controlling the cooking appliance to work according to the adjusted cooking mode after the adjusted cooking mode is determined based on the adjustment data; and the storage module is used for storing the association relationship between the type of the food and the corresponding cooking mode into a cooking database.
Optionally, the apparatus further comprises: the new food identification module is used for identifying the type of the new food if the cooking appliance is detected to be put into the new food after the incidence relation between the type of the food and the corresponding cooking mode is stored; the new food inquiry module is used for inquiring whether a corresponding cooking mode exists in the cooking database or not based on the type of the new food; the new food control module is used for controlling the cooking appliance to work according to the inquired cooking mode if the corresponding cooking mode is inquired; and if the corresponding cooking mode is not inquired, controlling the cooking appliance to work according to the preset cooking mode.
Optionally, the apparatus further comprises: the output module is used for outputting inquiry information before controlling the cooking appliance to work according to the inquired cooking mode, wherein the inquiry information comprises voice prompt and/or text prompt and is used for prompting an operation object to update the taste data; the processing module is used for processing the updated taste data by using a corresponding depth certainty strategy gradient model and acquiring updated adjustment data if the operation object inputs new taste data based on the prompt information; and the second adjusting module adjusts the inquired cooking mode based on the updated adjusting data.
Optionally, the apparatus further includes an updating module, configured to update the cooking mode corresponding to the food in the cooking database based on the adjusted cooking mode.
Optionally, the identification module comprises: the acquisition module is used for acquiring a food image of food to be cooked; and the third determining module is used for identifying the food image by using the convolutional neural network model and determining the type of the food in the food image.
Optionally, the third determining module includes: the segmentation module is used for segmenting the food image to obtain a plurality of sub-pictures; the sub-picture processing module is used for processing a plurality of sub-pictures by using the convolutional neural network model and identifying food in each sub-picture; the first extraction module is used for extracting the outline of the sub-picture with the recognized food, and setting the area without the recognized food as a preset background to obtain a plurality of processed sub-pictures; and the splicing module is used for splicing the plurality of processed sub-pictures to obtain the restored food picture.
Optionally, the apparatus further comprises: the second extraction module is used for outputting the restored food picture after the plurality of processed sub-pictures are spliced to obtain the restored food picture, and extracting the food outline in the restored food picture; and the third determining submodule is used for determining the type of the food based on the food outline in the restored food picture.
According to another aspect of the embodiments of the present invention, there is also provided a storage medium including a stored program, wherein when the program is executed, an apparatus in which the storage medium is controlled performs any one of the above methods of controlling a cooking mode.
According to another aspect of the embodiments of the present invention, there is also provided a processor for executing a program, wherein the program executes any one of the above methods for controlling a cooking mode.
According to another aspect of the embodiments of the present invention, there is also provided a cooking appliance including: the image acquisition device is used for acquiring an image of food to be cooked; a controller for executing the program, wherein the following processing steps are executed on the data output from the image acquisition device when the program is executed: identifying the type of food to be cooked, and acquiring at least one type of taste data of the food customized by an operation object; determining a corresponding depth-determining policy gradient model based on the type of food; processing at least one sensory data of the food using the determined depth certainty strategy gradient model, obtaining adjustment data, wherein the adjustment data is used to adjust the cooking parameters; an adjusted cooking mode is determined based on the adjustment data.
In the embodiment of the invention, the type of food to be cooked is identified, and at least one type of taste data of the food customized by an operation object is obtained; determining a corresponding depth-determining policy gradient model based on the type of food; processing at least one sensory data of the food using the determined depth certainty strategy gradient model, obtaining adjustment data, wherein the adjustment data is used to adjust the cooking parameters; an adjusted cooking mode is determined based on the adjustment data. According to the scheme, a deep certainty strategy gradient algorithm of reinforcement learning is adopted, different cooking modes corresponding to different original food types are adjusted according to a user preference training algorithm, and the technical problem that a cooking control method is inflexible due to the fact that the cooking modes of cooking appliances are preset in a factory in the prior art is solved.
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 application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of an alternative method of controlling a cooking mode according to an embodiment of the present application;
FIG. 2 is an alternative deep deterministic strategy gradient algorithm learning flow diagram according to an embodiment of the application;
FIG. 3 is a learning flow chart of an alternative depth deterministic strategy gradient algorithm for controlling an electric rice cooker according to an embodiment of the present application;
FIG. 4 is a flow chart of an alternative personalized cooking profile according to an embodiment of the present application; and
fig. 5 is a schematic diagram of an alternative apparatus for controlling a cooking mode according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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, apparatus, system, article, or device 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, apparatus, article, or device.
Example 1
In accordance with an embodiment of the present invention, there is provided an embodiment of a method of controlling a cooking mode, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system, such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than presented herein.
Fig. 1 is a flowchart of a method of controlling a cooking mode according to an embodiment of the present invention, as shown in fig. 1, the method including the steps of:
step S102, identifying the type of food to be cooked, and acquiring at least one type of taste data of the food customized by the operation object.
In one alternative, the food may be granular grains such as rice, glutinous rice, corn, soybean, etc. The identification mode can be user experience identification, mobile phone APP photographing identification, network platform search and the like. The taste data can be soft, moderate, hard, fragrant, and nutritious.
Before cooking starts, the type of food to be cooked and the taste preference of the user need to be acquired.
And step S104, determining a corresponding depth certainty strategy gradient model based on the food type.
The Deep Deterministic Policy Gradient (DDPG) algorithm is a reinforcement learning algorithm based on an action-state (critic) framework.
Fig. 2 is a flow chart of a deep deterministic strategy gradient algorithm learning according to an embodiment of the application. As shown in fig. 2, the DDPG model includes an action network including an action-target-net (Actor-target-net) and an action-reality network (Actor-eval-net), a state network including a state-estimation network (critical-target-net) and a state-reality network (critical-eval-net), and a storage memory table, each row of the storage memory table stores a current state, an action, a reward, and a next state for learning the deep neural network model. The DDPG model comprises four deep neural networks, and the four deep neural networks are arranged in a structure of 4 layers. The control action comprises temperature, the running state comprises water adding amount, pressure, humidity and the like, and the reward is equipment which can be connected to a system inside the cooking appliance in the learning process and is used for detecting the characteristics of the food and judging the characteristics of the food by a user. The input of the action reality network is the current state, and the output is the action; the input of the action estimation network is the next state, and the output is the estimation action; the input of the state reality network is the current state and the actually executed action, and the output is an action-state value function Q; the input of the state estimation network is the next state and the estimated action of the action estimation network output, and the output is the action-state value function estimated value Q'. After a certain number of iterations, the real network parameters are copied to the estimation network.
And step S106, processing at least one type of taste data of the food by using the determined depth certainty strategy gradient model, and acquiring adjustment data, wherein the adjustment data is used for adjusting cooking parameters.
Step S108, the adjusted cooking mode is determined based on the adjustment data.
Taking rice as an example, fig. 3 is a learning flow chart of a DDPG algorithm controlled electric rice cooker according to an embodiment of the present application. Different DDPG models are trained and learned for different types of rice, and corresponding rice steaming modes are formulated. On the basis, different DDPG models are adjusted to have certain characteristics of rice after rice steaming, such as softness, fragrance, glutinousness and the like of the rice. In the learning process, equipment capable of detecting food characteristics, such as a temperature and humidity sensor, a pressure sensor and the like, is arranged in the cooking appliance, and meanwhile, the judgment of a user on the rice characteristics is added, and the two are used as reward mechanisms in DDPG learning. Then on the basis that different kinds of rice correspond to different DDPG models, learning the variation of the action parameters required for changing the characteristic degree of the rice, so as to learn the variation of the action control parameters of different degrees of the electric cooker required by the characteristics of different degrees, and determining the adjusted cooking mode based on the parameter variation.
Based on the scheme provided by the embodiment of the application, the type of food to be cooked is identified, and at least one type of taste data of the food customized by an operation object is obtained; determining a corresponding depth-determining policy gradient model based on the type of food; processing at least one sensory data of the food using the determined depth certainty strategy gradient model, obtaining adjustment data, wherein the adjustment data is used to adjust the cooking parameters; an adjusted cooking mode is determined based on the adjustment data. According to the scheme, a deep certainty strategy gradient algorithm of reinforcement learning is adopted, different cooking modes corresponding to different original food types are adjusted according to a user preference training algorithm, and the technical problem that a cooking control method is inflexible due to the fact that the cooking modes of cooking appliances are preset in a factory in the prior art is solved.
Optionally, before processing at least one of the sensory data of the food using the determined depth-deterministic policy gradient model to obtain the adjustment data, the method further comprises: different depth certainty strategy gradient models are obtained by training different kinds of food, and corresponding cooking modes are formulated according to the different depth certainty strategy gradient models.
In one alternative, the cooking modes may include at least one or more of cooking temperatures, pressure in the cooking appliance, cooking time and venting time, and vent valve opening for different cooking stages.
Optionally, after identifying the type of food to be cooked, the method further comprises: judging whether an instruction for entering a cooking mode is received; if an instruction is received, entering a step of acquiring at least one type of taste data of food customized by an operation object; and if the instruction is not received, controlling the cooking appliance to work according to a preset cooking mode.
Before a user uses the cooking appliance to cook, the cooking appliance prompts the user whether a personalized cooking mode is needed. If the taste of the user is popular and is not needed, the cooking is carried out according to a cooking mode preset by the food type; if the user has unique taste and needs personalized cooking, the preference degrees of the user on several characteristics are collected according to the several characteristics of the preset food, then the data are transmitted to an intelligent chip or a server of the local equipment, the intelligent chip or the server of the local equipment can adjust parameters in the cooking process according to the DDPG model corresponding to the food type, and the adjusted control mode is transmitted to the electric cooker to control a corresponding execution mechanism to cook.
Optionally, after determining the adjusted cooking mode based on the adjustment data, the method further comprises: controlling the cooking appliance to work according to the adjusted cooking mode; and storing the association relationship between the type of the food and the corresponding cooking mode into a cooking database.
In an alternative, the association relationship may be stored in advance in a cooking database of a smart chip of the local device or a cloud server.
Because the association relationship between the food type and the corresponding cooking mode is stored in the cooking database in advance, the cooking mode corresponding to the food type can be obtained by the cooking appliance through a table look-up method after the food type is known, and the processing time is shortened.
Fig. 4 is a flow chart of an alternative personalized cooking mode according to an embodiment of the present application, and as shown in fig. 4, when a user needs to cook food, it is first necessary to identify the kind of food to be cooked. Before cooking, the system prompts a user whether an individual cooking mode is needed or not, and if not, the electric cooker is controlled to cook according to a preset cooking mode of the identified food type; if the requirement is met, the preference degrees of the user to the characteristics are collected according to the preset characteristics of the food, then the data are transmitted to the intelligent chip of the electric cooker, the intelligent chip can cook according to the DDPG model corresponding to the food types, the corresponding personalized cooking mode is stored, and the next query is facilitated.
Optionally, after storing the association between the type of the food and the corresponding cooking mode, the method further includes: if the cooking appliance is detected to be put into new food, identifying the type of the new food; inquiring whether a corresponding cooking mode exists in a cooking database based on the type of the new food; if the corresponding cooking mode is inquired, controlling the cooking appliance to work according to the inquired cooking mode; and if the corresponding cooking mode is not inquired, controlling the cooking appliance to work according to the preset cooking mode.
The tastes of users are diversified, and new food materials are inevitably used each time. If the cooking appliance is detected to be put in new food, the specific type of the new food is firstly identified, and then whether a corresponding cooking mode exists in the cooking database or not is inquired. If the corresponding cooking mode is stored in the cooking database, controlling the cooking appliance to work according to the inquired cooking mode; and if the corresponding cooking mode is not inquired, controlling the cooking appliance to work according to the cooking mode preset by the user so as to further save time.
Optionally, before controlling the cooking appliance to operate according to the queried cooking mode, the method further includes: outputting inquiry information, wherein the inquiry information comprises a voice prompt and/or a text prompt and is used for prompting an operation object to update the taste data; if the operation object inputs new taste data based on the prompt information, processing the updated taste data by using a corresponding depth certainty strategy gradient model, and acquiring updated adjustment data; and adjusting the inquired cooking mode based on the updated adjustment data.
In an alternative, the query message may be output through a display panel disposed on an outer surface of the cooking appliance, and the display panel is used for prompting a user whether to update the taste data.
And if the user inputs new taste data through the display panel, processing the updated taste data by using the corresponding DDPG model, acquiring updated adjustment data, and adjusting the inquired cooking mode based on the updated adjustment data.
Optionally, the cooking mode corresponding to the food in the cooking database is updated based on the adjusted cooking mode.
Through the culinary art mode that different food correspond in the continuous update culinary art database, can make cooking utensil more and more intelligent, accord with user's demand more.
Optionally, identifying the type of food to be cooked includes: acquiring a food image of food to be cooked; and identifying the food image by using the convolutional neural network model, and determining the type of the food in the food image.
The convolutional neural network belongs to a supervised learning algorithm, is a special case in a deep neural network, and has the advantages of small weight number, high training speed and the like compared with a deep artificial neural network.
The convolutional 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. The input layer of the convolutional neural network is a food image, and the food image is analyzed and calculated by using the convolutional neural network, so that the identified food type is output.
Optionally, identifying the food image using a convolutional neural network model, determining a type of food in the food image, comprising: segmenting the food image to obtain a plurality of sub-pictures; processing a plurality of sub-pictures by using a convolutional neural network model, and identifying food in each sub-picture; carrying out contour extraction on the sub-pictures with the recognized food, and setting the areas without the recognized food as a preset background to obtain a plurality of processed sub-pictures; and (4) splicing the plurality of processed sub-pictures to obtain a restored food picture.
In the above steps, the original food image is segmented to obtain a plurality of sub-pictures. The greater the number of sub-pictures, the greater the accuracy of identifying the food category. Then, image features of food contained in each sub-picture are extracted, contour extraction is performed on the sub-pictures in which food is recognized, and a region in which food is not recognized is set to a predetermined background color, for example, black. And then resetting and splicing each sub-picture according to the segmentation sequence to obtain a restored food profile map.
Optionally, after the combining the plurality of processed sub-pictures to obtain the restored food picture, the method further includes: outputting the restored food picture, and extracting a food outline in the restored food picture; and determining the type of the food based on the food outline in the restored food picture.
In the above steps, after the reduced food pictures are obtained by amalgamation, the reduced food pictures are output and the reduced overall food profile is extracted to determine the specific type of the food, for example, if rice is placed in the cooking appliance, the rice breaking rate, the germ remaining rice and the like can be determined by calculating parameters such as length-width ratio, projection area and the like, so as to prepare a personalized cooking scheme which accords with different rice grain ratios.
In the whole process of a complete individual cooking mode, rice is taken as an example, and when a user needs to cook rice, the user can take a picture and transmit the picture to an intelligent chip of the electric cooker to identify the rice type. Before cooking, the system prompts a user whether an individual cooking mode is needed or not, and if not, the user performs the cooking according to a preset cooking mode of the identified rice type; if the intelligent chip is required, the preference degrees of the user to the characteristics are collected according to the preset characteristics of the rice, then the data are transmitted to the intelligent chip of the electric cooker, the intelligent chip can adjust cooking control parameters according to the DDPG model corresponding to the rice type, the adjusted control mode is transmitted to the electric cooker, the electric cooker is controlled to cook, and the corresponding personalized cooking mode is stored.
When a user cooks the rice cooker next time, firstly, the user can take a picture of the rice to identify, the rice cooker can search a cooking mode used by the same kind of rice for the last time through the previous history record of the user, judge whether the cooking mode is a user personalized cooking mode, if the cooking mode is the personalized cooking mode, inquire about which adjustment needs to be made for the rice cooked by the previous personalized cooking mode, and adjust the cooking control mode of the rice cooker by using a reinforcement learning algorithm on the basis of the previous personalized cooking mode according to the suggestion of the user; and if the history of the personalized cooking mode does not exist, inquiring whether the user needs the personalized cooking mode, if so, inquiring the taste preference of the user, then training the learning control parameters by using the DDPG model, and if not, cooking according to the preset mode of the rice type.
By the scheme, the optimized control parameters corresponding to the cooking modes of each time are continuously adjusted according to the feedback of the user, the cooking modes with the taste required by the user are obtained, and meanwhile, if the user wants to change the taste, the control cooking parameters are adjusted through the feedback before cooking, so that the personalized cooking mode in the real sense is realized.
Example 2
According to an embodiment of the present invention, there is provided an apparatus for controlling a cooking mode, and fig. 5 is a schematic view of the apparatus for controlling a cooking mode according to an embodiment of the present application. As shown in fig. 5, the apparatus 500 includes:
the identification module 502 is used for identifying the type of food to be cooked and acquiring at least one type of taste data of the food customized by the operation object.
A first determination module 504 for determining a corresponding depth certainty strategy gradient model based on the type of food.
A first adjustment module 506 for processing at least one sensory data of the food using the determined depth-deterministic strategic gradient model, obtaining adjustment data, wherein the adjustment data is used for adjusting the cooking parameter.
A second determining module 508 for determining an adjusted cooking mode based on the adjustment data.
Optionally, the apparatus further comprises: the making module is used for training different types of food to obtain different depth certainty strategy gradient models and making corresponding cooking modes according to the different depth certainty strategy gradient models before the determined depth certainty strategy gradient models are used for processing at least one type of taste data of the food and obtaining adjustment data.
Optionally, the apparatus further comprises: the judging module is used for judging whether an instruction for entering a cooking mode is received or not after the type of food to be cooked is identified; the execution module is used for entering the step of acquiring at least one type of taste data of food customized by the operation object if the instruction is received; and if the instruction is not received, controlling the cooking appliance to work according to a preset cooking mode.
Optionally, the apparatus further comprises: the control module is used for controlling the cooking appliance to work according to the adjusted cooking mode after the adjusted cooking mode is determined based on the adjustment data; and the storage module is used for storing the association relationship between the type of the food and the corresponding cooking mode into a cooking database.
Optionally, the apparatus further comprises: the new food identification module is used for identifying the type of the new food if the cooking appliance is detected to be put into the new food after the incidence relation between the type of the food and the corresponding cooking mode is stored; the new food inquiry module is used for inquiring whether a corresponding cooking mode exists in the cooking database or not based on the type of the new food; the new food control module is used for controlling the cooking appliance to work according to the inquired cooking mode if the corresponding cooking mode is inquired; and if the corresponding cooking mode is not inquired, controlling the cooking appliance to work according to the preset cooking mode.
Optionally, the apparatus further comprises: the output module is used for outputting inquiry information before controlling the cooking appliance to work according to the inquired cooking mode, wherein the inquiry information comprises voice prompt and/or text prompt and is used for prompting an operation object to update the taste data; the processing module is used for processing the updated taste data by using a corresponding depth certainty strategy gradient model and acquiring updated adjustment data if the operation object inputs new taste data based on the prompt information; and the second adjusting module adjusts the inquired cooking mode based on the updated adjusting data.
Optionally, the apparatus further includes an updating module, configured to update the cooking mode corresponding to the food in the cooking database based on the adjusted cooking mode.
Optionally, the identification module comprises: the acquisition module is used for acquiring a food image of food to be cooked; and the third determining module is used for identifying the food image by using the convolutional neural network model and determining the type of the food in the food image.
Optionally, the third determining module includes: the segmentation module is used for segmenting the food image to obtain a plurality of sub-pictures; the sub-picture processing module is used for processing a plurality of sub-pictures by using the convolutional neural network model and identifying food in each sub-picture; the first extraction module is used for extracting the outline of the sub-picture with the recognized food, and setting the area without the recognized food as a preset background to obtain a plurality of processed sub-pictures; and the splicing module is used for splicing the plurality of processed sub-pictures to obtain the restored food picture.
Optionally, the apparatus further comprises: the second extraction module is used for outputting the restored food picture after the plurality of processed sub-pictures are spliced to obtain the restored food picture, and extracting the food outline in the restored food picture; and the third determining submodule is used for determining the type of the food based on the food outline in the restored food picture.
It should be noted that, reference may be made to the relevant description in embodiment 1 for optional or preferred embodiments of this embodiment, but the present invention is not limited to the disclosure in embodiment 1, and is not described herein again.
Example 3
According to an embodiment of the present invention, there is provided a storage medium including a stored program, wherein the method of controlling a cooking mode in embodiment 1 is performed by an apparatus in which the storage medium is controlled when the program is executed.
Example 4
According to an embodiment of the present invention, there is provided a processor for executing a program, wherein the program executes the method of controlling the cooking mode in embodiment 1.
Example 5
According to an embodiment of the present invention, there is provided a cooking appliance including:
the image acquisition device is used for acquiring an image of food to be cooked.
A controller for executing the program, wherein the following processing steps are executed on the data output from the image acquisition device when the program is executed: identifying the type of food to be cooked, and acquiring at least one type of taste data of the food customized by an operation object; determining a corresponding depth-determining policy gradient model based on the type of food; processing at least one sensory data of the food using the determined depth certainty strategy gradient model, obtaining adjustment data, wherein the adjustment data is used to adjust the cooking parameters; an adjusted cooking mode is determined based on the adjustment data.
It should be noted that, reference may be made to the relevant description in embodiment 1 for optional or preferred embodiments of this embodiment, but the present invention is not limited to the disclosure in embodiment 1, and is not described herein again.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
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, a division of a unit may be a division of a logic function, and an actual implementation may have another division, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or may not be 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 parts displayed as units 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.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
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 apparatus 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 foregoing is only a preferred embodiment of the present invention, and it should be noted that it is obvious to those skilled in the art that various modifications and improvements can be made without departing from the principle of the present invention, and these modifications and improvements should also be considered as the protection scope of the present invention.
Claims (23)
1. A method of controlling a cooking mode, comprising:
identifying the type of food to be cooked, and acquiring at least one type of taste data of the food customized by an operation object;
determining a corresponding depth-determining policy gradient model based on the category of the food;
processing at least one sensory data of the food using the determined depth-deterministic strategic gradient model, obtaining adjustment data, wherein the adjustment data is used to adjust a cooking parameter;
an adjusted cooking mode is determined based on the adjustment data.
2. The method of claim 1, wherein prior to processing at least one sensory data of the food using the determined depth-deterministic policy gradient model, obtaining adjustment data, the method further comprises:
different depth certainty strategy gradient models are obtained by training different kinds of food, and corresponding cooking modes are formulated according to the different depth certainty strategy gradient models.
3. The method according to claim 1 or 2, wherein after identifying the kind of food to be cooked, the method further comprises:
judging whether an instruction for entering a cooking mode is received;
if the instruction is received, entering a step of acquiring at least one type of taste data of the food customized by an operation object;
and if the instruction is not received, controlling the cooking appliance to work according to a preset cooking mode.
4. The method according to claim 1 or 2, wherein after determining the adjusted cooking mode based on the adjustment data, the method further comprises:
controlling the cooking appliance to work according to the adjusted cooking mode;
and storing the association relationship between the type of the food and the corresponding cooking mode into a cooking database.
5. The method of claim 4, wherein after storing the association between the type of food and the corresponding cooking mode, the method further comprises:
if the cooking appliance is detected to be put in a new food, identifying the type of the new food;
querying whether a corresponding cooking mode exists in the cooking database based on the kind of the new food;
if the corresponding cooking mode is inquired, controlling the cooking appliance to work according to the inquired cooking mode;
and if the corresponding cooking mode is not inquired, controlling the cooking appliance to work according to the preset cooking mode.
6. The method of claim 5, wherein prior to controlling the cooking appliance to operate in the queried cooking mode, the method further comprises:
outputting inquiry information, wherein the inquiry information comprises a voice prompt and/or a text prompt for prompting the operation object to update the taste data;
if the operation object inputs new taste data based on the prompt information, processing the updated taste data by using a corresponding depth certainty strategy gradient model to obtain updated adjustment data;
and adjusting the inquired cooking mode based on the updated adjustment data.
7. The method of claim 6, wherein the cooking mode corresponding to the food item in the cooking database is updated based on the adjusted cooking mode.
8. The method of claim 1, wherein identifying the type of food to be cooked comprises:
acquiring a food image of the food to be cooked;
and identifying the food image by using a convolutional neural network model, and determining the type of food in the food image.
9. The method of claim 8, wherein identifying the food image using a convolutional neural network model, determining a type of food in the food image, comprises:
segmenting the food image to obtain a plurality of sub-pictures;
processing the plurality of sub-pictures using the convolutional neural network model, identifying food in each sub-picture;
carrying out contour extraction on the sub-pictures with the recognized food, and setting the areas without the recognized food as a preset background to obtain a plurality of processed sub-pictures;
and splicing the plurality of processed sub-pictures to obtain a restored food picture.
10. The method of claim 9, wherein after stitching the plurality of processed sub-pictures to obtain a reduced food picture, the method further comprises:
outputting the restored food picture, and extracting a food outline in the restored food picture;
determining the type of the food based on the food outline in the restored food picture.
11. An apparatus for controlling a cooking mode, comprising:
the identification module is used for identifying the type of food to be cooked and acquiring at least one type of taste data of the food customized by an operation object;
a first determination module to determine a corresponding depth certainty policy gradient model based on a category of the food;
a first adjustment module for processing at least one sensory data of the food using the determined depth-deterministic strategic gradient model, obtaining adjustment data, wherein the adjustment data is used to adjust a cooking parameter;
a second determination module for determining an adjusted cooking mode based on the adjustment data.
12. The apparatus of claim 11, further comprising:
the making module is used for training different types of food to obtain different depth certainty strategy gradient models and making corresponding cooking modes according to the different depth certainty strategy gradient models before the determined depth certainty strategy gradient models are used for processing at least one type of taste data of the food and obtaining adjustment data.
13. The apparatus of claim 11 or 12, further comprising:
the judging module is used for judging whether an instruction for entering a cooking mode is received or not after the type of food to be cooked is identified;
the execution module is used for entering the step of acquiring at least one type of taste data of the food customized by the operation object if the instruction is received; and if the instruction is not received, controlling the cooking appliance to work according to a preset cooking mode.
14. The apparatus of claim 11 or 12, further comprising:
the control module is used for controlling the cooking appliance to work according to the adjusted cooking mode after the adjusted cooking mode is determined based on the adjustment data;
and the storage module is used for storing the association relationship between the type of the food and the corresponding cooking mode into a cooking database.
15. The apparatus of claim 14, further comprising:
the new food identification module is used for identifying the type of the new food if the cooking appliance is detected to be put into the new food after the association relationship between the type of the food and the corresponding cooking mode is stored;
the new food inquiry module is used for inquiring whether a corresponding cooking mode exists in the cooking database or not based on the type of the new food;
the new food control module is used for controlling the cooking appliance to work according to the inquired cooking mode if the corresponding cooking mode is inquired; and if the corresponding cooking mode is not inquired, controlling the cooking appliance to work according to the preset cooking mode.
16. The apparatus of claim 15, further comprising:
the output module is used for outputting inquiry information before controlling the cooking appliance to work according to the inquired cooking mode, wherein the inquiry information comprises a voice prompt and/or a text prompt and is used for prompting the operation object to update the taste data;
a processing module, configured to, if the operation object inputs new taste data based on the prompt information, process the updated taste data using a corresponding depth certainty policy gradient model, and obtain updated adjustment data;
and the second adjusting module is used for adjusting the inquired cooking mode based on the updated adjusting data.
17. The apparatus of claim 16, further comprising an updating module for updating the cooking mode corresponding to the food item in the cooking database based on the adjusted cooking mode.
18. The apparatus of claim 11, wherein the identification module comprises:
the acquisition module is used for acquiring a food image of the food to be cooked;
and the third determination module is used for identifying the food image by using a convolutional neural network model and determining the type of food in the food image.
19. The apparatus of claim 18, wherein the third determining module comprises:
the segmentation module is used for segmenting the food image to obtain a plurality of sub-pictures;
the sub-picture processing module is used for processing the plurality of sub-pictures by using the convolutional neural network model and identifying food in each sub-picture;
the first extraction module is used for extracting the outline of the sub-picture with the recognized food, and setting the area without the recognized food as a preset background to obtain a plurality of processed sub-pictures;
and the splicing module is used for splicing the plurality of processed sub-pictures to obtain a restored food picture.
20. The apparatus of claim 19, further comprising:
the second extraction module is used for outputting the restored food picture after the plurality of processed sub-pictures are spliced to obtain the restored food picture, and extracting the food outline in the restored food picture;
and the third determining submodule is used for determining the type of the food based on the food outline in the restored food picture.
21. A storage medium comprising a stored program, wherein the apparatus on which the storage medium is located is controlled to perform the method of controlling a cooking mode according to any one of claims 1 to 10 when the program is run.
22. A processor for running a program, wherein the program when running performs the method of controlling a cooking mode of any one of claims 1 to 10.
23. A cooking appliance, comprising:
the image acquisition device is used for acquiring an image of food to be cooked;
a controller for executing a program, wherein the following processing steps are performed on data output from the image acquisition apparatus when the program is executed: identifying the type of food to be cooked, and acquiring at least one type of taste data of the food customized by an operation object; determining a corresponding depth-determining policy gradient model based on the category of the food; processing at least one sensory data of the food using the determined depth-deterministic strategic gradient model, obtaining adjustment data, wherein the adjustment data is used to adjust a cooking parameter; an adjusted cooking mode is determined based on the adjustment data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910033517.3A CN111435229A (en) | 2019-01-14 | 2019-01-14 | Method and device for controlling cooking mode and cooking appliance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910033517.3A CN111435229A (en) | 2019-01-14 | 2019-01-14 | Method and device for controlling cooking mode and cooking appliance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111435229A true CN111435229A (en) | 2020-07-21 |
Family
ID=71580732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910033517.3A Pending CN111435229A (en) | 2019-01-14 | 2019-01-14 | Method and device for controlling cooking mode and cooking appliance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111435229A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113435279A (en) * | 2021-06-17 | 2021-09-24 | 青岛海尔科技有限公司 | Cooking time reminding method and device, storage medium and electronic device |
| CN113796717A (en) * | 2021-10-11 | 2021-12-17 | 熊作芒 | Intelligent tea set based on reinforcement learning |
| EP4260771A1 (en) | 2022-04-13 | 2023-10-18 | Seb S.A. | Method for determining at least one cooking parameter of a cooking appliance from a plurality of images |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012127412A1 (en) * | 2011-03-24 | 2012-09-27 | Koninklijke Philips Electronics N.V. | Preparation of food controlled by a taste sensor |
| CN105212685A (en) * | 2015-10-20 | 2016-01-06 | 上海纯米电子科技有限公司 | The method for pushing of a kind of cooking process and sensory analysis and cloud electric cooker system |
| CN106580063A (en) * | 2017-02-10 | 2017-04-26 | 浙江苏泊尔家电制造有限公司 | Cooking device |
| CN106897661A (en) * | 2017-01-05 | 2017-06-27 | 合肥华凌股份有限公司 | A kind of Weigh sensor method of food materials image, system and household electrical appliance |
| CN109090983A (en) * | 2018-09-05 | 2018-12-28 | 深圳市猎搜有限公司 | The control method and control device that intelligent electric cooker is cooked |
-
2019
- 2019-01-14 CN CN201910033517.3A patent/CN111435229A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012127412A1 (en) * | 2011-03-24 | 2012-09-27 | Koninklijke Philips Electronics N.V. | Preparation of food controlled by a taste sensor |
| CN105212685A (en) * | 2015-10-20 | 2016-01-06 | 上海纯米电子科技有限公司 | The method for pushing of a kind of cooking process and sensory analysis and cloud electric cooker system |
| CN106897661A (en) * | 2017-01-05 | 2017-06-27 | 合肥华凌股份有限公司 | A kind of Weigh sensor method of food materials image, system and household electrical appliance |
| CN106580063A (en) * | 2017-02-10 | 2017-04-26 | 浙江苏泊尔家电制造有限公司 | Cooking device |
| CN109090983A (en) * | 2018-09-05 | 2018-12-28 | 深圳市猎搜有限公司 | The control method and control device that intelligent electric cooker is cooked |
Non-Patent Citations (1)
| Title |
|---|
| 张法帅等: "基于深度强化学习的无人艇航行控制", 《计测技术》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113435279A (en) * | 2021-06-17 | 2021-09-24 | 青岛海尔科技有限公司 | Cooking time reminding method and device, storage medium and electronic device |
| CN113435279B (en) * | 2021-06-17 | 2023-12-19 | 青岛海尔科技有限公司 | Reminding method and device for cooking duration, storage medium and electronic device |
| CN113796717A (en) * | 2021-10-11 | 2021-12-17 | 熊作芒 | Intelligent tea set based on reinforcement learning |
| EP4260771A1 (en) | 2022-04-13 | 2023-10-18 | Seb S.A. | Method for determining at least one cooking parameter of a cooking appliance from a plurality of images |
| FR3134504A1 (en) | 2022-04-13 | 2023-10-20 | Seb S.A. | Method for determining at least one cooking parameter of a cooking appliance from a plurality of images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111435229A (en) | Method and device for controlling cooking mode and cooking appliance | |
| CN107468048A (en) | Cooking apparatus and its control method | |
| CN107725453B (en) | Fan and control method and system thereof | |
| CN108107762A (en) | Cooking control method and culinary art control device, storage medium and cooking equipment | |
| CN108181819A (en) | Inter-linked controlling method, device, system and the home appliance of home appliance | |
| US10995960B2 (en) | Food preparation entity | |
| CN109799761B (en) | Method and device for determining menu execution equipment and storage medium | |
| CN108538363A (en) | A kind of method and cooking appliance of determining culinary art pattern | |
| CN110726222B (en) | Air conditioner control method and device, storage medium and processor | |
| CN110826574A (en) | Food material maturity determination method and device, kitchen electrical equipment and server | |
| CN112782990A (en) | Control method and device of intelligent equipment, storage medium and electronic equipment | |
| CN108415301A (en) | Cook parameter modification method and device | |
| CN112146236A (en) | Adjusting system, control method, control device, line control device, server and medium | |
| AU2019302632B2 (en) | Method for operating a cooking appliance | |
| CN109407554A (en) | Kitchen automatic cooking control method, device, storage medium and computer equipment | |
| CN111435426A (en) | Method and device for determining cooking mode based on rice grain recognition result and cooking appliance | |
| CN110726214A (en) | Method and device for controlling air conditioner | |
| CN115762743A (en) | Home service system, method and device and computer equipment | |
| CN114052513B (en) | Cooking processing method and device, household appliance and storage medium | |
| CN114704948A (en) | Method and device for controlling air conditioner, air conditioner and storage medium | |
| CN116350085A (en) | Method and device for controlling a zone oven and zone oven | |
| CN116802681A (en) | Method for determining the end of a cooking time of a food item and household cooking appliance | |
| WO2018133850A1 (en) | Cooking method and device, display method and apparatus for control interface, and storage medium | |
| CN110895721B (en) | Method and device for predicting electric appliance function | |
| CN111722595B (en) | Operation control method and device, cooking utensil, remote control equipment and storage medium |
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: 20200721 |