Food material cooking control method and device, cooking equipment and storage medium

Abstract

The invention relates to the technical field of intelligent equipment, and discloses a food material cooking control method and device, cooking equipment and a storage medium. The method comprises the steps that current multi-mode initial parameters of to-be-cooked food materials are obtained, and the multi-mode initial parameters comprise the food material type, the food material weight and the initial temperature; a current cooking strategy matched with the current multi-mode initial parameters is determined through a decision model, the current cooking strategy comprises stage cooking strategies of one or more stages, and each stage cooking strategy comprises one or more of the target temperature, the duration time, the cooking mode and the stage switching condition; according to the current cooking strategy, one or more devices are controlled to cook the food materials to be cooked. Therefore, a'zero-experience user 'can obtain'professional-level' cooking finished products through'one-key operation 'under any food material specification or food material type, and the self-adaptability and intelligence of the cooking equipment are improved.

Description

Technical Field

[0001] This application relates to the field of smart device technology, such as methods, apparatus, cooking equipment, and storage media for controlling food cooking. Background Technology

[0002] Modern consumers, especially younger generations, pursue a high-quality lifestyle and enjoy the pleasure of cooking, but at the same time, they generally face the contradiction of "scarcity of time" and "lack of skills." They want to achieve professional-level cooking results but lack the experience and time of professional chefs. Therefore, they place higher demands on the "intelligence," "automation," and "ease of use" of home appliances.

[0003] Currently, cooking equipment, such as ovens, microwave ovens, and air fryers, can automate cooking through preset programs. This involves testing one or more sets of what are considered the "optimal" cooking parameters (temperature, time, mode) for common, standardized ingredients (such as whole chickens, pizzas, and cookies). Users can then select the corresponding program, and the cooking equipment will use these parameters to cook. However, this cooking control method is extremely rigid and lacks flexibility. Using the same cooking parameters for a 1kg chicken and a 2.5kg chicken might result in one chicken being overcooked and burnt, while the other remains uncooked. Of course, this cooking method also struggles to produce dishes that meet user needs for special ingredients, such as frozen or other special ingredients. Furthermore, the cooking process is typically monitored using a single parameter, such as the core temperature of the food, stopping cooking when it reaches a set temperature, or the current cooking time, stopping cooking when it exceeds a set time. This monitoring method only controls the "end point" but cannot optimize the "process," requiring users to manually set process parameters.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0006] This disclosure provides a method, apparatus, cooking equipment, and storage medium for controlling the cooking of ingredients, in order to solve the technical problem that the intelligence of cooking equipment needs to be improved.

[0007] In some embodiments, the method includes: Obtain the current multimodal initial parameters of the ingredients to be cooked, including: ingredient type, ingredient weight, and initial temperature; The decision model determines the current cooking strategy that matches the current multimodal initial parameters. The current cooking strategy includes one or more stage cooking strategies, and each stage cooking strategy includes one or more of the following: target temperature, duration, cooking mode, and stage switching conditions. Based on the current cooking strategy, control one or more devices to perform the cooking process on the ingredients to be cooked.

[0008] In this way, through multimodal initial parameters, decision models, and a closed-loop architecture of multi-stage collaborative control, the cooking process can generate a stage-by-stage cooking strategy that perfectly matches the type, weight, and initial temperature of the ingredients within seconds, without relying on user experience. This greatly improves the success rate of cooking different sizes of ingredients, such as frozen, refrigerated, whole, or diced ingredients, and significantly enhances the intelligence level of cooking equipment and user experience.

[0009] In some embodiments, obtaining the current multimodal initial parameters of the food to be cooked includes: The current image of the ingredients to be cooked is acquired through an image acquisition device. A convolutional neural network (CNN) image recognition model is trained to identify the current image of the ingredients and determine the type of ingredients to be cooked. The weight of the ingredients to be cooked is obtained through a weight acquisition device; The initial temperature of the food to be cooked is obtained through a temperature acquisition device.

[0010] It is evident that by using a trained CNN image recognition model to classify current food images in real time, the accuracy of food recognition can be improved. Combined with weight and temperature acquisition devices, precise three-dimensional data such as type, weight, and initial temperature can be obtained in one go without opening the lid or damaging the food. This yields multimodal initial parameters, reducing initial errors caused by manual estimation or single-point acquisition, providing accurate input for subsequent decision-making models, and ensuring a high degree of accuracy in the starting point of cooking strategies.

[0011] In some embodiments, obtaining the current multimodal initial parameters of the food to be cooked further includes: Get the cooking information of the ingredients to be cooked as input by the user.

[0012] Therefore, users can input the corresponding ingredient cooking information according to their needs. In this way, cooking decisions can be made based on user needs and preferences, taking into account both intelligent and personalized experience.

[0013] In some embodiments, determining the current cooking strategy that matches the current multimodal initial parameters includes: Based on the saved first decision model, determine the current cooking strategy that matches the current multimodal initial parameters. The first decision model includes the correspondence between ingredient type, weight, initial temperature, and cooking strategy; or... Based on the saved second decision model, determine the current cooking strategy that matches the current multimodal initial parameters. The second decision model is a mathematical model constructed based on the heat conduction equation, taking into account the type and weight of the ingredients, initial temperature, and target temperature; or... Based on the saved third decision model, a current cooking strategy matching the current multimodal initial parameters is determined. The third decision model is a machine learning model trained based on ingredient sample information.

[0014] By employing three heterogeneous decision engines—lookup tables, mathematical models based on Fourier's law of heat conduction, and machine learning models—it can quickly output cooking strategies for common ingredients and provide feasible solutions for unseen new ingredient categories. This achieves a tiered balance between response speed and generalization ability, thereby overcoming the predicament of fixed programs being unable to handle non-standard ingredients and significantly improving the equipment's adaptability.

[0015] In some embodiments, determining the current cooking strategy that matches the current multimodal initial parameters further includes: If a cooking strategy matching the current multimodal initial parameters is found in the first decision model, the found cooking strategy is determined as the current cooking strategy. The first decision model is a multidimensional lookup table that includes the correspondence between ingredient type, weight, initial temperature and cooking strategy. If no cooking strategy matching the current multimodal initial parameters is found, the second decision model is used to solve the problem based on the current multimodal initial parameters, and the solution is determined as the current cooking strategy. Without obtaining a solution, the current multimodal initial parameters are input into the third decision model to predict the corresponding current cooking strategy.

[0016] As can be seen, by using lookup tables, mathematical models based on Fourier's law of heat conduction, and forced degradation order of machine learning models, both device performance and reliability are taken into account. No manual configuration is required if any model fails, maintaining a continuous experience with zero user intervention and significantly improving the system's reliability and platform scalability.

[0017] In some embodiments, controlling one or more devices to perform the cooking operation on the ingredients to be cooked includes: Based on the current cooking strategy in the current cooking strategy, a corresponding current multi-channel PWM control signal is generated to control the cooking in the current stage. The current multi-channel PWM control signal includes one or more of the following: a first current PWM duty cycle for adjusting the heating tube for adjusting the upper and lower heating temperatures, a second current PWM duty cycle for adjusting the fan speed of the internal circulation of the cooking equipment, and a third current PWM duty cycle for adjusting the steam injection amount of the steam generator. The current monitoring parameter values ​​in the current stage of cooking control are obtained, and if the current stage switching conditions are met based on the current monitoring parameter values, the stage cooking strategy of the next stage is switched, and the operation control of one or more corresponding devices is performed. The current monitoring parameter values ​​include one or more of the following: the current temperature value inside the device, the current temperature value at the center of the food, and the current stage cooking duration.

[0018] By generating multi-channel PWM control signals, the duty cycle of the heating element, circulating fan, and steam generator can be independently adjusted, and the cavity temperature, food center temperature, and stage duration can be monitored in real time. Thus, stage switching can be triggered by two or more conditions such as temperature threshold and duration, so that the cooking professional indicators can reach the level of professional chefs, and no user intervention is required in the process, which significantly improves the cooking quality and automation.

[0019] In some embodiments, after cooking the ingredients to be cooked, the process further includes: Obtain cooking feedback information from the ingredients to be cooked, and update the decision model based on the cooking feedback information. The cooking feedback information includes one or more of the following: temperature curve information, wind speed curve information, and user satisfaction feedback information.

[0020] In this way, the decision-making model can be updated based on cooking feedback, such as triggering sample write-back and model retraining, thereby forming a self-evolutionary closed loop, ensuring that the device becomes increasingly intelligent and continuously optimizes cooking results and user experience.

[0021] In some embodiments, the apparatus includes a processor and a memory storing program instructions, wherein the processor is configured to execute the above-described method for controlling the cooking of ingredients when executing the program instructions.

[0022] In some embodiments, the device includes: a device body, wherein the aforementioned means for controlling the cooking of ingredients is mounted on the device body.

[0023] In some embodiments, the storage medium stores program instructions that, when executed, perform the method described above for controlling the cooking of ingredients.

[0024] The method, apparatus, cooking equipment, and storage medium for controlling food cooking provided in this disclosure can achieve the following technical effects: By acquiring multimodal initial parameters and fusing three models for decision-making, a multi-stage cooking strategy that precisely matches the type, weight, and initial temperature of the ingredients can be quickly generated and controlled. This allows even users with zero experience to obtain professional-grade, highly consistent, and low-energy-consumption cooked products with a single click, regardless of the ingredient size or type, thus improving the adaptability and intelligence of the cooking equipment. Furthermore, the collaborative operation of multiple components further enhances cooking quality and automation; and by updating the decision model based on cooking feedback, the equipment possesses self-learning capabilities, continuously optimizing its strategies and ensuring that the equipment becomes increasingly intelligent.

[0025] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0026] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein: Figure 1 This is a schematic flowchart of a method for controlling the cooking of ingredients provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of the structure of an oven provided in an embodiment of this disclosure; Figure 3 This is a schematic flowchart of a method for controlling the cooking of ingredients provided in an embodiment of this disclosure; Figure 4 This is a schematic diagram of a food cooking control device provided in an embodiment of the present disclosure; Figure 5 This is a schematic diagram of a food cooking control device provided in an embodiment of the present disclosure; Figure 6 This is a schematic diagram of a food cooking control device provided in an embodiment of the present disclosure; Figure 7 This is a schematic diagram of the structure of a cooking device provided in an embodiment of this disclosure. Detailed Implementation

[0027] To provide a more detailed understanding of the features and technical content of the embodiments of this disclosure, the implementation of the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this disclosure. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0028] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0029] Unless otherwise stated, the term "multiple" means two or more.

[0030] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0031] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0032] Ovens, microwave ovens, air fryers, and other cooking appliances are all intelligent devices. In this embodiment, the cooking appliance can make intelligent decisions based on multimodal initial parameters such as ingredient type, weight, and initial temperature, generating one or more stage cooking strategies. It then controls one or more components within the cooking appliance according to these stage cooking strategies. This allows even users with zero experience to obtain professional-grade, highly consistent, and low-energy-consumption cooked products with any ingredient size or type through a single click, improving the adaptability and intelligence of the cooking appliance. The intelligent decision-making can be based on various models, including lookup table models, mathematical models based on Fourier's law of heat conduction, and machine learning models. This allows for both heterogeneous decision-making and forced degradation decisions, further enhancing the flexibility and intelligence of cooking control while also considering device performance and reliability. Furthermore, the decision model can be updated based on cooking feedback, enabling the appliance to have self-learning capabilities and continuously optimize its strategies, ensuring the appliance becomes increasingly intelligent.

[0033] Figure 1 This is a schematic flowchart illustrating a method for controlling the cooking of ingredients according to an embodiment of this disclosure. Figure 1 As shown, the method includes: Step 101: Obtain the current multimodal initial parameters of the ingredients to be cooked, including: ingredient type, ingredient weight, and initial temperature.

[0034] When one, two, or more ingredients such as chicken, steak, tomatoes, and potatoes are placed in cooking appliances such as ovens, microwave ovens, electric cookers, frying pans, and air fryers, these ingredients are considered to be the ingredients to be cooked. Before cooking, it is necessary to obtain the initial parameters of the ingredients to be cooked. In this embodiment, the initial parameters are multimodal. These parameters can be obtained through a configured image acquisition device to acquire a current image of the ingredients to be cooked, through a configured weight acquisition device to acquire the weight of the ingredients to be cooked, and through a temperature acquisition device to acquire the initial temperature of the ingredients to be cooked, among two or more of these. Of course, the cooking appliance also has a recognition function and can also recognize the acquired multimodal initial parameters. Therefore, in some embodiments, obtaining the current multimodal initial parameters of the ingredients to be cooked includes: acquiring a current image of the ingredients to be cooked through an image acquisition device; using a trained convolutional neural network (CNN) image recognition model to recognize the current image of the ingredients to be cooked and obtain the type of ingredients; acquiring the weight of the ingredients to be cooked through a weight acquisition device; and acquiring the initial temperature of the ingredients to be cooked through a temperature acquisition device.

[0035] For example, an oven may be equipped with a multimodal sensing matrix, including a weight sensor on the oven floor, an infrared temperature sensor and a high-definition camera on the top of the cavity, and may also include a contact temperature probe, humidity sensor, fan speed sensor, etc. Thus, after food is placed in the oven, through the interface with each sensor, one, two, or more initial parameter information can be obtained, such as the food image, food weight, food temperature, humidity inside the cavity, and fan speed inside the cavity. This data can then be processed and identified to obtain the current multimodal initial parameters, including the type and weight of the food, and the initial temperature.

[0036] The process involves acquiring an image of the food to be cooked using an image acquisition device. Image recognition can be performed in various ways, including training a convolutional neural network (CNN) image recognition model to identify the type of food in the image. Other information about the food, such as its projected area and thickness, can also be obtained, leading to its volume.

[0037] The specific types of Convolutional Neural Network (CNN) image recognition models trained can vary. For example, lightweight single-task classification networks, including MobileNetV3, ShuffleNetV2, and EfficientNet-B0, can be trained using image samples corresponding to various common food types to obtain a CNN image recognition model capable of predicting food types. Alternatively, multi-task shared backbone networks, including EfficientNet-B0, can predict food type, projected area, thickness, and other parameters simultaneously.

[0038] Of course, in some embodiments, the cooking device can not only automatically and intelligently acquire the current multimodal initial parameters of the ingredients to be cooked, but also acquire the cooking information of the ingredients input by the user. For example, the user can adjust and modify the intelligently acquired multimodal initial parameters, or input information other than the acquired multimodal initial parameters, such as modifying the intelligently acquired ingredient weight, or inputting cooking flavor information, such as "crispy on the outside and juicy on the inside".

[0039] Step 102: Determine the current cooking strategy that matches the current multimodal initial parameters through the decision model. The current cooking strategy includes: one or more stage cooking strategies, and each stage cooking strategy includes: one or more of the following: target temperature, duration, cooking mode, and stage switching conditions.

[0040] Different cooking devices, different ingredients, and even the same ingredient may have different cooking processes depending on the current multimodal initial parameters. Some cooking processes only require a single stage of stir-frying, while others may require multiple stages such as defrosting, high-temperature heating, and low-temperature browning. Therefore, in this embodiment, the cooking device can intelligently determine a current cooking strategy that matches the current multimodal initial parameters. This current cooking strategy matches the cooking process of the ingredient and includes one, two, or more stage cooking strategies. Each stage cooking strategy includes one or more of the following: target temperature, duration, and cooking mode. The cooking mode may be a preset cooking mode, such as a defrosting mode, a heating mode, or a browning mode. In other words, the cooking parameters in these preset cooking modes are pre-configured. Alternatively, in some embodiments, determining the cooking mode in each stage cooking strategy may involve directly determining the cooking parameters, such as the heating element temperature and fan speed, or determining the cooking mode in each stage cooking strategy may involve determining the control signals corresponding to the cooking parameters, such as PWM control signals for the heating element temperature and fan speed.

[0041] In the case of a multi-stage cooking strategy, automatic switching between stages is required. Therefore, each stage cooking strategy can include stage switching conditions, such as: when the current internal temperature reaches the target temperature, directly switching to the next cooking stage; or when the current duration reaches the target duration, directly switching to the next cooking stage; or, when the current internal temperature of the ingredients reaches the set temperature and the internal airflow reaches the set airflow force, switching to the next cooking stage. In other words, the stage switching condition in each cooking strategy can be a single switching condition or a combination of multiple switching conditions.

[0042] Of course, in this embodiment of the present disclosure, the cooking device can intelligently determine the current cooking strategy that matches the current multimodal initial parameters. That is, the cooking device can pre-store one, two, or more decision models, and thus, the current cooking strategy that matches the current multimodal initial parameters can be determined through the stored decision models.

[0043] In some embodiments, determining the current cooking strategy matching the current multimodal initial parameters includes: determining the current cooking strategy matching the current multimodal initial parameters according to a first decision model, wherein the first decision model includes the correspondence between ingredient type, weight, initial temperature and cooking strategy; or, determining the current cooking strategy matching the current multimodal initial parameters according to a second decision model, wherein the second decision model is a mathematical model constructed based on the heat conduction equation according to ingredient type, weight, initial temperature and target temperature; or, determining the current cooking strategy matching the current multimodal initial parameters according to a third decision model, wherein the third decision model is a machine learning model obtained by training on ingredient sample information.

[0044] In some embodiments, the first decision model may be a multidimensional lookup table indexed by {type × weight range × initial temperature}, which stores the optimal cooking parameters verified by experiments, including one or more of the following: cooking temperature, duration, cooking mode, steam volume, air volume, etc.

[0045] Table 1 is a multidimensional lookup table included in the first decision model corresponding to an oven in this embodiment of the present disclosure.

[0046]

[0047] Table 1 If the ingredient to be cooked is chicken wings, with a weight of 400g and an initial temperature of 10℃, then according to Table 1, the corresponding current cooking strategy can be found. This current cooking strategy includes only one stage, where the oven's top heat temperature is 200℃, and the bottom heat temperature is 220℃, etc. If the ingredient to be cooked is still chicken wings, with a weight of 800g and an initial temperature of -10℃, then according to Table 1, the corresponding current cooking strategy can also be found. However, this current cooking strategy includes two stages. Stage 1 may include: top heat temperature of 180℃, bottom heat temperature of 180℃, etc., and the corresponding stage switching condition is that the core temperature of the ingredient reaches 0℃. Stage 2 may include: top heat temperature of 200℃, bottom heat temperature of 200℃, duration of 1000s, etc. It can be seen that the cooking equipment can save a first decision model to determine the current cooking strategy that matches the current multimodal initial parameters. Of course, in some embodiments, the first decision model can be a multidimensional lookup table indexed by {type × weight range × initial state}, where the initial state can be determined based on the initial temperature. For example, if the initial temperature is less than 0°C, the initial state can be determined as frozen; if the initial temperature is greater than or equal to 0°C but less than 2°C, the initial state can be determined as chilled; and if the initial temperature is greater than or equal to 2°C, the initial state can be determined as refrigerated. Since only the cooking strategy needs to be looked up in the stored correspondence, the decision-making speed is very fast, generally within 50ms, the corresponding current cooking strategy will be obtained.

[0048] Of course, cooking equipment can also establish more complex mathematical models, which can be stored as a second decision model. The second decision model can be obtained based on the heat conduction equation (such as Fourier's law). The second decision model will consider the specific heat capacity, thermal conductivity, density of the food, and the target temperature to solve for the required heating power and time. Among them, specific heat capacity, thermal conductivity, density, etc. can be obtained according to the type of food. Of course, density can also be obtained according to the weight of the food and the volume obtained by image recognition.

[0049] For example, the current multimodal initial parameters obtained by the oven include: steak size (2.5cm thick, 156cm² projected area) obtained through CNN recognition, 380g obtained through a weight sensor, -16℃ obtained through a temperature sensor, and medium-rare (70% cooked) input by the user. These parameters are then input into a transient temperature field solution model based on Fourier's law of heat conduction for solution. The solution results are shown in Table 2.

[0050]

[0051] Table 2 Therefore, the oven can determine the solution result as the current cooking strategy, as shown in Table 2. The current cooking strategy includes four stages: each stage cooking strategy includes corresponding cooking parameters and corresponding stage switching conditions, which will not be elaborated here. Because it requires solving the Fourier equation, the time for intelligent decision-making through the second decision model may be longer than that through the first decision model, but it is still relatively fast.

[0052] In some embodiments, a large amount of successful parameter data from professional chefs cooking various sizes of ingredients is collected, i.e., a large amount of ingredient cooking sample information is obtained. Then, a machine learning model, such as a gradient boosting tree or a neural network, is trained. This model can learn the complex nonlinear relationships in expert experience and make predictions, i.e., predict a cooking strategy that matches the multimodal initial parameters. For example, by collecting successful parameters from professional chefs on a large scale, a "multimodal input-multi-stage output" sample of the oven is constructed. Using a gradient boosting tree (XGBoost), a third decision model can be obtained. Thus, if the multimodal initial parameters include: broccoli, 450g, 2.0cm thickness, area 180 square centimeters, initial temperature 4℃, and the user input of soft and crisp, the oven can predict the current cooking strategy through the third decision model, as shown in Table 3.

[0053]

[0054] Table 3 As can be seen, the current cooking strategy determined by the oven based on the third decision model, matching the current multimodal initial parameters, is shown in Table 3. The current cooking strategy also includes four stages: each stage cooking strategy, which includes corresponding cooking parameters and stage switching conditions, details of which will not be elaborated here. Because it requires calling lightweight XGBoost, determining the current cooking strategy based on the third decision model takes longer than determining it based on the first and second decision models, and also places higher demands on the hardware.

[0055] By employing three heterogeneous decision engines—lookup tables, mathematical models based on Fourier's law of heat conduction, and machine learning models—it can quickly output cooking strategies for common ingredients and provide feasible solutions for unseen new ingredient categories. This achieves a tiered balance between response speed and generalization ability, thereby overcoming the predicament of fixed programs being unable to handle non-standard ingredients and significantly improving the equipment's adaptability.

[0056] Because there are many types of ingredients, and their weights, initial temperatures, etc., making decisions based on the stored first decision model, while fast, cannot necessarily cover all ingredient types, weights, and initial temperatures. Therefore, in some embodiments, determining the current cooking strategy that matches the current multimodal initial parameters further includes: if a cooking strategy matching the current multimodal initial parameters is found in the first decision model, the found cooking strategy is determined as the current cooking strategy. The first decision model is a multidimensional lookup table that includes the correspondence between ingredient types, weights, initial temperatures, and cooking strategies. If no cooking strategy matching the current multimodal initial parameters is found, a second decision model is used to solve the problem based on the current multimodal initial parameters. If a solution is obtained, the solution is determined as the current cooking strategy. If no solution is obtained, the current multimodal initial parameters are input into a third decision model to predict the corresponding current cooking strategy.

[0057] As can be seen, by using lookup tables, mathematical models based on Fourier's law of heat conduction, and forced degradation order of machine learning models, both device performance and reliability are taken into account. No manual configuration is required if any model fails, maintaining a continuous experience with zero user intervention and significantly improving the system's reliability and platform scalability.

[0058] Step 103: Based on the current cooking strategy, control one or more devices to perform the cooking operation on the ingredients to be cooked.

[0059] Different cooking appliances may include different components. For example, an oven includes an upper heating element, a lower heating element, a fan, a steam emitter, etc.; an air fryer includes an upper heating element, a fan, etc.; and a microwave oven includes a magnetron, a turntable, etc. Therefore, different cooking appliances can control the operation of one or more corresponding components according to the current cooking strategy.

[0060] In some embodiments, controlling one or more devices to perform cooking operations on the food to be cooked includes: generating a corresponding current multi-channel PWM control signal to perform current stage cooking control according to the current stage cooking strategy in the current cooking strategy, wherein the current multi-channel PWM control signal includes one or more of the following: a first current PWM duty cycle for adjusting the heating tube for adjusting the upper and lower heating temperatures, a second current PWM duty cycle for adjusting the fan speed of the internal circulation fan of the cooking device, and a third current PWM duty cycle for adjusting the steam injection amount of the steam generator.

[0061] The cooking equipment includes an upper heating element, a lower heating element, a fan, and a steam emitter. These components can be controlled by pulse width modulation (PWM) signals.

[0062] Furthermore, in some embodiments, controlling one or more devices to cook the food also includes: acquiring the current monitoring parameter value in the current stage of cooking control, and, if it is determined that the current stage switching conditions are met based on the current monitoring parameter value, switching to the next stage cooking strategy, and performing corresponding operation control of one or more devices, wherein the current monitoring parameter value includes one or more of the following: the current temperature value inside the device, the current temperature value at the center of the food, and the current stage cooking duration.

[0063] For example, the current cooking strategy is shown in Table 2. According to the oven's Stage 1 cooking policy, the corresponding current multi-channel PWM control signal can be generated and the upper heating element, lower heating element, fan, and steam emitter in the oven can be controlled respectively. The first current PWM duty cycle includes 40% and 30%; the second current PWM is obtained based on 800RPM; and the third current PWM duty cycle is 20%. Furthermore, the system monitors the current temperature of the food's center. When the current temperature is greater than 0°C, the system switches to the next cooking stage. Based on the oven's Stage 2 cooking policy, it generates corresponding multi-channel PWM control signals to control the operation of the upper heating element, lower heating element, fan, and steam emitter. The first current PWM duty cycle includes 80% and 60%; the second current PWM is based on 1500 RPM; and the third current PWM duty cycle is 0%. Similarly, the system monitors the current temperature of the food's center. When the current temperature is greater than 55°C, the system switches to the next cooking stage. Based on the oven's Stage 3 cooking policy, it generates corresponding multi-channel PWM control signals to control the operation of the upper heating element, lower heating element, fan, and steam emitter. The first current PWM duty cycle includes 100% and 0%; the second current PWM is based on 2500 RPM; and the third current PWM duty cycle is 0%. The system also monitors the cooking duration of Stage 3. When the cooking duration of Stage 3 reaches 90 seconds, the system switches to the next cooking stage. Finally, based on the oven's Stage 4 cooking policy, the corresponding current multi-channel PWM control signal is generated and used to control the operation of the upper heating element, lower heating element, fan, and steam emitter in the oven. The first current PWM duty cycle includes 0% and 0%; the second current PWM is obtained based on 500 RPM; and the third current PWM duty cycle is 0%. Similarly, the cooking duration of Stage 4 is monitored, and the cooking is completed when the cooking duration of Stage 4 reaches 3 minutes.

[0064] In this way, by generating multi-channel PWM control signals, the duty cycle of the heating element, circulating fan, and steam generator can be adjusted independently, and the cavity temperature, the center temperature of the food, and the duration of each stage can be monitored in real time. Thus, stage switching can be triggered by two or more conditions such as temperature threshold and duration, so that the cooking professional indicators can reach the level of a professional chef, and no user intervention is required throughout the process, which significantly improves the cooking quality and the degree of automation.

[0065] As can be seen, in this embodiment of the disclosure, by acquiring multimodal initial parameters and making decisions through three-model fusion, a multi-stage cooking strategy that precisely matches the type, weight, and initial temperature of the ingredients can be quickly generated, and one or more devices can be controlled. In this way, even "users with zero experience" can obtain "professional-grade, highly consistent, and low-energy-consumption" cooked products with "one-click operation" under any ingredient specifications or types, thus improving the adaptability of the cooking equipment.

[0066] In some embodiments, after cooking the ingredients, the process further includes: obtaining cooking feedback information from the ingredients and updating the decision model based on the cooking feedback information. The cooking feedback information includes one or more of temperature curve information, wind speed curve information, and user satisfaction feedback information. This allows the decision model to be updated based on the cooking feedback information, for example, by triggering sample write-back and model retraining, thereby forming a self-evolutionary closed loop that ensures the device becomes increasingly intelligent and continuously optimizes cooking results and user experience.

[0067] The following describes the operation process in a specific embodiment, illustrating the food cooking control process of the system for food cooking control provided by the embodiments of the present invention.

[0068] In this embodiment of the disclosure, the cooking device may be an oven, such as... Figure 2 As shown, the oven includes: a device 100 for controlling food cooking, a multimodal sensing matrix 200, and components 300. The device 100 includes a main controller MCU, such as an ARM Cortex-M series. The multimodal sensing matrix 200 includes a weight sensor placed on the oven base, an infrared temperature sensor and a high-definition camera located on the top of the cavity, a contact temperature probe, and a touchscreen, etc. Components 300 include an upper heating element, a lower heating element, a fan, a steam emitter, etc. The device 100 for controlling food cooking can be connected to each sensor via a corresponding interface and can also control the operation of the corresponding component 300 via PWM. Furthermore, the oven stores the first decision model shown in Table 1, the transient temperature field solution model based on Fourier's law of heat conduction (i.e., the second decision model), and a lightweight neural network model (i.e., the third decision model).

[0069] Figure 3 This is a schematic flowchart of a method for controlling the cooking of ingredients provided in an embodiment of this disclosure. In one embodiment, combined with... Figure 2 and Figure 3 The processes used for controlling the cooking of ingredients include: Step 301: After confirming that the ingredients to be cooked are placed in the cavity, the oven acquires the current image of the ingredients to be cooked through a high-definition camera. A convolutional neural network (CNN) image recognition model is trained to identify the current image of the ingredients and obtain the type, area, and thickness of the ingredients to be cooked.

[0070] Step 302: The oven obtains the weight of the food to be cooked through the configured weight sensor, and obtains the initial temperature of the food to be cooked through the contact temperature probe.

[0071] The order of steps 301 and 302 is not limited, and they can be executed simultaneously.

[0072] Step 303: The oven searches for a cooking strategy that matches the current multimodal initial parameters in the first decision model, where the multimodal initial parameters include: ingredient type, ingredient weight, and initial temperature.

[0073] Step 304: Determine if a cooking strategy matching the current multimodal initial parameters has been found. If yes, proceed to step 305; otherwise, proceed to step 306.

[0074] In Table 1, a cooking strategy that matches the current multimodal initial parameters can be found. If a strategy is found, proceed to step 305.

[0075] Step 305: The oven will identify the found cooking strategy as the current cooking strategy and proceed to step 310.

[0076] Step 306: The oven solves the problem based on the second decision model according to the current multimodal initial parameters.

[0077] Step 307: Determine if a solution has been obtained? If yes, proceed to step 308; otherwise, proceed to step 309.

[0078] Step 308: The oven determines the solution result as the current cooking strategy and proceeds to step 310.

[0079] Step 309: The oven inputs the current multimodal initial parameters into the third decision model, predicts the corresponding current cooking strategy, and then proceeds to step 310.

[0080] Step 310: Determine if the current cooking strategy includes only one stage. If yes, proceed to step 311; otherwise, proceed to step 312.

[0081] Step 311: The oven generates a corresponding current multi-channel PWM control signal based on the current cooking strategy to perform corresponding cooking control. This current multi-channel PWM control signal includes one or more of the following: a first current PWM duty cycle for adjusting the heating element's upper and lower heating temperatures; a second current PWM duty cycle for adjusting the fan speed within the cooking equipment; and a third current PWM duty cycle for adjusting the steam generator's steam injection volume. Proceed to step 318.

[0082] Step 312: The oven determines the Phase 1 cooking strategy in the current cooking strategy as the current phase cooking strategy.

[0083] Step 313: The oven generates the corresponding current multi-channel PWM control signal according to the current cooking strategy.

[0084] Step 314: The oven performs corresponding cooking control for the current stage based on the current multi-channel PWM control signal, and obtains the current monitored parameter values ​​in the current stage of cooking control.

[0085] Step 315: Determine whether the current stage switching conditions are met based on the current monitoring parameter values. If yes, proceed to step 316; otherwise, return to step 314.

[0086] The current cooking strategy includes stage switching conditions. If the current temperature value of the center of the ingredients reaches the set temperature, it can be determined that the current stage switching conditions are met; or, if the duration of the current stage reaches the set time, it can be determined that the current stage switching conditions are met.

[0087] Step 316: Is there a next stage of cooking strategy? If so, proceed to step 317; otherwise, proceed to step 318.

[0088] Step 317: The oven determines the next stage of cooking strategy as the current cooking strategy and returns to step 313.

[0089] Step 318: The oven obtains cooking feedback information from the ingredients to be cooked and updates the decision model based on the cooking feedback information. The cooking feedback information includes one or more of the following: temperature curve information, fan speed curve information, and user satisfaction feedback information.

[0090] As can be seen, in this embodiment, after the oven acquires multimodal initial parameters such as ingredient type, weight, and initial temperature, it makes intelligent decisions by using lookup tables, a mathematical model based on Fourier's law of heat conduction, and a forced degradation order of a machine learning model. This generates one or more staged cooking strategies, and controls one or more components in the cooking equipment according to these strategies. This allows even users with zero experience to obtain professional-grade, highly consistent, and low-energy-consumption cooked products with any ingredient size or type through a single click, improving the oven's adaptability and intelligence. Furthermore, the decision model can be updated based on cooking feedback, giving the oven self-learning capabilities and continuously optimizing its strategies to ensure it becomes increasingly intelligent.

[0091] Based on the above process of controlling the cooking of ingredients, a device for controlling the cooking of ingredients can be constructed. Figure 4 This is a schematic diagram illustrating the result of a food cooking control device provided in an embodiment of this disclosure, such as... Figure 4 As shown, the food cooking control device 400 includes: a multi-mode acquisition module 410, a strategy determination module 420, and a strategy control module 430.

[0092] The multimodal acquisition module 410 is configured to acquire the current multimodal initial parameters of the food to be cooked, including: food type, food weight, and initial temperature.

[0093] The strategy determination module 420 is configured to determine a current cooking strategy that matches the current multimodal initial parameters through a decision model. The current cooking strategy includes: one or more stage cooking strategies, each stage cooking strategy including: target temperature, duration, cooking mode, stage switching conditions, or one or more of these.

[0094] The strategy control module 430 is configured to control one or more devices to perform cooking operations on the ingredients to be cooked according to the current cooking strategy.

[0095] In some embodiments, the multi-mode acquisition module 410 includes: The first acquisition unit is configured to acquire a current image of the food to be cooked through an image acquisition device, and to obtain a convolutional neural network (CNN) image recognition model through training to identify the current food image and obtain the type of food to be cooked.

[0096] The second acquisition unit is configured to acquire the weight of the ingredients to be cooked through a weight acquisition device.

[0097] The third acquisition unit is configured to acquire the initial temperature of the food to be cooked through a temperature acquisition device.

[0098] In some embodiments, the multi-mode acquisition module 410 further includes: The input acquisition unit is configured to acquire the cooking information of the ingredients to be cooked, which is input by the user.

[0099] In some embodiments, the strategy determination module 420 includes: The first determining unit is configured to determine the current cooking strategy that matches the current multimodal initial parameters based on a saved first decision model, wherein the first decision model includes the correspondence between ingredient type, weight, initial temperature and cooking strategy.

[0100] The second determining unit is configured to determine the current cooking strategy that matches the current multimodal initial parameters based on the saved second decision model, wherein the second decision model is a mathematical model constructed based on the heat conduction equation according to the type and weight of ingredients, initial temperature and target temperature.

[0101] The third determining unit is configured to determine the current cooking strategy that matches the current multimodal initial parameters based on the saved third decision model, wherein the third decision model is a machine learning model trained based on ingredient sample information.

[0102] In some embodiments, the strategy determination module 420 is specifically configured to: if a cooking strategy matching the current multimodal initial parameters is found in the first decision model, determine the found cooking strategy as the current cooking strategy; if no cooking strategy matching the current multimodal initial parameters is found, solve the problem based on the second decision model according to the current multimodal initial parameters, and determine the solution result as the current cooking strategy if the solution result is obtained; if no solution result is obtained, input the current multimodal initial parameters into the third decision model to predict the corresponding current cooking strategy.

[0103] In some embodiments, the policy control module 430 includes: The stage control unit is configured to generate a corresponding current multi-channel PWM control signal for current stage cooking control based on the current stage cooking strategy in the current cooking strategy. The current multi-channel PWM control signal includes one or more of the following: a first current PWM duty cycle for adjusting the heating element for adjusting the upper and lower heating temperatures, a second current PWM duty cycle for adjusting the fan speed of the internal circulation fan of the cooking equipment, and a third current PWM duty cycle for adjusting the steam injection amount of the steam generator.

[0104] The stage switching unit is configured to acquire the current monitoring parameter value in the current stage cooking control, and switch to the next stage cooking strategy when the current stage switching conditions are met based on the current monitoring parameter value. The current monitoring parameter value includes one or more of the following: the current temperature value inside the equipment, the current temperature value at the center of the food, and the current stage cooking duration.

[0105] In some embodiments, it also includes: The feedback update module is configured to obtain cooking feedback information of the ingredients to be cooked and update the decision model based on the cooking feedback information. The cooking feedback information includes one or more of the following: temperature curve information, wind speed curve information, and user satisfaction feedback information.

[0106] The cooking control process of the food ingredient cooking control device provided in the embodiments of the present invention will be illustrated below with reference to specific examples.

[0107] Figure 5 This is a schematic diagram of a food cooking control device provided in an embodiment of this disclosure. Figure 5 As shown, the food cooking control device 400 can be applied to an air fryer. This device includes: a multi-mode acquisition module 410, a strategy determination module 420, a strategy control module 430, and a feedback update module 440. The multi-mode acquisition module 410 includes: a first acquisition unit 411, a second acquisition unit 412, a third acquisition unit 413, and a fourth acquisition unit 414. The air fryer stores a machine learning model trained based on food sample information; therefore, the strategy determination module 420 may include: a third determination unit 423. The strategy control module 430 includes: a stage control unit 431 and a stage switching unit 432.

[0108] In this process, after the food to be cooked is placed inside the air fryer cavity, the first acquisition unit 411 in the multimodal acquisition module 410 acquires the current image of the food to be cooked through an image acquisition device. A convolutional neural network (CNN) image recognition model is then trained to identify the type of food to be cooked. The second acquisition unit 412 acquires the weight of the food to be cooked through a configured weight acquisition device. The third acquisition unit 413 acquires the initial temperature of the food to be cooked through a temperature acquisition device. When the user inputs cooking information via a touchscreen, such as "crispy on the outside and juicy on the inside," the fourth acquisition unit 414 acquires the cooking information of the food to be cooked, thereby obtaining the current multimodal initial parameters of the food to be cooked.

[0109] Thus, the third determining unit 423 in the strategy determining module 420 can determine the current cooking strategy that matches the current multimodal initial parameters based on the third decision model.

[0110] The current cooking strategy may include one, two, or more stages. Therefore, for any given stage cooking strategy, the stage control unit 431 in the strategy control module 430 can generate a corresponding current multi-channel PWM control signal to control the current stage cooking based on the current stage cooking strategy. This current multi-channel PWM control signal includes a first current PWM duty cycle for adjusting the heating temperature of the upper heating element and a second current PWM duty cycle for adjusting the fan speed of the air fryer's internal circulation. The stage switching unit 432 acquires the current monitored parameter values ​​in the current stage cooking control and, based on the current monitored parameter values, determines that the current stage switching conditions are met, switches to the next stage cooking strategy. Thus, the stage control unit 431 continues to control the upper heating element and the fan, while the stage switching unit 432 continues switching until all stages in the current cooking strategy are completed.

[0111] After cooking, the feedback update module 440 can obtain cooking feedback information of the ingredients to be cooked, and update the decision model based on the cooking feedback information. The cooking feedback information includes one or more of the following: temperature curve information, wind speed curve information, and user satisfaction feedback information.

[0112] As can be seen, in this embodiment, after acquiring multimodal initial parameters such as ingredient type, weight, and initial temperature, the device for controlling food cooking uses a machine learning model to make intelligent decisions, generating one or more stage cooking strategies. Based on these stage cooking strategies, it controls one or more components in the cooking equipment. This allows even users with zero experience to obtain professional-grade, highly consistent, and low-energy-consumption cooked products with a single click, regardless of ingredient size or type, thus improving the air fryer's adaptability and intelligence. Furthermore, the decision model can be updated based on cooking feedback, giving the air fryer self-learning capabilities and continuously optimizing its strategies to ensure it becomes increasingly intelligent.

[0113] This disclosure provides a device 600 for controlling the cooking of ingredients, the structure of which is as follows: Figure 6 As shown, it includes: The processor 1000 and memory 1001 may further include a communication interface 1002 and a bus 1003. The processor 1000, communication interface 1002, and memory 1001 can communicate with each other via the bus 1003. The communication interface 1002 can be used for information transmission. The processor 1000 can call logical instructions stored in the memory 1001 to execute the method for controlling food cooking described in the above embodiment.

[0114] Furthermore, the logic instructions in the aforementioned memory 1001 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0115] The memory 1001, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 1000 executes functional applications and data processing by running the program instructions / modules stored in the memory 1001, that is, it implements the method for controlling food cooking in the above method embodiments.

[0116] The memory 1001 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 1001 may include high-speed random access memory and may also include non-volatile memory.

[0117] This disclosure provides a food ingredient cooking control device, including: a processor and a memory storing program instructions, wherein the processor is configured to execute a food ingredient cooking control method when executing the program instructions.

[0118] This disclosure provides a cooking device, such as an oven, air fryer, microwave oven, electric cooker, pressure cooker, etc. Figure 7 As shown, the device includes a main body 700, and the aforementioned device 400 (600) for controlling food cooking is installed within the main body 700. The installation relationship described herein is not limited to placement within the product, but also includes installation connections with other components of the product, including but not limited to physical connections, electrical connections, or signal transmission connections. Those skilled in the art will understand that the device 400 (600) for controlling food cooking can be adapted to suitable corresponding main bodies 700 to achieve other feasible embodiments.

[0119] This disclosure provides a storage medium storing program instructions that, when executed, perform the method for controlling food cooking as described above.

[0120] This disclosure provides a computer program product, which includes a computer program stored on a storage medium. The computer program includes program instructions that, when executed by a computer, cause the computer to perform the data retrieval method described above.

[0121] The aforementioned storage medium can be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0122] The technical solutions of this disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this disclosure. The aforementioned storage medium can be a non-transitory storage medium, including: a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and other media capable of storing program code; it can also be a transient storage medium.

[0123] The foregoing description and accompanying drawings fully illustrate embodiments of the present disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included or replace parts and features of other embodiments. The scope of the embodiments of this disclosure includes the entire scope of the claims and all available equivalents of the claims. While the terms “first,” “second,” etc., may be used in this application to describe elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. For example, a first element may be called a second element without changing the meaning of the description, and similarly, a second element may be called a first element, provided that all occurrences of “first element” are consistently renamed and all occurrences of “second element” are consistently renamed. First and second elements are both elements, but may not be the same element. Moreover, the terminology used in this application is only for describing embodiments and is not intended to limit the claims. As used in the description of the embodiments and claims, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” are intended to also include the plural forms. Similarly, the term “and / or” as used herein means including one or more of the associated listed any and all possible combinations. Additionally, when used herein, the terms “comprise” and its variations “comprises” and / or “comprising” refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase “comprising an…” does not exclude the presence of additional identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0124] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0125] The methods and products disclosed in the embodiments herein (including but not limited to devices and equipment) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to implement this embodiment according to actual needs. In addition, the functional units in the embodiments of this disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0126] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for controlling the cooking of ingredients, characterized in that, include: Obtain the current multimodal initial parameters of the ingredients to be cooked, including: ingredient type, ingredient weight, and initial temperature; The decision model determines the current cooking strategy that matches the current multimodal initial parameters. The current cooking strategy includes one or more stage cooking strategies, and each stage cooking strategy includes one or more of the following: target temperature, duration, cooking mode, and stage switching conditions. Based on the current cooking strategy, control one or more devices to perform the cooking process on the ingredients to be cooked.

2. The method according to claim 1, characterized in that, The acquisition of the current multimodal initial parameters of the ingredients to be cooked includes: The current image of the ingredients to be cooked is acquired through an image acquisition device. A convolutional neural network (CNN) image recognition model is trained to identify the current image of the ingredients and determine the type of ingredients to be cooked. The weight of the ingredients to be cooked is obtained through a weight acquisition device; The initial temperature of the food to be cooked is obtained through a temperature acquisition device.

3. The method according to claim 2, characterized in that, The process of obtaining the current multimodal initial parameters of the ingredients to be cooked also includes: Get the cooking information of the ingredients to be cooked as input by the user.

4. The method according to claim 1, characterized in that, The determination of the current cooking strategy that matches the current multimodal initial parameters includes: Based on the saved first decision model, determine the current cooking strategy that matches the current multimodal initial parameters. The first decision model includes the correspondence between ingredient type, weight, initial temperature, and cooking strategy; or... Based on the saved second decision model, determine the current cooking strategy that matches the current multimodal initial parameters. The second decision model is a mathematical model constructed based on the heat conduction equation, taking into account the type and weight of the ingredients, initial temperature, and target temperature; or... Based on the saved third decision model, the current cooking strategy that matches the current multimodal initial parameters is determined. The third decision model is a machine learning model trained based on the cooking sample information of ingredients.

5. The method according to claim 4, characterized in that, The determination of the current cooking strategy that matches the current multimodal initial parameters also includes: If a cooking strategy matching the current multimodal initial parameters is found in the first decision model, the found cooking strategy is determined as the current cooking strategy. The first decision model is a multidimensional lookup table that includes the correspondence between ingredient type, weight, initial temperature and cooking strategy. If no cooking strategy matching the current multimodal initial parameters is found, the second decision model is used to solve the problem based on the current multimodal initial parameters, and the solution is determined as the current cooking strategy. Without obtaining a solution, the current multimodal initial parameters are input into the third decision model to predict the corresponding current cooking strategy.

6. The method according to claim 1, characterized in that, The control of one or more devices to perform the cooking operation on the ingredients to be cooked includes: Based on the current cooking strategy in the current cooking strategy, a corresponding current multi-channel PWM control signal is generated to control the cooking in the current stage. The current multi-channel PWM control signal includes one or more of the following: a first current PWM duty cycle for adjusting the heating tube for adjusting the upper and lower heating temperatures, a second current PWM duty cycle for adjusting the fan speed of the internal circulation of the cooking equipment, and a third current PWM duty cycle for adjusting the steam injection amount of the steam generator. The current monitoring parameter values ​​in the current stage of cooking control are obtained, and if the current stage switching conditions are met based on the current monitoring parameter values, the stage cooking strategy of the next stage is switched, and the operation control of one or more corresponding devices is performed. The current monitoring parameter values ​​include one or more of the following: the current temperature value inside the device, the current temperature value at the center of the food, and the current stage cooking duration.

7. The method according to any one of claims 1-6, characterized in that, After cooking the ingredients, the process also includes: Obtain cooking feedback information from the ingredients to be cooked, and update the decision model based on the cooking feedback information. The cooking feedback information includes one or more of the following: temperature curve information, wind speed curve information, and user satisfaction feedback information.

8. A device for controlling the cooking of ingredients, the device comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to perform, when executing the program instructions, the method for food ingredient cooking control as described in any one of claims 1-7.

9. A cooking device, characterized in that, include: Equipment body; The device for controlling the cooking of ingredients as described in claim 8 is installed on the main body of the device.

10. A storage medium storing program instructions, characterized in that, When the program instructions are executed, they perform the method for controlling the cooking of ingredients as described in any one of claims 1-7.

Images