CN109732615B - Cooking robot and cooking control method and device thereof, storage medium and server - Google Patents
Cooking robot and cooking control method and device thereof, storage medium and server Download PDFInfo
- Publication number
- CN109732615B CN109732615B CN201811535239.3A CN201811535239A CN109732615B CN 109732615 B CN109732615 B CN 109732615B CN 201811535239 A CN201811535239 A CN 201811535239A CN 109732615 B CN109732615 B CN 109732615B
- Authority
- CN
- China
- Prior art keywords
- cooking
- food material
- dish
- robot
- cooked
- 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.)
- Active
Links
Images
Abstract
The invention provides a cooking robot and a cooking control method, a cooking control device, a storage medium and a server thereof, wherein the method comprises the following steps: acquiring a cooking state detection model corresponding to each food material in the food materials contained in a dish to be cooked; the cooking state detection model corresponding to each food material is obtained by respectively carrying out model training on the basis of pre-collected cooking state data of each food material in the cooking process; when the dish is cooked, controlling the robot to cook each food material of the dish independently based on the cooking state detection model corresponding to each food material; and after each food material in the food materials contained in the dish is cooked to a preset cooking state, controlling the robot to perform mixed cooking on the food materials contained in the dish. According to the scheme provided by the invention, the cooking robot can be controlled to cook each food material of the dish to the optimal state independently, and then mix and heat the food materials, so that the requirement of a user on each food material is met.
Description
Technical Field
The invention relates to the field of robots, in particular to a cooking robot, a cooking control method and device thereof, a storage medium and a server.
Background
At present, the application of the robot is limited in the aspect of mechanical labor, and the application of technical labor is lacked. The difficulty of cooking dishes by using a robot is that whether the dishes are delicious and edible is identified, and the dish cooking is not perfect only by simple technologies such as image identification, and the like, so that a more optimized scheme for cooking the dishes by using the robot is required.
Disclosure of Invention
The present invention is directed to overcome the drawbacks of the prior art, and provides a cooking robot, a cooking control method and apparatus thereof, a storage medium, and a server, so as to solve the problem that the simple techniques of image recognition and the like are not complete enough in the prior art for cooking dishes by the robot.
One aspect of the present invention provides a cooking control method of a cooking robot, including: acquiring a cooking state detection model corresponding to each food material in the food materials contained in a dish to be cooked; the cooking state detection model corresponding to each food material is obtained by respectively carrying out model training on the basis of pre-collected cooking state data of each food material in the cooking process; when the dish is cooked, controlling the robot to cook each food material of the dish independently based on the cooking state detection model corresponding to each food material; and after each food material in the food materials contained in the dish is cooked to a preset cooking state, controlling the robot to perform mixed cooking on the food materials contained in the dish.
Optionally, the robot has a simulated visual nervous system, a simulated olfactory nervous system, and/or a simulated gustatory nervous system; based on the cooking state detection model corresponding to each food material, each food material of the dish is cooked independently, and the method comprises the following steps: respectively collecting color information, smell information and/or taste information of each food material through the simulated visual nervous system, the simulated olfactory nervous system and/or the simulated gustatory nervous system; respectively performing model matching detection on the collected color information, smell information and/or taste information of each food material based on the obtained cooking state detection model corresponding to each food material; and adjusting the cooking process of each food material according to the matching result of the model matching so as to enable each food material to reach a preset cooking state.
Optionally, adjusting the cooking process of each food material according to the matching result of the model matching includes: and when the matching result of the model matching of any food material is that the color information, the smell information and/or the taste information of the food material are matched with the preset cooking model corresponding to the food material, finishing the cooking of the food material.
Optionally, the controlling the robot to cook each food material of the dish individually based on the cooking state detection model corresponding to each food material further includes: acquiring edible oil information used for cooking the dish to acquire a preset edible oil heating time length of each food material of the dish when the food material is cooked by using the edible oil; and when each food material is cooked independently, the used edible oil is heated for the preset edible oil heating time, and then the cooking robot is controlled to add the corresponding food material for cooking.
Optionally, the cooking state data includes: at least one of a burn-out temperature, a smoke generation temperature, decomposition products, and a hydrocarbon ratio for each time period.
Another aspect of the present invention provides a cooking control apparatus of a cooking robot, including: the model acquisition unit is used for acquiring a cooking state detection model corresponding to each food material in the food materials contained in the dish to be cooked; the cooking state detection model corresponding to each food material is obtained by respectively carrying out model training on the basis of pre-collected cooking state data of each food material in the cooking process; the independent control unit is used for controlling the cooking robot to cook each food material of the dish independently based on the cooking state detection model corresponding to each food material when the dish is cooked; and the mixing control unit is used for controlling the cooking robot to perform mixing cooking on the food materials contained in the dish after each food material in the food materials contained in the dish is cooked to a preset cooking state.
Optionally, the cooking robot has a simulated visual nervous system, a simulated olfactory nervous system, and/or a simulated gustatory nervous system; the individual control unit includes: the acquisition subunit is used for respectively acquiring the color information, the smell information and/or the taste information of each food material through the simulated visual nervous system, the simulated olfactory nervous system and/or the simulated gustatory nervous system; the detection subunit is used for respectively performing model matching detection on the collected color information, smell information and/or taste information of each food material based on the obtained cooking state detection model corresponding to each food material; and the adjusting subunit is used for adjusting the cooking process of each food material according to the matching result of the model matching so as to enable each food material to reach a preset cooking state.
Optionally, the adjusting unit adjusts the cooking process of each food material according to the matching result of the model matching, including: and when the matching result of the model matching of any food material is that the color information, the smell information and/or the taste information of the food material are matched with the preset cooking model corresponding to the food material, finishing the cooking of the food material.
Optionally, the separate control unit further includes: an obtaining subunit, configured to obtain edible oil information used for cooking the dish, so as to obtain a preset edible oil heating time length of each food material of the dish when the food material is cooked by using the edible oil; and the control subunit is used for heating the used edible oil for the preset edible oil heating time length when each food material is independently cooked, and controlling the cooking robot to add the corresponding food material for cooking.
Optionally, the cooking state data includes: at least one of a burn-out temperature, a smoke generation temperature, decomposition products, and a hydrocarbon ratio for each time period.
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.
Yet another aspect of the invention provides a cooking robot 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 any of the methods described above.
In another aspect, the invention provides a cooking robot, comprising any one of the cooking control devices.
Yet another aspect of the present invention provides a server comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of any of the methods described above when executing the program.
In still another aspect, the present invention provides a server including the cooking control apparatus of the cooking robot as described in any one of the above.
According to the technical scheme, the cooking robot can be controlled to cook each food material of dishes to an optimal state independently, then the dishes are mixed and heated, one dish required by a user is formed by combining various food material units, only the food material units are required to be cooked to the optimal state, and finally the dishes are mixed to the optimal state in a certain mixing mode; and the invention can detect whether each food material reaches the best cooking state or not by utilizing a simulated vision, smell and/or taste nervous system based on the pre-established cooking state detection model corresponding to each food material, thereby controlling each food material to reach the latest cooking state.
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 cooking control method of a cooking robot provided by the invention;
fig. 2 is a functional distribution diagram of cooking control of the cooking robot according to an embodiment of the present invention;
fig. 3 is a schematic workflow diagram of a cooking robot according to an embodiment of the present invention;
fig. 4 is a schematic flowchart of a step of individually cooking each food material of the dish based on a preset cooking model corresponding to each food material according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an embodiment of a cooking control device of a cooking robot provided by the invention;
FIG. 6 is a schematic diagram of an implementation of a stand-alone control unit, according to an embodiment of 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.
The invention provides a cooking control method of a cooking robot. The invention may be implemented on the server side or on the cooking robot side (e.g. in a robot controller).
Fig. 2 is a functional distribution diagram of cooking control of the cooking robot according to an embodiment of the present invention. As shown in fig. 2, a01 is a data source, a02 is a cloud computing platform (cloud platform for short) maintained by a server, a03 is a robot controller, a10 is a simulated visual nervous system, a11 is a simulated olfactory nervous system, a12 is a simulated gustatory nervous system, a09 is a cooking robot entity, and B01 is an instruction execution unit.
The method comprises the steps of summarizing data of chemical components (such as hydrocarbon content, biomacromolecule content, metal mineral content, water content, smoke ratio during heating, smoke component content and the like), characteristics (such as decomposition product content and reaction rate under aerobic and high temperature, decomposition product content and reaction rate under oxygen-less and high temperature, smoke ratio during heating), physical components (such as impurities and external water), characteristics (such as dryness, humidity, temperature and hardness) and the like of food materials on the market into a database, and extracting effective data through data cleaning. This data is named data source a 01.
The server maintains and operates a whole set of cloud computing platform A02 for performing service management on the data source A01, and the server has the following functions: data matching, data reasonability detection, new data recording, data graph display, relationship maintenance of data and model parameters and the like.
Fig. 1 is a method schematic diagram of an embodiment of a cooking control method of a cooking robot according to the present invention.
As shown in fig. 1, according to an embodiment of the present invention, the robot cooking control method includes at least step S110, step S120, and step S130.
Step S110, obtaining a preset cooking model corresponding to each food material in the food materials contained in the dish to be cooked.
The preset cooking state detection model corresponding to each food material is obtained by respectively carrying out model training on the basis of pre-collected cooking state data of each food material in the cooking process. The cooking state data includes, for example, at least one of a temperature for dry out, a temperature for smoke generation, decomposition products, and a hydrocarbon ratio for each period of time.
The model training process of the cooking state detection model is described below with reference to an example. For example, a palace chicken bouillon, includes food materials: chicken breast, peanut kernel, red pepper, fistular onion stalk and ginger. And correspondingly establishing 5 model training tasks, taking model training of 'detecting chicken breast meat heating to the optimal state' as an example. Acquiring a data set of all relevant valid data of the chicken breast from an A01 data source (each data is a group of data like a burning temperature, a smoking temperature, decomposition products, a hydrocarbon ratio of each time period and the like, and such data forms a data set trained by model parameters of 'detection of heating of the chicken breast to the best state'), acquiring the model parameters of 'detection of heating of the chicken breast to the best state' through relevant algorithm processing, establishing a cooking state detection model of the detected chicken breast, and handing the parameters to A02 for processing. And randomly acquiring ten thousand data from A01, testing the cooking state detection model, and continuing to train model parameters when the cooking state detection model does not pass. After passing, the cooking state detection model is handed to cloud computing platform a02 for processing. The a02 is responsible for accessing the cooking state detection model to the a03 controller. Reference may be made in particular to the steps performed by the cloud computing platform in fig. 3.
Step S120, when the dish is cooked, each food material of the dish is cooked independently based on the preset cooking model corresponding to each food material.
Each food material is heated individually to an optimum state and then mixed and heated. The food material is equivalent to one element (water is no exception), each element can be mixed with proper materials to form the food material unit, and a dish required by a user is formed by combining various food material units, and only the food material unit is optimally cooked and finally mixed.
The robot has a simulated visual nervous system (e.g., an electronic eye based on a simulated nervous system), a simulated olfactory nervous system (e.g., an electronic nose based on a simulated nervous system), and/or a simulated taste nervous system (e.g., an electronic tongue based on a simulated nervous system).
Fig. 4 is a schematic flowchart of a step of individually cooking each food material of the dish based on the preset cooking model corresponding to each food material according to the embodiment of the present invention. As shown in fig. 4, in a specific embodiment, step S120 includes step S121, step S122, and step S123.
Step S121, respectively collecting color information, smell information and/or taste information of each food material through the simulated visual nervous system, the simulated olfactory nervous system and/or the simulated gustatory nervous system.
Specifically, color information of each food material of the dish is collected in real time through a simulated visual nervous system, smell information of each food material of the dish is collected in real time through the simulated olfactory nervous system, and/or taste information of each food material of the dish is collected in real time through the simulated gustatory nervous system.
And S122, respectively performing model matching detection on the collected color information, smell information and/or taste information of each food material based on the obtained cooking state detection model corresponding to each food material.
Namely, the collected color information, smell information and/or taste information of each food material are input into the corresponding cooking state detection model for matching, so that a matching result is obtained.
Step S123, adjusting the cooking process of each food material according to the matching result of the model matching so as to enable each food material to reach a preset cooking state.
In particular, the temperature and/or pressure of the cooking tool (e.g. a pot) in which the food material is located may be adjusted. And when the matching result of the model matching of any food material is that the color information, the smell information and/or the taste information of the food material are matched with the preset cooking model corresponding to the food material, finishing the cooking of the food material.
The following description is made of an example of "chicken breast" of the aforementioned "Tungbao chicken dices". Meanwhile, fig. 3 may also be combined, wherein fig. 3 is a schematic workflow diagram of a cooking robot according to an embodiment of the present invention. The robot has three simulation nervous systems of vision, smell and taste, and by transmitting nerve detection signals such as color, smell and taste to the controller A03 in real time, the nerve detection signals are complex digital signals, and for convenience of explaining the process, the description is as follows: color, smell, and taste. The controller A03 transmits the neural detection signal to the cloud platform A02 in a communication mode of the Internet of things. The cloud platform a02 prepares a corresponding cooking state detection model, analyzes the neural detection signal into a value required by the model, performs model matching detection to obtain a detection result, and the cloud platform a02 continues to perform matching detection on the detection result (the matching standard is from the data source a01 summarized in the experiment, and the optimal state is the best color, the best taste and the best smell) to see whether the optimal state is met. If the color, the taste and the taste are all in accordance with the requirements, the cloud platform A02 sends a control command to the controller A03, and the controller A03 controls the command execution unit B01 of the robot to stop cooking of the chicken breast. Otherwise, corresponding regulating commands (e.g., corresponding temperature and pressure control commands) are sent to the controller a03, and the controller a03 controls the command execution unit B01 to make adjustments until the optimal state is met.
Similarly, the other food materials of the 'Tungbao chicken dices' complete corresponding model matching detection according to the steps similar to the steps, and whether the food materials meet the optimal state or not is judged. Wherein, the red pepper, the ginger, the soy sauce, the vinegar, the oil, the salt and other proper materials can be added in the heating process of each food material without limitation.
Further, obtaining edible oil information used for cooking the dish to obtain a preset edible oil heating time length of each food material of the dish when the food material is cooked by using the edible oil; and when each food material is cooked independently, heating the used edible oil for the preset edible oil heating time, and then adding the corresponding food material for cooking. Wherein the preset cooking oil heating time period for each food material when cooked using the cooking oil is the heating time period required for each food material to heat to a corresponding preset cooking temperature (e.g., an optimal cooking temperature) when cooked using the cooking oil; the preset heating time of the edible oil when each food material is cooked by using the edible oil is obtained by detecting chemical components in the heating process of the edible oil (for example, detecting temperature change data and oil smoke components of the edible oil) and/or performing a cooking experiment on each food material by using the edible oil separately.
Specifically, the optimal time for mixing the edible oil (the time length for the edible oil to reach the optimal temperature from heating, a temperature-time coordinate graph can be drawn through experiments, and the time length for the edible oil to reach the optimal temperature from heating can be obtained only by finding the time corresponding to the temperature under the condition that the optimal temperature is determined) is obtained by detecting the temperature change data and the oil smoke components of the edible oil; by performing an individual experiment on each food material based on the mixable optimal time, physical and chemical characteristics of gas in the heating process are obtained, and a regression equation is simulated by combining a preset algorithm, so that the preset heating time of the edible oil before the food material is put into a cooking tool (for example, a pot) is given, and reference can be specifically made to the steps in the experimental area in fig. 3. For example, the optimal cooking temperature set TempList1 of the common food materials is calculated by analyzing the components of each edible oil on the market and extracting the data of heating speed, boiling point, smoking temperature, temperature for drying and intermediate smoking temperature. The cooking robot accesses the data source A01 by monitoring the stages of oil boiling, oil smoke emission, dry burning after smoke emission and the like and recording data such as temperature, time and the like. The cloud platform a02 fits an optimal time convergence point according to the optimal cooking temperature of the food material and the speed curve (temperature-time) of the edible oil heated by the robot (the speed curve of the edible oil heated by the robot can be used for drawing a temperature-time curve graph through experiments, and when the optimal cooking temperature of the food material is determined, the time for heating the edible oil to the optimal cooking temperature corresponding to the food material can be obtained only by finding the time corresponding to the temperature on the curve), and obtains the optimal (which is a regression number of a group of numbers and is regression data of a large amount of optimal data) edible oil heating time (i.e. the preset edible oil heating time) BestTemp suitable for different edible oils and different food materials through a large amount of experimental discrete data, and accesses the data source a 01. The controller a03 obtains corresponding data from the cloud platform a02 through network communication, and makes corresponding control to the robot, for example, heating edible oil to an optimal temperature, and then adding food materials.
Optionally, the image library can also be established by training images through machine vision. The method comprises the steps of acquiring edible, inedible and optimal edible three-stage images of each food material corresponding to each edible oil as much as possible through experiments, establishing an image library through a large number of experiments or simulation experiments, carrying out image recognition through big data processing, artificial intelligence image processing and the like, training a set of algorithm for recognizing optimal edible images, calling the algorithm to recognize image data collected in real time during cooking, judging whether the optimal edible time is reached or not, and controlling the cooking robot to stop cooking in set time when the optimal edible time is reached.
Optionally, chemical analysis of gas molecules within the cooking environment may be performed in addition to image processing to achieve final confirmation of the optimal edibility status of the cooked dish. Through a large number of experiments, the gas chemical components of each food material corresponding to each edible oil and the prepared condiments in equal proportion during the cooking period are detected, and the optimal gas chemical component proportion is obtained through processing by a preset algorithm. When the cooking robot detects that the proportion of various gas chemical components in the air reaches a preset critical value, an algorithm of the optimal edible image is triggered, the image acquisition is started, and the gas detection is started after the images are matched. That is, the actually detected gas chemical composition data is compared with the preset optimal gas chemical composition. This process may be performed by a server. And the server returns a cooking completion instruction to the controller in combination with the image recognition result.
Step S130, after each of the food materials contained in the dish is cooked to a preset state, mixing and cooking the food materials contained in the dish.
Because the essence of each dish is the mixing of food material units, the dish is formed by mixing food material units without dividing into soup, Sichuan dish and Guangdong dish, and after each food material in the food materials contained in the dish is cooked to a preset cooking state (optimal state), the food materials contained in the dish are mixed and cooked.
The invention can particularly adopt a cloud computing platform to carry out centralized service on the data layer and the machine control layer, and each cooking state model is established and is accessed to the cloud platform. When the controller receives signals transmitted by the robot nervous system, the signals are processed by the cloud platform and correspondingly controlled, so that the operation behavior of the robot is controlled. The implementation of each part of the invention can refer to fig. 3.
Fig. 5 is a schematic structural diagram of an embodiment of a cooking control device of a cooking robot according to the present invention. As shown in fig. 5, the cooking control apparatus 100 of the cooking robot includes: a model acquisition unit 110, an individual control unit 120, and a hybrid control unit 130.
The model obtaining unit 110 is configured to obtain a cooking state detection model corresponding to each of food materials included in a dish to be cooked. The cooking state detection model corresponding to each food material is obtained by respectively carrying out model training on the basis of pre-collected cooking state data of each food material in the cooking process. The cooking state data includes, for example, at least one of a temperature for dry out, a temperature for smoke generation, decomposition products, and a hydrocarbon ratio for each period of time.
The model training process of the cooking state detection model is described below with reference to an example. Meanwhile, fig. 3 may also be combined, wherein fig. 3 is a schematic workflow diagram of a cooking robot according to an embodiment of the present invention. For example, a palace chicken bouillon, includes food materials: chicken breast, peanut kernel, red pepper, fistular onion stalk and ginger. And correspondingly establishing 5 model training tasks, taking model training of 'detecting chicken breast meat heating to the optimal state' as an example. Acquiring a data set of all relevant valid data of the chicken breast from an A01 data source (each data is a group of data like a burning temperature, a smoking temperature, decomposition products, a hydrocarbon ratio of each time period and the like, and such data forms a data set trained by model parameters of 'detecting the heating of the chicken breast to the best state'), acquiring the model parameters of 'detecting the heating of the chicken breast to the best state' through relevant algorithm processing, establishing a cooking state detection model C01 of the detected chicken breast, and handing the parameters to A02 for processing. And randomly acquiring ten thousand data from A01, testing the cooking state detection model, and continuing to train model parameters when the cooking state detection model does not pass. After passing, the cooking state detection model is handed to cloud computing platform a02 for processing. The a02 is responsible for accessing the cooking state detection model to the a03 controller. Reference may be made in particular to the steps performed by the cloud computing platform in fig. 3.
The individual control unit 120 is configured to control the cooking robot to individually cook each food material of the dish based on the cooking state detection model corresponding to each food material when the dish is cooked.
Each food material is heated individually to an optimum state and then mixed and heated. The food material is equivalent to one element (water is no exception), each element can be mixed with proper materials to form the food material unit, and a dish required by a user is formed by combining various food material units, and only the food material unit is optimally cooked and finally mixed.
In one embodiment, the robot has a simulated visual nervous system (e.g., an electronic eye based on a simulated nervous system), a simulated olfactory nervous system (e.g., an electronic nose based on a simulated nervous system), and/or a simulated gustatory nervous system (e.g., an electronic tongue based on a simulated nervous system).
FIG. 6 is a schematic diagram of an implementation of a stand-alone control unit, according to an embodiment of the invention. As shown in fig. 6, in one embodiment, the individual control unit 120 includes an acquisition subunit 121, a detection subunit 122, and an adjustment subunit 123.
The collecting subunit 121 is configured to collect color information, odor information and/or taste information of each food material through the simulated visual nervous system, the simulated olfactory nervous system and/or the simulated gustatory nervous system, respectively; namely, color information of each food material of the dish is collected in real time through a simulated visual nervous system, odor information of each food material of the dish is collected in real time through the simulated olfactory nervous system, and/or taste information of each food material of the dish is collected in real time through the simulated gustatory nervous system.
The detection subunit 122 is configured to perform model matching detection on the collected color information, smell information, and/or taste information of each food material, respectively, based on the obtained cooking state detection model corresponding to each food material; namely, the collected color information, smell information and/or taste information of each food material are input into the corresponding cooking state detection model for matching, so that a matching result is obtained.
The adjusting subunit 123 is configured to adjust a cooking process of each food material according to a matching result of the model matching, so that each food material reaches a preset cooking state.
In particular, the temperature and/or pressure of the cooking tool (e.g. a pot) in which the food material is located may be adjusted. And when the matching result of the model matching of any food material is that the color information, the smell information and/or the taste information of the food material are matched with the preset cooking model corresponding to the food material, finishing the cooking of the food material.
The following description is made of an example of "chicken breast" of the aforementioned "Tungbao chicken dices". Meanwhile, fig. 3 may also be combined, wherein fig. 3 is a schematic workflow diagram of a cooking robot according to an embodiment of the present invention. The robot has three simulation nervous systems of vision, smell and taste, and by transmitting nerve detection signals such as color, smell and taste to the controller A03 in real time, the nerve detection signals are complex digital signals, and for convenience of explaining the process, the description is as follows: color, smell, and taste. The controller A03 transmits the neural detection signal to the cloud platform A02 in a communication mode of the Internet of things. The cloud platform a02 prepares a corresponding cooking state detection model, analyzes the neural detection signal into a value required by the model, performs model matching detection to obtain a detection result, and the cloud platform a02 continues to perform matching detection on the detection result (the matching standard is from the data source a01 summarized in the experiment, and the optimal state is the best color, the best taste and the best smell) to see whether the optimal state is met. If the color, the taste and the taste are all in accordance with the requirements, the cloud platform A02 sends a control command to the controller A03, and the controller A03 controls the command execution unit B01 of the robot to stop cooking of the chicken breast. Otherwise, corresponding regulating commands (e.g., corresponding temperature and pressure control commands) are sent to the controller a03, and the controller a03 controls the command execution unit B01 to make adjustments until the optimal state is met.
Similarly, the other food materials of the 'Tungbao chicken dices' complete corresponding model matching detection according to the steps similar to the steps, and whether the food materials meet the optimal state or not is judged. Wherein, the red pepper, the ginger, the soy sauce, the vinegar, the oil, the salt and other proper materials can be added in the heating process of each food material without limitation.
Further, the individual control unit 120 further includes an acquisition subunit and a control subunit (not shown).
An obtaining subunit, configured to obtain edible oil information used for cooking the dish, so as to obtain a preset edible oil heating time length of each food material of the dish when the food material is cooked by using the edible oil; and the control subunit is used for heating the used edible oil for the preset edible oil heating time length when each food material is independently cooked, and controlling the cooking robot to add the corresponding food material for cooking.
Wherein the preset cooking oil heating time period for each food material when cooked using the cooking oil is the heating time period required for each food material to heat to a corresponding preset cooking temperature (e.g., an optimal cooking temperature) when cooked using the cooking oil; the preset heating time of the edible oil when each food material is cooked by using the edible oil is obtained by detecting chemical components in the heating process of the edible oil (for example, detecting temperature change data and oil smoke components of the edible oil) and/or performing a cooking experiment on each food material by using the edible oil separately.
Specifically, the optimal time for mixing the edible oil (the time length for the edible oil to reach the optimal temperature from heating, a temperature-time coordinate graph can be drawn through experiments, and the time length for the edible oil to reach the optimal temperature from heating can be obtained only by finding the time corresponding to the temperature under the condition that the optimal temperature is determined) is obtained by detecting the temperature change data and the oil smoke components of the edible oil; by performing an individual experiment on each food material based on the mixable optimal time, physical and chemical characteristics of gas in the heating process are obtained, and a regression equation is simulated by combining a preset algorithm, so that the preset heating time of the edible oil before the food material is put into a cooking tool (for example, a pot) is given, and reference can be specifically made to the steps in the experimental area in fig. 3. For example, the optimal cooking temperature set TempList1 of the common food materials is calculated by analyzing the components of each edible oil on the market and extracting the data of heating speed, boiling point, smoking temperature, temperature for drying and intermediate smoking temperature. The cooking robot accesses the data source A01 by monitoring the stages of oil boiling, oil smoke emission, dry burning after smoke emission and the like and recording data such as temperature, time and the like. The cloud platform a02 fits an optimal time convergence point according to the optimal cooking temperature of the food material and the speed curve (temperature-time) of the edible oil heated by the robot (the speed curve of the edible oil heated by the robot can be used for drawing a temperature-time curve graph through experiments, and when the optimal cooking temperature of the food material is determined, the time for heating the edible oil to the optimal cooking temperature corresponding to the food material can be obtained only by finding the time corresponding to the temperature on the curve), and obtains the optimal (which is a regression number of a group of numbers and is regression data of a large amount of optimal data) edible oil heating time (i.e. the preset edible oil heating time) BestTemp suitable for different edible oils and different food materials through a large amount of experimental discrete data, and accesses the data source a 01. The controller a03 obtains corresponding data from the cloud platform a02 through network communication, and makes corresponding control to the robot, for example, heating edible oil to an optimal temperature, and then adding food materials.
Optionally, the image library can also be established by training images through machine vision. The method comprises the steps of acquiring edible, inedible and optimal edible three-stage images of each food material corresponding to each edible oil as much as possible through experiments, establishing an image library through a large number of experiments or simulation experiments, carrying out image recognition through big data processing, artificial intelligence image processing and the like, training a set of algorithm for recognizing optimal edible images, calling the algorithm to recognize image data collected in real time during cooking, judging whether the optimal edible time is reached or not, and controlling the cooking robot to stop cooking in set time when the optimal edible time is reached.
Optionally, chemical analysis of gas molecules within the cooking environment may be performed in addition to image processing to achieve final confirmation of the optimal edibility status of the cooked dish. Through a large number of experiments, the gas chemical components of each food material corresponding to each edible oil and the prepared condiments in equal proportion during the cooking period are detected, and the optimal gas chemical component proportion is obtained through processing by a preset algorithm. When the cooking robot detects that the proportion of various gas chemical components in the air reaches a preset critical value, an algorithm of the optimal edible image is triggered, the image acquisition is started, and the gas detection is started after the images are matched. That is, the actually detected gas chemical composition data is compared with the preset optimal gas chemical composition. This process may be performed by a server. And the server returns a cooking completion instruction to the controller in combination with the image recognition result.
The mixing control unit 130 is configured to control the cooking robot to perform mixing cooking on the food materials contained in the dish after each food material in the food materials contained in the dish is cooked to a preset cooking state.
Specifically, each dish is essentially a mixture of food material units, and is not divided into soup, Sichuan dish and Guangdong dish, and is formed by mixing food material units, and after each food material in the food materials contained in the dish is cooked to a preset cooking state (optimal state), the food materials contained in the dish are mixed and cooked.
The invention also provides a storage medium corresponding to the cooking control method of the cooking robot, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the computer program realizes the steps of any one of the methods.
The invention also provides a cooking robot corresponding to the cooking control method of the cooking robot, which comprises a processor, a memory and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the methods when executing the program.
The invention also provides a cooking robot corresponding to the cooking control device of the cooking robot, which comprises the cooking control device of any one of the cooking robots.
The invention also provides a server corresponding to the cooking control method of the cooking robot, which comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of any one of the methods.
The invention also provides a server corresponding to the cooking control device of the cooking robot, which comprises the cooking control device of any one of the cooking robots.
According to the scheme provided by the invention, the cooking robot can be controlled to cook each food material of the dish to the optimal state independently, then the dish is mixed and heated, one dish required by a user is formed by combining various food material units, only each food material unit needs to be cooked to the optimal state, and finally the dish is mixed to the optimal state in a certain mixing mode; and the invention can detect whether each food material reaches the best cooking state or not by utilizing a simulated vision, smell and/or taste nervous system based on the pre-established cooking state detection model corresponding to each food material, thereby controlling each food material to reach the latest cooking state.
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 (13)
1. A cooking control method of a cooking robot, comprising:
acquiring a cooking state detection model corresponding to each food material in the food materials contained in a dish to be cooked; the cooking state detection model corresponding to each food material is obtained by respectively carrying out model training on the basis of pre-collected cooking state data of each food material in the cooking process;
when the dish is cooked, controlling the robot to cook each food material of the dish independently based on the cooking state detection model corresponding to each food material;
after each food material in the food materials contained in the dish is cooked to a preset cooking state, controlling the robot to perform mixed cooking on the food materials contained in the dish;
the cooking state data includes: at least one of a burn-out temperature, a smoke generation temperature, decomposition products, and a hydrocarbon ratio for each time period.
2. The method of claim 1, wherein the robot has a simulated visual nervous system, a simulated olfactory nervous system, and/or a simulated gustatory nervous system;
based on the cooking state detection model corresponding to each food material, each food material of the dish is cooked independently, and the method comprises the following steps:
respectively collecting color information, smell information and/or taste information of each food material through the simulated visual nervous system, the simulated olfactory nervous system and/or the simulated gustatory nervous system;
respectively performing model matching detection on the collected color information, smell information and/or taste information of each food material based on the obtained cooking state detection model corresponding to each food material;
and adjusting the cooking process of each food material according to the matching result of the model matching so as to enable each food material to reach a preset cooking state.
3. The method of claim 2, wherein adjusting the cooking process of each food material according to the matching result of the model matching comprises:
and when the matching result of the model matching of any food material is that the color information, the smell information and/or the taste information of the food material are matched with the preset cooking model corresponding to the food material, finishing the cooking of the food material.
4. The method of claim 1, wherein controlling the robot to cook each food material of the dish individually based on the cooking state detection model corresponding to each food material further comprises:
acquiring edible oil information used for cooking the dish to acquire a preset edible oil heating time length of each food material of the dish when the food material is cooked by using the edible oil;
and when each food material is cooked independently, the used edible oil is heated for the preset edible oil heating time, and then the cooking robot is controlled to add the corresponding food material for cooking.
5. A cooking control device of a cooking robot, comprising:
the model acquisition unit is used for acquiring a cooking state detection model corresponding to each food material in the food materials contained in the dish to be cooked; the cooking state detection model corresponding to each food material is obtained by respectively carrying out model training on the basis of pre-collected cooking state data of each food material in the cooking process;
the independent control unit is used for controlling the cooking robot to cook each food material of the dish independently based on the cooking state detection model corresponding to each food material when the dish is cooked; and the number of the first and second groups,
the mixing control unit is used for controlling the cooking robot to perform mixing cooking on the food materials contained in the dish after each food material in the food materials contained in the dish is cooked to a preset cooking state;
the cooking state data includes: at least one of a burn-out temperature, a smoke generation temperature, decomposition products, and a hydrocarbon ratio for each time period.
6. The device of claim 5, wherein the cooking robot has a simulated visual nervous system, a simulated olfactory nervous system, and/or a simulated gustatory nervous system;
the individual control unit includes:
the acquisition subunit is used for respectively acquiring the color information, the smell information and/or the taste information of each food material through the simulated visual nervous system, the simulated olfactory nervous system and/or the simulated gustatory nervous system;
the detection subunit is used for respectively performing model matching detection on the collected color information, smell information and/or taste information of each food material based on the obtained cooking state detection model corresponding to each food material;
and the adjusting subunit is used for adjusting the cooking process of each food material according to the matching result of the model matching so as to enable each food material to reach a preset cooking state.
7. The apparatus of claim 6, wherein the adjusting subunit adjusts the cooking process of each food material according to the matching result of the model matching, and comprises:
and when the matching result of the model matching of any food material is that the color information, the smell information and/or the taste information of the food material are matched with the preset cooking model corresponding to the food material, finishing the cooking of the food material.
8. The apparatus of claim 5, wherein the separate control unit further comprises:
an obtaining subunit, configured to obtain edible oil information used for cooking the dish, so as to obtain a preset edible oil heating time length of each food material of the dish when the food material is cooked by using the edible oil;
and the control subunit is used for heating the used edible oil for the preset edible oil heating time length when each food material is independently cooked, and controlling the cooking robot to add the corresponding food material for cooking.
9. 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 4.
10. A cooking robot comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method according to any one of claims 1-4 when executing the program.
11. A cooking robot comprising the cooking control device according to any one of claims 5 to 8.
12. A server comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1 to 4 when executing the program.
13. A server, characterized in comprising the cooking control means of the cooking robot according to any one of claims 5-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811535239.3A CN109732615B (en) | 2018-12-14 | 2018-12-14 | Cooking robot and cooking control method and device thereof, storage medium and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811535239.3A CN109732615B (en) | 2018-12-14 | 2018-12-14 | Cooking robot and cooking control method and device thereof, storage medium and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109732615A CN109732615A (en) | 2019-05-10 |
| CN109732615B true CN109732615B (en) | 2020-09-29 |
Family
ID=66359475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811535239.3A Active CN109732615B (en) | 2018-12-14 | 2018-12-14 | Cooking robot and cooking control method and device thereof, storage medium and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109732615B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110132890A (en) * | 2019-05-20 | 2019-08-16 | 梁志鹏 | According to the method and device of the unmanned culinary cuisine operation of food materials optimizing components |
| CN111493671A (en) * | 2019-12-27 | 2020-08-07 | 李娟娟 | Instant seasoning platform and method for hot pot with hot pepper bottom |
| CN112180870A (en) * | 2020-10-10 | 2021-01-05 | 珠海格力智能装备有限公司 | Grouting control method and device for egg roll machine |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10113132A (en) * | 1996-10-11 | 1998-05-06 | Ryota Katahira | Manufacturing method and cooking method for instant scalloped food and soup |
| CN1489927B (en) * | 2003-09-19 | 2010-08-11 | 张一平 | Automatic Chinese dish cooking method and automatic intelligent cooking utensils |
| CN101901015B (en) * | 2009-05-27 | 2014-02-26 | 深圳市爱可机器人技术有限公司 | Heat control system for cooking device based on machine vision |
| CN104248331A (en) * | 2014-09-16 | 2014-12-31 | 广东美的厨房电器制造有限公司 | Cooking utensil and method and device for controlling cooking utensil |
| CN108309021B (en) * | 2018-01-20 | 2023-06-09 | 江苏大学 | Intelligent regulation automatic cooker and intelligent control method thereof |
| CN108261048B (en) * | 2018-03-09 | 2020-10-02 | 九阳股份有限公司 | Cooking process of cooking machine |
| CN108552936A (en) * | 2018-05-11 | 2018-09-21 | 九阳股份有限公司 | The cooking methods of cooking machine and cooking machine |
-
2018
- 2018-12-14 CN CN201811535239.3A patent/CN109732615B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109732615A (en) | 2019-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109732615B (en) | Cooking robot and cooking control method and device thereof, storage medium and server | |
| WO2020207293A1 (en) | Method and device for automatically cooking food | |
| CN108322493B (en) | Food material identification and cooking pushing method and system, server and cooking appliance | |
| CN108538363A (en) | A kind of method and cooking appliance of determining culinary art pattern | |
| CN108133743A (en) | A kind of methods, devices and systems of information push | |
| CN107886170B (en) | Control method, device and system of cooking appliance, storage medium and processor | |
| CN106485052A (en) | A kind of intelligent cooking system and method | |
| CN104679568B (en) | Cooking apparatus and its updating menu method, system and server | |
| CN109683529A (en) | A kind of cooking control method, device and cooking equipment | |
| WO2020179401A1 (en) | Cooking robot, cooking robot control device, and control method | |
| CN109683516A (en) | Auxiliary cooking method, household appliance and computer storage medium | |
| CN106773859A (en) | A kind of intelligent cooking control method | |
| WO2016206889A1 (en) | Control unit and method for determining a recipe | |
| CN110132890A (en) | According to the method and device of the unmanned culinary cuisine operation of food materials optimizing components | |
| CN110934508A (en) | Oven control method and device | |
| CN108013733A (en) | Cooking control method, device and system | |
| CN110989389A (en) | Menu adjusting method and device | |
| CN109062277A (en) | The heating means and device of food, storage medium, processor | |
| CN108134809A (en) | A kind of methods, devices and systems of information push | |
| CN110916470B (en) | Recipe management method based on household appliance and household appliance | |
| CN113598625B (en) | Cooking control method and device based on intelligent cooking slice | |
| WO2020179407A1 (en) | Data processing device and data processing method | |
| CN111419096B (en) | Food processing method, controller and food processing equipment | |
| CN111603050A (en) | Method and device for controlling cooker, storage medium and cooker | |
| CN114092806A (en) | Recognition method and device thereof, cooking equipment and control method thereof 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |