Model training method, cooking control method, system, equipment and medium

Abstract

The present invention discloses a model training method, a cooking control method, a system, a device and a medium, the method comprising: obtaining several groups of sample cooking data associated with the cooking state of ingredients; the sample cooking data comprises sample ingredient influencing parameters and corresponding sample ingredient maturity level information, taking each group of sample ingredient influencing parameters as input, and the corresponding sample ingredient maturity level information as output, and training to obtain a target prediction model; the target prediction model is used to predict the cooking time corresponding to different ingredient maturity levels in any cooking environment. The present invention takes the obtained sample ingredient influencing parameters as input, and the corresponding sample ingredient maturity level information as output, and trains to obtain a target prediction model; the accuracy of the target prediction model is improved, and it is ensured that when cooking ingredients in different pots, the cooking time required for different ingredients can be accurately controlled to ensure the cooking taste of the food, which greatly improves the user's cooking experience.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a model training method, a cooking control method, a system, a device and a medium. Background Art

[0002] In daily life, users often use pots to steam and cook food (for example, steamed buns, sweet potatoes, leftovers, etc.) or cook chicken soup, fish soup, etc. on gas stoves. If the cooking time is not well controlled, the steamed food will not be cooked or too mushy. Due to the different ingredients, the time required to cook to perfection is also different. In the process of steaming and cooking food, the corresponding cooking time is usually set for different ingredients according to recipes or experience, or the maturity of the ingredients is always paid attention to during the cooking process. Confirm whether the food is cooked by trial and error before ending the cooking. However, it is more troublesome to look up recipes and ask experienced chefs, and the cooking time required for different ingredients is also affected by the firepower and the amount of water. It is difficult to grasp the accurate cooking time. The trial method requires lifting the pot lid many times, which will cause the steam in the pot to overflow from the pot many times, resulting in increased energy consumption. Summary of the invention

[0003] The technical problem to be solved by the present invention is to overcome the defects of the prior art that the cooking time of ingredients is controlled by searching for recipes, asking questions, and picking up the pot lid to try, which is time-consuming, labor-intensive, and consumes electricity. A model training method, cooking control method, system, equipment, and medium are provided.

[0004] The present invention solves the above technical problems through the following technical solutions:

[0005] The present invention provides a method for training a food maturity level prediction model, the training method comprising:

[0006] Acquire several groups of sample cooking data associated with the cooking status of ingredients;

[0007] The sample cooking data includes sample food influencing parameters and corresponding sample food maturity level information, and different sample food maturity level information corresponds to different cooking times;

[0008] Taking each group of sample food influencing parameters as input and the corresponding sample food maturity level information as output, training to obtain a target prediction model;

[0009] The target prediction model is used to predict the cooking time corresponding to different food maturity levels in any cooking environment.

[0010] Preferably, the sample ingredient influencing parameter corresponds to ingredient associated data and / or cooking equipment associated data.

[0011] Preferably, the food-related data includes food category data and / or food weight data;

[0012] and / or,

[0013] The cooking equipment-related data includes at least one of volume data of the cooking equipment, initial water volume data, and real-time stable steam flow data.

[0014] Preferably, when the sample food influencing parameters include the volume data of the cooking equipment, the initial water volume data, the real-time stable steam flow data and the food weight data, the step of taking each group of the sample food influencing parameters as input and the corresponding sample food maturity level information as output to train and obtain the target prediction model includes:

[0015] A regression prediction model is adopted to take the influencing parameters of each group of sample ingredients as input and the corresponding maturity level information of the sample ingredients as output, and the target prediction model is obtained through training.

[0016] Preferably, when the sample food influencing parameter also includes the food category data, the training method includes:

[0017] The food category data is used to update the new target prediction model.

[0018] Preferably, the calculation formula corresponding to the target prediction model obtained by training with the volume data, the initial water volume data, the real-time stable steam flow data and the food weight data is:

[0019] G=f(V,L,Q,M)

[0020] The step of using the food category data to update the new target prediction model comprises:

[0021]

[0022] Wherein, G represents the target prediction model, V represents the volume data, L represents the initial water volume data, Q represents the real-time stable steam flow data, M represents the food weight data, and Ic represents the food category vector corresponding to the food category data. Represents the updated target prediction model.

[0023] The present invention also provides a training system for a food maturity level prediction model, the training system comprising a first acquisition module and a training module;

[0024] The first acquisition module is used to acquire several groups of sample cooking data associated with the cooking status of the food ingredients;

[0025] The sample cooking data includes sample food influencing parameters and corresponding sample food maturity level information, and different sample food maturity level information corresponds to different cooking times;

[0026] The training module is used to take each group of sample food influencing parameters as input and the corresponding sample food maturity level information as output, and train to obtain a target prediction model;

[0027] The target prediction model is used to predict the cooking time corresponding to different food maturity levels in any cooking environment.

[0028] Preferably, the sample ingredient influencing parameter corresponds to ingredient associated data and / or cooking equipment associated data.

[0029] Preferably, the food-related data includes food category data and / or food weight data;

[0030] and / or,

[0031] The cooking equipment-related data includes at least one of volume data of the cooking equipment, initial water volume data, and real-time stable steam flow data.

[0032] Preferably, when the sample ingredient influencing parameters include the volume data of the cooking equipment, the initial water volume data, the real-time stable steam flow data and the ingredient weight data, the training module is specifically used to adopt a regression prediction model to take each group of the sample ingredient influencing parameters as input and the corresponding sample ingredient maturity level information as output, and train to obtain a target prediction model.

[0033] Preferably, when the sample food influencing parameter further includes the food category data, the training system further includes an updating module;

[0034] The updating module is used to update the new target prediction model using the food category data.

[0035] Preferably, the calculation formula corresponding to the target prediction model obtained by training with the volume data, the initial water volume data, the real-time stable steam flow data and the food weight data is:

[0036] G=f(V,L,Q,M)

[0037] The updating module, which is used to update the new target prediction model using the food category data, includes:

[0038]

[0039] Wherein, G represents the target prediction model, V represents the volume data, L represents the initial water volume data, Q represents the real-time stable steam flow data, M represents the food weight data, and Ic represents the food category vector corresponding to the food category data. Represents the updated target prediction model.

[0040] The present invention also provides a cooking control method, which is implemented by using the above-mentioned training method of the food maturity level prediction model, and the control method comprises:

[0041] Obtain actual cooking data associated with the cooking status of ingredients in the current cooking environment;

[0042] Inputting the actual cooking data into the target prediction model to output the cooking time corresponding to different food maturity levels under the current cooking environment;

[0043] The input target ingredient maturity level is obtained to determine the corresponding target cooking time, so as to control the cooking device to cook for the target cooking time.

[0044] Preferably, the cooking device is provided with a gas flow detection device and a weighing device, and the step of obtaining actual cooking data associated with the cooking state of the food in the current cooking environment comprises:

[0045] Acquiring food weight data and initial water volume data of the cooking device through the weighing device;

[0046] Collecting real-time and stable steam flow data of the cooking device through the gas flow detection device;

[0047] The volume data of the cooking device is obtained through label information on the cooking device or a volume measuring device.

[0048] The present invention also provides a cooking control system, which is implemented by using the training system of the above-mentioned food maturity level prediction model, and is characterized in that the control system includes a second acquisition module, a third acquisition module and a fourth acquisition module;

[0049] The second acquisition module is used to acquire actual cooking data associated with the cooking state of the ingredients in the current cooking environment;

[0050] The third acquisition module is used to input the actual cooking data into the target prediction model to output the cooking time corresponding to different maturity levels of ingredients under the current cooking environment;

[0051] The fourth acquisition module is used to acquire the input target ingredient maturity level to determine the corresponding target cooking time, so as to control the cooking device to cook for the target cooking time.

[0052] Preferably, the cooking device is provided with a gas flow detection device and a weighing device, and the second acquisition module includes a first acquisition unit, a collection unit and a second acquisition unit;

[0053] The first acquisition unit is used to acquire the weight data of the food material and the initial water volume data of the cooking device through the weighing device;

[0054] The collecting unit is used to collect the real-time stable steam flow data of the cooking device through the gas flow detection device;

[0055] The second acquiring unit is used to acquire the volume data of the cooking device through label information on the cooking device or a volume measuring device.

[0056] The present invention also provides a smart home appliance, comprising the above-mentioned cooking control system.

[0057] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned training method of the food maturity level prediction model or the above-mentioned cooking control method when executing the computer program.

[0058] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the computer program implements the above-mentioned training method of the food maturity level prediction model, or implements the above-mentioned cooking control method.

[0059] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present invention.

[0060] The positive and progressive effects of the present invention are:

[0061] The present invention obtains several groups of sample cooking data associated with the cooking status of ingredients, and uses the sample ingredient influencing parameters in each group of sample cooking data as input, and the corresponding sample ingredient maturity level information as output, to train a target prediction model; it achieves prediction of the cooking time corresponding to different ingredient maturity levels in any cooking environment based on the target prediction model, improves the accuracy of the target prediction model, ensures that when ingredients are steamed in different pots, the cooking time required for different ingredients can be accurately controlled to ensure the cooked taste of the food, and greatly improves the cooking experience of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 The present invention is a flowchart of a method for training a food maturity level prediction model according to Embodiment 1 of the present invention.

[0063] Figure 2 This is a first flow chart of the training method of the food maturity level prediction model of Example 2 of the present invention.

[0064] Figure 3 This is a second flow chart of the method for training a food maturity level prediction model according to Embodiment 2 of the present invention.

[0065] Figure 4 This is a module diagram of a training system for a food maturity level prediction model according to Example 3 of the present invention.

[0066] Figure 5 This is a flow chart of the cooking control method according to embodiment 4 of the present invention.

[0067] Figure 6 This is a schematic diagram of a kitchen scene according to Embodiment 4 of the present invention.

[0068] Figure 7 This is a module diagram of a cooking control system according to Embodiment 5 of the present invention.

[0069] Figure 8 This is a schematic diagram of the structure of an electronic device according to Embodiment 6 of the present invention. DETAILED DESCRIPTION

[0070] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples.

[0071] Example 1

[0072] like Figure 1 As shown, the training method of the food maturity level prediction model of this embodiment includes:

[0073] S101, obtaining several groups of sample cooking data associated with the cooking status of ingredients;

[0074] In this embodiment, the sample cooking data includes the sample food influencing parameters and the corresponding sample food maturity level information, and different sample food maturity level information corresponds to different cooking times;

[0075] In this embodiment, the sample food influencing parameter corresponds to food-related data and / or cooking equipment-related data.

[0076] The cooking equipment-related data includes, but is not limited to, the volume data of the cooking equipment, the initial water volume data, and the real-time stable steam flow data.

[0077] S102, taking the influencing parameters of each group of sample ingredients as input and the corresponding sample ingredient maturity level information as output, and training to obtain a target prediction model;

[0078] In this embodiment, the target prediction model is used to predict the cooking time corresponding to different maturity levels of ingredients in any cooking environment.

[0079] This embodiment obtains several groups of sample cooking data associated with the cooking status of the ingredients, and uses the sample ingredient influencing parameters in each group of sample cooking data as input, and the corresponding sample ingredient maturity level information as output, to train a target prediction model; it achieves prediction of the cooking time corresponding to different ingredient maturity levels in any cooking environment based on the target prediction model, improves the accuracy of the target prediction model, ensures that when cooking ingredients in different pots, the cooking time required for different ingredients can be accurately controlled to ensure the cooking taste of the food, and greatly improves the user's cooking experience.

[0080] Example 2

[0081] The training method of the food maturity level prediction model of this embodiment is a further improvement of the embodiment 1, specifically:

[0082] When the sample food influencing parameters include the volume data of the cooking equipment, the initial water volume data, the real-time stable steam flow data, and the food weight data, such as Figure 2 As shown, step S102 includes:

[0083] S1021. Using a regression prediction model, taking the influencing parameters of each group of sample ingredients as input and the corresponding sample ingredient maturity level information as output, training to obtain a target prediction model.

[0084] In an practicable solution, when the sample food influencing parameter also includes food category data, such as Figure 3 As shown, the training method also includes:

[0085] S103: Update the food category data to obtain a new target prediction model.

[0086] In one feasible solution, the target prediction model is trained using volume data, initial water volume data, real-time stable steam flow data, and food weight data to obtain a calculation formula corresponding to the target prediction model:

[0087] G=f(V,L,Q,M)

[0088] In this embodiment, taking the cooking device as a pot as an example, the dependent variables of the food maturity level S are: volume data V, initial water volume data L, real-time stable steam flow data Q, food category data C, and food weight data M. The food maturity level S can be obtained by using different food category data C in different pots (with different V values), different initial water volume data L, real-time stable steam flow data Q under different fire states, and different food weight data M to obtain the cooking time T corresponding to the food maturity level S of different food category data C.C , and then the relationship mapping is performed based on the independent variable x = [V, L, Q, M] and the dependent variable food maturity level S. The specific mapping method can discretize the food maturity level S and can be used to map T at a fixed time interval △t. C Classify and obtain the corresponding food maturity level S' through the following formula C .

[0089] S′ C =i T C ∈[i*△t, (i+1)*△t], i∈0,1,2…

[0090] Finally, we can get the discrete maturity level S′ of all ingredients, that is, S′=[S′0,…,S′ C ]. Then, x and S′ are trained by regression (for example, XGBoost (tree ensemble model), LightGBM (a framework for implementing gradient descent tree algorithm), neural network, etc.) to obtain the corresponding regression prediction model G, that is, G = f(V, L, Q, M), and output the C-dimensional vector of food category data.

[0091] Step S103 includes:

[0092]

[0093] Wherein, G represents the target prediction model, V represents the volume data, L represents the initial water volume data, Q represents the real-time stable steam flow data, M represents the food weight data, and Ic represents the food category vector corresponding to the food category data (for example, Ic = [0, 0, ..., 1, ..., 0], with a total of C dimensions, the component under the corresponding food index is 1, and the rest are 0). Represents the updated target prediction model.

[0094] In this embodiment, the volume data V, the initial water volume data L, the real-time stable steam flow data Q, the food weight data M and the corresponding food category data C obtained in advance can be used according to the above formula The maturity level of ingredient C can be predicted.

[0095] This embodiment proposes a method for identifying the maturity level of ingredients based on a regression prediction model. Specifically, the regression prediction model is used to take the influencing parameters of each group of sample ingredients as input and the corresponding sample ingredient maturity level information as output, and a target prediction model is obtained by training. Furthermore, a new target prediction model is obtained by updating the ingredient category data, thereby further improving the accuracy of the target prediction model.

[0096] Example 3

[0097] like Figure 4As shown, the training system of the food maturity level prediction model of this embodiment includes a first acquisition module 1 and a training module 2;

[0098] A first acquisition module 1 is used to acquire several groups of sample cooking data associated with the cooking state of the food;

[0099] In this embodiment, the sample cooking data includes the sample food influencing parameters and the corresponding sample food maturity level information, and different sample food maturity level information corresponds to different cooking times;

[0100] In this embodiment, the sample food influencing parameter corresponds to food-related data and / or cooking equipment-related data.

[0101] The cooking equipment-related data includes, but is not limited to, the volume data of the cooking equipment, the initial water volume data, and the real-time stable steam flow data.

[0102] Training module 2, used to take the influencing parameters of each group of sample ingredients as input and the corresponding sample ingredient maturity level information as output, and train to obtain a target prediction model;

[0103] In this embodiment, the target prediction model is used to predict the cooking time corresponding to different maturity levels of ingredients in any cooking environment.

[0104] This embodiment obtains several groups of sample cooking data associated with the cooking status of the ingredients, and uses the sample ingredient influencing parameters in each group of sample cooking data as input, and the corresponding sample ingredient maturity level information as output, to train a target prediction model; it achieves prediction of the cooking time corresponding to different ingredient maturity levels in any cooking environment based on the target prediction model, improves the accuracy of the target prediction model, ensures that when cooking ingredients in different pots, the cooking time required for different ingredients can be accurately controlled to ensure the cooking taste of the food, and greatly improves the user's cooking experience.

[0105] In an implementable scheme, when the sample food influencing parameters include the volume data of the cooking equipment, the initial water volume data, the real-time stable steam flow data, and the food weight data, the training module 2 is specifically used to use a regression prediction model to take each group of sample food influencing parameters as input and the corresponding sample food maturity level information as output, and train to obtain the target prediction model.

[0106] In an practicable solution, when the sample food influencing parameter also includes food category data, such as Figure 4 As shown, the training system also includes an updating module 3;

[0107] The updating module 3 is used to update the food category data to obtain a new target prediction model.

[0108] In one feasible solution, the target prediction model is trained using volume data, initial water volume data, real-time stable steam flow data, and food weight data to obtain a calculation formula corresponding to the target prediction model:

[0109] G=f(V,L,Q,M)

[0110] In this embodiment, taking the cooking device as a pot as an example, the dependent variables of the food maturity level S are: volume data V, initial water volume data L, real-time stable steam flow data Q, food category data C, and food weight data M. The food maturity level S can be obtained by using different food category data C in different pots (with different V values), different initial water volume data L, real-time stable steam flow data Q under different fire states, and different food weight data M to obtain the cooking time T corresponding to the food maturity level S of different food category data C. C , and then the relationship mapping is performed based on the independent variable x = [V, L, Q, M] and the dependent variable food maturity level S. The specific mapping method can discretize the food maturity level S and can be used to map T at a fixed time interval △t. C Classify and obtain the corresponding food maturity level S' through the following formula C .

[0111] S′ C =i T C ∈[i*△t, (i+1)*△t], i∈0,1,2…

[0112] Finally, we can get the discrete maturity level S′ of all ingredients, that is, S′=[S′0,…,S′ C ]. Then, x and S′ are trained by regression (e.g., XGBoost, LightGBM, neural network, etc.) to obtain the corresponding regression prediction model G, that is, G = f(V, L, Q, M), and the C-dimensional vector of food category data is output.

[0113] The updating module 3 is used to update the new target prediction model using the food category data, including:

[0114]

[0115] Wherein, G represents the target prediction model, V represents the volume data, L represents the initial water volume data, Q represents the real-time stable steam flow data, M represents the food weight data, and Ic represents the food category vector corresponding to the food category data (for example, Ic = [0, 0, ..., 1, ..., 0], with a total of C dimensions, the component under the corresponding food index is 1, and the rest are 0). Represents the updated target prediction model.

[0116] In this embodiment, the volume data V, the initial water volume data L, the real-time stable steam flow data Q, the food weight data M and the corresponding food category data C obtained in advance can be used according to the above formula The maturity level of ingredient C can be predicted.

[0117] This embodiment proposes a food maturity level identification system based on a regression prediction model. Specifically, the regression prediction model is used to take the influencing parameters of each group of sample food as input and the corresponding sample food maturity level information as output, and a target prediction model is obtained by training. Furthermore, a new target prediction model is obtained by updating the food category data, thereby further improving the accuracy of the target prediction model.

[0118] Example 4

[0119] The cooking control method of this embodiment is implemented by using the training method of the food maturity level prediction model of the above-mentioned embodiment 1 or 2. Specifically, Figure 5 As shown, the control method includes:

[0120] S201, obtaining actual cooking data associated with the cooking state of ingredients in the current cooking environment;

[0121] S202, inputting actual cooking data into a target prediction model to output cooking times corresponding to different levels of maturity of ingredients under the current cooking environment;

[0122] In a possible embodiment, the time required for a food ingredient to be cooked to maturity under certain conditions is defined as the maturity level of the food ingredient, for example, the maturity level of a food ingredient that is cooked to maturity in 0-5 minutes is Level I, the maturity level of a food ingredient that is cooked to maturity in 5-10 minutes is Level II, the maturity level of a food ingredient that is cooked to maturity in 10-15 minutes is Level III, and the maturity level of a food ingredient that is cooked to maturity in 15-20 minutes is Level IV. It should be noted that the results of the above-mentioned food ingredients being cooked to maturity under certain conditions are obtained by testing by professionals, and the standard is that the food ingredient is neither overcooked nor overcooked.

[0123] In addition, it should be noted that the maturity level of ingredients in this embodiment can also be refined. For example, each maturity level of ingredients can be refined into various effects such as crispy, moderate, soft and glutinous. By collecting multiple groups of offline cooking data associated with the cooking status of ingredients and then conducting offline training, the cooking time of corresponding ingredients when users want to obtain different tastes can be obtained.

[0124] S203: Acquire the input target ingredient maturity level to determine the corresponding target cooking time, so as to control the cooking device to cook the target cooking time.

[0125] In the present embodiment, for a certain ingredient, the system only needs to obtain the maturity level of the ingredient input by the user to determine the target cooking time corresponding to the ingredient, thereby controlling the cooking equipment to cook the ingredient to the target cooking time, avoiding the ingredient from being overcooked or over-cooked, meeting the needs of the user, and ensuring that when ingredients are steamed in different pots, the cooking time required for different ingredients can be accurately controlled to ensure the cooking taste of the food, greatly improving the user's cooking experience.

[0126] In an practicable solution, the cooking device is provided with a gas flow detection device and a weighing device, and step S201 includes:

[0127] Obtain food weight data and initial water volume data of cooking equipment through weighing equipment;

[0128] In this embodiment, the weighing device is arranged at the bottom of the cooking device. The weighing device may be a pressure sensor or other device capable of weighing. For example, the weight data of the food and the initial water volume data of the cooking device may be obtained through the pressure sensor.

[0129] Collect real-time and stable steam flow data of cooking equipment through gas flow detection equipment;

[0130] In this embodiment, the gas flow detection device may be a gas flow meter, or other device that can detect gas flow, which is not specifically limited here.

[0131] The volume data of the cooking device is obtained through label information on the cooking device or a volume measuring device.

[0132] In this embodiment, the ingredient category data can be identified through the image recognition function of the camera of the mobile terminal; for example, the mobile terminal is a smart phone, and assuming that the smart phone has established a communication connection with the cooking device, when the user puts a certain ingredient into the cooking device, the category of the current ingredient can be obtained by scanning the QR code or barcode on the ingredient packaging through the camera in the smart phone.

[0133] The gas flow detection device of this embodiment can be applied to a variety of scenarios, such as a gas flow detection device in a kitchen scenario.

[0134] Take the kitchen scene as an example, the cooking equipment is a pot, and the gas flow detection equipment is a gas flow meter. Figure 6As shown, a represents a stove, b represents a pot placed on the stove a, c represents a gas flow meter, d represents a pot cover body, e represents a bracket on the stove a, and f represents a stove fire switch; wherein, a gas flow meter c is provided on the pot cover body d, which is used to monitor the steam flow from the pot to the outside of the pot in real time during cooking; a human-computer interaction module is provided on the stove fire switch f, and both the gas flow meter c and the human-computer interaction module are provided with a power module and a communication module to realize real-time information feedback between the gas flow meter c and the stove fire switch f. In the specific implementation process, the user can set the total cooking time of a certain ingredient through the human-computer interaction module, and after the cooking time is over, the stove fire switch f will automatically turn off.

[0135] It should be noted that when the food category and the initial amount of water in the pot are determined, the size of the steam flow data in a steady state is related to the firepower and the pot volume, so the pot volume and the steam flow value in a steady state can be used to represent the firepower. The maturity level of the food is related to the food category, the firepower, and the initial amount of water in the pot. Therefore, the factors that usually affect the maturity level of the food include but are not limited to the food category data, the pot volume data, the initial water volume data in the pot, the steam flow data in a steady state, and the food weight data. Other factors that affect the food can also be considered according to the actual scene requirements to meet the usage requirements of different actual cooking scenes.

[0136] This embodiment inputs the actual cooking data associated with the cooking status of the ingredients in the current cooking environment into the trained target prediction model to output the cooking time corresponding to different ingredient maturity levels in the current cooking environment, and determines the corresponding target cooking time by obtaining the input target ingredient maturity level, thereby controlling the cooking equipment to cook the target ingredient to the target cooking time. The cooking time required for different ingredients can be accurately controlled to ensure that the ingredients are not overcooked or overcooked, thereby meeting the needs of users and improving the cooking control efficiency.

[0137] Example 5

[0138] The cooking control system of this embodiment is implemented by using the training system of the food maturity level prediction model of the above-mentioned embodiment 3. Specifically, Figure 7 As shown, the control system includes a second acquisition module 81, a third acquisition module 82 and a fourth acquisition module 83;

[0139] The second acquisition module 81 is used to acquire actual cooking data associated with the cooking state of the ingredients in the current cooking environment;

[0140] A third acquisition module 82 is used to input the actual cooking data into the target prediction model to output the cooking time corresponding to different food maturity levels under the current cooking environment;

[0141] In a possible embodiment, the time required for a food ingredient to be cooked to maturity under certain conditions is defined as the maturity level of the food ingredient, for example, the maturity level of a food ingredient that is cooked to maturity in 0-5 minutes is Level I, the maturity level of a food ingredient that is cooked to maturity in 5-10 minutes is Level II, the maturity level of a food ingredient that is cooked to maturity in 10-15 minutes is Level III, and the maturity level of a food ingredient that is cooked to maturity in 15-20 minutes is Level IV. It should be noted that the results of the above-mentioned food ingredients being cooked to maturity under certain conditions are obtained by testing by professionals, and the standard is that the food ingredient is neither overcooked nor overcooked.

[0142] In addition, it should be noted that the maturity level of ingredients in this embodiment can also be refined. For example, each maturity level of ingredients can be refined into various effects such as crispy, moderate, soft and glutinous. By collecting multiple groups of offline cooking data associated with the cooking status of ingredients and then conducting offline training, the cooking time of corresponding ingredients when users want to obtain different tastes can be obtained.

[0143] The fourth acquisition module 83 is used to acquire the input target ingredient maturity level to determine the corresponding target cooking time, so as to control the cooking device to cook for the target cooking time.

[0144] In the present embodiment, for a certain ingredient, the system only needs to obtain the maturity level of the ingredient input by the user to determine the target cooking time corresponding to the ingredient, thereby controlling the cooking equipment to cook the ingredient to the target cooking time, avoiding the ingredient from being overcooked or over-cooked, meeting the needs of the user, and ensuring that when ingredients are steamed in different pots, the cooking time required for different ingredients can be accurately controlled to ensure the cooking taste of the food, greatly improving the user's cooking experience.

[0145] In one feasible solution, the cooking device is provided with a gas flow detection device and a weighing device, such as Figure 7 As shown, the second acquisition module 81 includes a first acquisition unit 811, a collection unit 812 and a second acquisition unit 813;

[0146] A first acquisition unit 811 is used to acquire food weight data and initial water volume data of a cooking device through a weighing device;

[0147] In this embodiment, the weighing device is arranged at the bottom of the cooking device. The weighing device may be a pressure sensor or other device capable of weighing. For example, the weight data of the food and the initial water volume data of the cooking device may be obtained through the pressure sensor.

[0148] A collection unit 812, used to collect real-time stable steam flow data of the cooking device through a gas flow detection device;

[0149] In this embodiment, the gas flow detection device may be a gas flow meter, or other device that can detect gas flow, which is not specifically limited here.

[0150] The second acquiring unit 813 is used to acquire the volume data of the cooking device through label information on the cooking device or a volume measuring device.

[0151] In this embodiment, the ingredient category data can be identified through the image recognition function of the camera of the mobile terminal; for example, the mobile terminal is a smart phone, and assuming that the smart phone has established a communication connection with the cooking device, when the user puts a certain ingredient into the cooking device, the category of the current ingredient can be obtained by scanning the QR code or barcode on the ingredient packaging through the camera in the smart phone.

[0152] The gas flow detection device of this embodiment can be applied to a variety of scenarios, such as a gas flow detection device in a kitchen scenario.

[0153] Take the kitchen scene as an example, the cooking equipment is a pot, and the gas flow detection equipment is a gas flow meter. Figure 6 As shown, a represents a stove, b represents a pot placed on the stove a, c represents a gas flow meter, d represents a pot cover body, e represents a bracket on the stove a, and f represents a stove fire switch; wherein, a gas flow meter c is provided on the pot cover body d, which is used to monitor the steam flow from the pot to the outside of the pot in real time during cooking; a human-computer interaction module is provided on the stove fire switch f, and both the gas flow meter c and the human-computer interaction module are provided with a power module and a communication module to realize real-time information feedback between the gas flow meter c and the stove fire switch f. In the specific implementation process, the user can set the total cooking time of a certain ingredient through the human-computer interaction module, and after the cooking time is over, the stove fire switch f will automatically turn off.

[0154] It should be noted that when the food category and the initial amount of water in the pot are determined, the size of the steam flow data in a steady state is related to the firepower and the pot volume, so the pot volume and the steam flow value in a steady state can be used to represent the firepower. The maturity level of the food is related to the food category, the firepower, and the initial amount of water in the pot. Therefore, the factors that usually affect the maturity level of the food include but are not limited to the food category data, the pot volume data, the initial water volume data in the pot, the steam flow data in a steady state, and the food weight data. Other factors that affect the food can also be considered according to the actual scene requirements to meet the usage requirements of different actual cooking scenes.

[0155] This embodiment inputs the actual cooking data associated with the cooking status of the ingredients in the current cooking environment into the trained target prediction model to output the cooking time corresponding to different ingredient maturity levels in the current cooking environment, and determines the corresponding target cooking time by obtaining the input target ingredient maturity level, thereby controlling the cooking equipment to cook the target ingredient to the target cooking time. The cooking time required for different ingredients can be accurately controlled to ensure that the ingredients are not overcooked or overcooked, thereby meeting the needs of users and improving the cooking control efficiency.

[0156] The present invention also provides a smart home appliance, which includes the cooking control system in the above embodiment 5. The smart home appliance can control its own working time through the above cooking control system, and can automatically adjust its own working time according to actual needs, effectively saving energy.

[0157] Example 6

[0158] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Example 6 of the present invention. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the training method of the food maturity level prediction model in any of Examples 1 or 2 is implemented. Figure 8 The electronic device 30 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0159] like Figure 8 As shown, the electronic device 30 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0160] The bus 33 includes a data bus, an address bus, and a control bus.

[0161] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read-only memory (ROM) 323 .

[0162] The memory 32 may also include a program / utility 325 having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0163] The processor 31 executes various functional applications and data processing by running the computer program stored in the memory 32, such as the training method of the food maturity level prediction model in any embodiment of Embodiment 1 or 2 of the present invention.

[0164] The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 35. Furthermore, the model generating device 30 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 36. Figure 8 As shown, the network adapter 36 communicates with other modules of the model-generated device 30 via the bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model-generated device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0165] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0166] Example 7

[0167] A schematic diagram of the structure of an electronic device provided in Embodiment 7 of the present invention. The schematic diagram of the structure of the electronic device in this embodiment is similar to Figure 8 The electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the cooking control method of embodiment 4 is implemented when the processor executes the program. Figure 8 The electronic device 30 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0168] like Figure 8 As shown, the electronic device 30 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0169] The bus 33 includes a data bus, an address bus, and a control bus.

[0170] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read-only memory (ROM) 323 .

[0171] The memory 32 may also include a program / utility 325 having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0172] The processor 31 executes various functional applications and data processing by running the computer programs stored in the memory 32, such as the cooking control method of embodiment 4 of the present invention.

[0173] The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 35. Furthermore, the model generating device 30 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 36. Figure 8 As shown, the network adapter 36 communicates with other modules of the model-generated device 30 via the bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model-generated device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0174] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0175] Example 8

[0176] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the training method of the food maturity level prediction model of any embodiment in Embodiment 1 or 2 is implemented.

[0177] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0178] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the training method of the food maturity level prediction model of any embodiment in Example 1 or 2.

[0179] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0180] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that this is only for illustration and the protection scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but these changes and modifications all fall within the protection scope of the present invention.

[0181] Example 9

[0182] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the cooking control method of embodiment 4 is implemented.

[0183] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0184] In a possible implementation manner, the present invention can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the cooking control method of embodiment 4.

[0185] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0186] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that this is only for illustration and the protection scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A method for training a food maturity level prediction model, characterized in that: The training method comprises: Acquire several groups of sample cooking data associated with the cooking status of ingredients; The sample cooking data includes sample food influencing parameters and corresponding sample food maturity level information, and different sample food maturity level information corresponds to different cooking times; Taking each group of sample food influencing parameters as input and the corresponding sample food maturity level information as output, training to obtain a target prediction model; The target prediction model is used to predict the cooking time corresponding to different food maturity levels in any cooking environment; The sample food influencing parameter corresponds to food-related data and / or cooking equipment-related data; The food-related data includes food category data and / or food weight data; and / or, The cooking equipment-related data includes at least one of volume data of the cooking equipment, initial water volume data, and real-time stable steam flow data; When the sample food influencing parameters include the volume data of the cooking device, the initial water volume data, the real-time stable steam flow data and the food weight data, the step of taking each group of the sample food influencing parameters as input and the corresponding sample food maturity level information as output to train and obtain the target prediction model includes: A regression prediction model is used to take the influencing parameters of each group of sample ingredients as input and the corresponding maturity level information of the sample ingredients as output, and the target prediction model is obtained by training; When the sample food influencing parameter also includes the food category data, the training method includes: The food category data is used to update the new target prediction model.

2. The method for training a food maturity level prediction model according to claim 1, characterized in that: The calculation formula corresponding to the target prediction model obtained by training using the volume data, the initial water volume data, the real-time stable steam flow data and the food weight data is: The step of using the food category data to update the new target prediction model comprises: Wherein, G represents the target prediction model, V represents the volume data, L represents the initial water volume data, Q represents the real-time stable steam flow data, M represents the food weight data, and Ic represents the food category vector corresponding to the food category data. Represents the updated target prediction model.

3. A training system for a food maturity level prediction model, characterized in that: The training system includes a first acquisition module and a training module; The first acquisition module is used to acquire several groups of sample cooking data associated with the cooking status of the food ingredients; The sample cooking data includes sample food influencing parameters and corresponding sample food maturity level information, and different sample food maturity level information corresponds to different cooking times; The training module is used to take each group of sample food influencing parameters as input and the corresponding sample food maturity level information as output, and train to obtain a target prediction model; The target prediction model is used to predict the cooking time corresponding to different food maturity levels in any cooking environment; The sample food influencing parameter corresponds to food-related data and / or cooking equipment-related data; The food-related data includes food category data and / or food weight data; and / or, The cooking equipment-related data includes at least one of volume data of the cooking equipment, initial water volume data, and real-time stable steam flow data; When the sample food influencing parameters include the volume data of the cooking device, the initial water volume data, the real-time stable steam flow data and the food weight data, the training module is specifically used to adopt a regression prediction model to take each group of the sample food influencing parameters as input and the corresponding sample food maturity level information as output, and train to obtain the target prediction model; When the sample food influencing parameter also includes the food category data, the training system further includes an updating module; The updating module is used to update the new target prediction model using the food category data.

4. A cooking control method, the control method is implemented by using the training method of the food maturity level prediction model described in claim 1 or 2, characterized in that: The control method comprises: Obtain actual cooking data associated with the cooking status of ingredients in the current cooking environment; Inputting the actual cooking data into the target prediction model to output the cooking time corresponding to different food maturity levels under the current cooking environment; The input target ingredient maturity level is obtained to determine the corresponding target cooking time, so as to control the cooking device to cook for the target cooking time.

5. The cooking control method according to claim 4, characterized in that: The cooking device is provided with a gas flow detection device and a weighing device, and the step of obtaining actual cooking data associated with the cooking state of the food in the current cooking environment comprises: Acquiring food weight data and initial water volume data of the cooking device through the weighing device; Collecting real-time and stable steam flow data of the cooking device through the gas flow detection device; The volume data of the cooking device is obtained through label information on the cooking device or a volume measuring device.

6. A cooking control system, the control system being implemented by using the training system of the food maturity level prediction model according to claim 3, characterized in that: The control system includes a second acquisition module, a third acquisition module and a fourth acquisition module; The second acquisition module is used to acquire actual cooking data associated with the cooking state of the ingredients in the current cooking environment; The third acquisition module is used to input the actual cooking data into the target prediction model to output the cooking time corresponding to different maturity levels of ingredients under the current cooking environment; The fourth acquisition module is used to acquire the input target ingredient maturity level to determine the corresponding target cooking time, so as to control the cooking device to cook for the target cooking time.

7. The cooking control system according to claim 6, characterized in that: The cooking device is provided with a gas flow detection device and a weighing device, and the second acquisition module includes a first acquisition unit, a collection unit and a second acquisition unit; The first acquisition unit is used to acquire the weight data of the food material and the initial water volume data of the cooking device through the weighing device; The collecting unit is used to collect the real-time stable steam flow data of the cooking device through the gas flow detection device; The second acquiring unit is used to acquire the volume data of the cooking device through label information on the cooking device or a volume measuring device.

8. A smart home appliance, characterized in that: Comprising a cooking control system as claimed in claim 6 or 7.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the training method of the food maturity level prediction model as described in claim 1 or 2, or implements the cooking control method as described in claim 4 or 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the training method of the food maturity level prediction model as described in claim 1 or 2, or implements the cooking control method as described in claim 4 or 5.

Images