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

Abstract

The invention discloses a food material cooking control method and device, equipment and a storage medium. The method comprises the following steps: acquiring a cooking food material image; performing image detection on the cooking food material image by adopting a pre-trained lightweight food material detection model to obtain a food material type and a food material position of at least one target food material output by the model; according to the food material type and the food material position of each target food material, cooking parameters are determined; and executing a corresponding equipment control action based on the cooking parameters to obtain a cooking result. According to the technical scheme, the flexibility of the food material cooking process is improved, effective and accurate identification of the food materials is achieved, accurate determination of the cooking parameters is improved, and therefore the cooking quality is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a food cooking control method, device, equipment and storage medium. Background Art

[0002] With the advancement of science and technology, people's living standards are constantly improving, and their requirements for diet are getting higher and higher. However, for most non-professional chefs, they do not have rich cooking experience. Therefore, how to use modern scientific and technological means to simplify and standardize the cooking control process has become an urgent problem to be solved.

[0003] Existing cooking automation methods usually require users to prepare ingredients and set cooking parameters according to preset recipes. However, this cooking method mostly relies on the cooking parameters pre-configured by the preset recipes, lacking certain flexibility. In addition, it is impossible to effectively and accurately identify the ingredients, resulting in the inability to determine the cooking parameters based on the actual situation of the ingredients, which in turn leads to a decrease in cooking quality. Summary of the invention

[0004] The present invention provides a food cooking control method, device, equipment and storage medium to improve the flexibility of the food cooking process, realize effective and accurate identification of food, improve the accurate determination of cooking parameters, and thus improve cooking quality.

[0005] According to one aspect of the present invention, a method for controlling food cooking is provided, the method comprising:

[0006] Get cooking ingredients images;

[0007] Using a pre-trained lightweight food detection model to perform image detection on the cooking food image, and obtaining the food type and food location of at least one target food output by the model;

[0008] Determining cooking parameters according to the type and location of each target ingredient;

[0009] Corresponding equipment control actions are executed based on the cooking parameters to obtain cooking results.

[0010] According to another aspect of the present invention, a food cooking control device is provided, the device comprising:

[0011] An ingredient image acquisition module, used to acquire cooking ingredient images;

[0012] An image detection module, used to perform image detection on the cooking ingredient image using a pre-trained lightweight ingredient detection model, and obtain an ingredient type and an ingredient location of at least one target ingredient output by the model;

[0013] A cooking parameter determination module, used to determine cooking parameters according to the type and location of each target ingredient;

[0014] The control execution module is used to execute corresponding equipment control actions based on the cooking parameters to obtain cooking results.

[0015] According to another aspect of the present invention, there is provided a cooking device, the cooking device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the food cooking control method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the food cooking control method described in any embodiment of the present invention when executed.

[0020] The technical solution of the present invention comprehensively considers the type and location of ingredients in the process of determining cooking parameters. At the same time, image detection of cooking ingredient images is performed based on a pre-trained lightweight ingredient detection model, thereby achieving effective and accurate identification of ingredients, rather than completely controlling cooking based on cooking parameters corresponding to pre-selected pre-made recipes. This improves the flexibility of the cooking process and the accurate determination of cooking parameters, thereby improving cooking quality.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1A is a flow chart of a food cooking control method provided according to Embodiment 1 of the present invention;

[0024] Figure 1BIt is a structural schematic diagram of a detection network model based on the fusion of the YOLO-V8 model and the CBAM according to the first embodiment of the present invention;

[0025] Figure 2 is a flow chart of a food cooking control method provided according to Embodiment 2 of the present invention;

[0026] Figure 3 is a flow chart of a food cooking control method provided according to Embodiment 3 of the present invention;

[0027] Figure 4 is a flow chart of a food cooking control method provided according to Embodiment 4 of the present invention;

[0028] Figure 5 is a structural schematic diagram of a food cooking control device provided according to Embodiment 5 of the present invention;

[0029] Figure 6 It is a structural schematic diagram of a cooking device for implementing the food cooking control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

[0033] Figure 1AThis is a flow chart of a food cooking control method provided in the first embodiment of the present invention. This embodiment can be applied to the situation where the cooking parameters of the cooking device are accurately determined to control the cooking of the food based on the cooking parameters. The method can be executed by a food cooking control device, which can be implemented in the form of hardware and / or software, and the food cooking control device can be configured in the cooking device. Figure 1A As shown, the method can be performed by a cooking device, and specifically includes:

[0034] S110, acquiring cooking ingredient images.

[0035] S120: Use a pre-trained lightweight ingredient detection model to perform image detection on the cooking ingredient image, and obtain the ingredient type and ingredient location of at least one target ingredient output by the model.

[0036] S130: Determine cooking parameters according to the type and location of each target ingredient.

[0037] S140: Execute corresponding equipment control actions based on the cooking parameters to obtain cooking results.

[0038] The cooking ingredient image can be captured by an image acquisition device deployed in the cooking device. The image acquisition device is located directly above the cavity of the cooking device, and is used to capture images of the ingredients placed directly below its own position when the placement action of the ingredient plate is detected. For example, the cooking device may be a steam oven, and the image acquisition device may be a camera; the image acquisition device may remain in standby mode under normal circumstances, and when the placement action of the ingredients is detected, the image acquisition device captures images of the ingredients placed in the cooking device to obtain cooking ingredient images.

[0039] The lightweight food detection model can be pre-trained by relevant technicians and pre-deployed in the cooking equipment; the lightweight food cooking model occupies less memory and has relatively low detection accuracy. The lightweight food detection model is used to predict the type and location of food in the cooking food image.

[0040] Specifically, the cooking ingredient images captured by the image acquisition device are input into a pre-trained lightweight ingredient detection model, and the lightweight ingredient detection model predicts the type and location of ingredients in the cooking ingredient images to obtain the type and location of at least one target ingredient output by the model.

[0041] Based on the type of target ingredients and the position of the ingredients, the cooking parameters are determined. Specifically, the cooking parameters may include cooking temperature, cooking humidity, cooking time, and the heating power of the heating tube. Different types of ingredients may correspond to different cooking temperatures, cooking humidity, and cooking times, and the mapping relationship may be pre-set by relevant technical personnel according to actual needs. Different positions of ingredients correspond to different heating powers of heating tubes, and the mapping relationship may be pre-set by relevant technical personnel according to actual needs. It should be noted that the position of the ingredients is the relative position of the ingredients relative to the internal cavity of the cooking device. A plurality of heating tubes located at different positions are arranged around the cavity of the cooking device. According to the position of the ingredients, the heating power of different heating tubes can be adaptively adjusted, and the mapping relationship between the specific position of the ingredients and the heating power of the specific heating tubes can be pre-set according to actual experience values ​​or experimental values.

[0042] The cooking device executes corresponding device control actions based on the determined cooking parameters, obtains the cooking results, and displays the cooking results to the initiator of the food cooking.

[0043] The technical solution of the present invention comprehensively considers the type and location of ingredients in the process of determining cooking parameters. At the same time, image detection of cooking ingredient images is performed based on a pre-trained lightweight ingredient detection model, thereby achieving effective and accurate identification of ingredients, rather than completely controlling cooking based on cooking parameters corresponding to pre-selected pre-made recipes. This improves the flexibility of the cooking process and the accurate determination of cooking parameters, thereby improving cooking quality.

[0044] The present embodiment also provides a model training method for a lightweight food detection model, including: obtaining food sample images of different food in different cooking devices, and marking the food types and food positions in the food sample images to obtain food sample images with labels of standard food types and standard food positions; using the food sample images to perform model training on a pre-built detection network model to obtain a trained target food detection model; performing model quantization processing on the target food detection model to obtain a lightweight food detection model.

[0045] In order to ensure the richness and diversity of the food sample images, and thus ensure that the trained lightweight food detection model can take into account the image detection of different ingredients under different types of cooking equipment, in the process of constructing the food sample images, the same and different food images under different cooking equipment are selected as food sample images.

[0046] The positions and types of ingredients in the food sample images are annotated to generate sample labels. The positions of ingredients are reflected in the food sample images in the form of detection frames, including the relative position coordinates of the detection frames. Manual, automated or semi-automated annotation methods can be used, and the label value of the food sample image obtained is the true value of the sample.

[0047] Exemplarily, a food sample image marked with standard food types and standard food locations is input into a pre-built detection network model to obtain the predicted food types and predicted food locations output by the model. The detection network model may be a YOLO series model (a deep learning model for real-time object detection) and SSD (Single Shot MultiBox Detector), etc.

[0048] According to the standard food type, standard food location, predicted food type and predicted food location, based on the preset loss function, the loss value is determined; the detection network model is trained according to the loss value until the model training end condition is met, and the target food detection model that has completed the training is obtained. Among them, the model training end condition can be that the loss value tends to be stable or the loss value reaches a set loss threshold or the number of iterations reaches a set number of iterations threshold, etc., which is not limited in this embodiment.

[0049] The target food detection model is quantized, which may be performed by model pruning, post-training quantization, or low-rank decomposition, thereby reducing the storage size, computational complexity, and memory usage of the model while maintaining the performance of the model as much as possible to obtain a lightweight food detection model.

[0050] In order to further improve the recognition accuracy of cooking ingredient images, this embodiment adopts a method of combining the YOLO-V8 model with the CBAM (Convolutional Block Attention Module) to obtain a detection network model.

[0051] In an optional embodiment, the model structure of the detection network model includes a YOLO-V8 network module and a convolutional block attention module (CBAM). The YOLO-V8 network module includes a backbone network, a neck network, and a detection head. Figure 1B A structural diagram of a detection network model based on the fusion of the YOLO-V8 model and the CBAM is shown. The input end of the convolutional block attention module (CBAM) is connected to the output end of the backbone network; the output end of the convolutional block attention module (CBAM) is connected to the input end of the neck network.

[0052] Correspondingly, a detection network model pre-constructed with food sample images is used for model training to obtain a trained target food detection model, including: inputting the food sample image into the backbone network of the YOLO-V8 network module for feature extraction to obtain a multi-scale feature map; inputting the multi-scale feature map into the convolution block attention module for feature map weighting processing to obtain a weighted feature map; inputting the weighted feature map into the neck network of the YOLO-V8 network module for feature map fusion processing to obtain a fused feature map; inputting the fused feature map into the detection head of the YOLO-V8 network module for feature processing to obtain predicted food types and predicted food positions; and training the detection network model according to the standard food types, standard food positions, predicted food types and predicted food positions of the food sample images until the model training end conditions are met to obtain the target food detection model.

[0053] The model parameters required for the model training process can be pre-set according to actual needs. For example, the batch size is set to 16, the workers (the number of parallel processes for data loading) is set to 8, the optimizer (stochastic gradient descent optimizer) is selected as SGD, the image size of the food sample image is 640 pixels × 640 pixels, the learning rate is set to 0.01, and the maximum number of iterations is set to 1000 steps.

[0054] The food sample image is input into the backbone network of the YOLO-V8 network module, and the backbone network extracts low-order (edge / texture) to high-order features (semantics) to obtain multi-scale features. The multi-scale feature map is input into the convolutional block attention module (CBAM) for feature map weighting processing to obtain a weighted feature map. Specifically, the weighted feature map is processed by the channel attention module (CAM) in the CBAM, and the feature map of each channel is weighted to obtain the channel attention weight, and the channel attention weight is multiplied by the weighted feature map channel by channel to obtain the feature map after channel attention adjustment. The feature map after channel attention adjustment is input into the spatial attention module (SAM), and the adjusted feature map is processed by the spatial attention module (SAM) in the CBAM, and the feature map of each spatial position is weighted to obtain the spatial attention weight, and the spatial attention weight is multiplied by the adjusted feature map channel by channel to obtain the weighted feature map. The weighted feature map is input into the neck network of the YOLO-V8 network module for feature map fusion processing, which fuses high-level semantic features and transmits the underlying positioning information to obtain a fused fusion feature map. The fused feature map is input into the detection head of the YOLO-V8 network module to predict the type and location of the food, and the predicted type and location of the food are obtained.

[0055] According to the standard food type, standard food position, predicted food type and predicted food position of the food sample image, based on the preset loss function, the loss value is determined; the detection network model is trained according to the loss value until the model training end condition is met, and the target food detection model that has completed the training is obtained. Among them, the model training end condition can be that the loss value tends to be stable or the loss value reaches a set loss threshold or the number of iterations reaches a set number of iterations threshold, etc., which is not limited in this embodiment.

[0056] The above technical solution uses the model that integrates the YOLO network model and the CBAM mechanism as the detection network model, and the YOLO-V8 network model can achieve ideal results in the target detection task. However, in the process of identifying and detecting food sample images, the YOLO-V8 network model has errors in the recognition results due to the influence of lighting in the cooking equipment and the superposition of some foods, and its recognition results will also have a serious impact on the final cooking parameters, resulting in some foods not being able to achieve the best steaming and baking results. Therefore, the CBAM attention mechanism is added to the original YOLO-V8 network model, so that the model pays more attention to the foreground and target area of ​​the image during training, while SAM pays attention to the position rich in contextual information during network training. The addition of the CBAM attention mechanism can increase the weight of the food feature area and reduce the background feature weight when the network performs feature learning, so that the model pays more attention to the target to be detected, improves the situation of false detection and missed detection in the image, improves the accuracy of food detection, and further realizes the effective and accurate identification of ingredients, improves the accurate determination of cooking parameters, and thus improves the cooking quality.

[0057] Embodiment 2

[0058] Figure 2 This is a flow chart of a food cooking control method provided in Example 2 of the present invention. This embodiment is optimized and improved on the basis of the above technical solutions.

[0059] Furthermore, before the step of "using a pre-trained lightweight ingredient detection model to perform image detection on the cooking ingredient image, and obtain the ingredient type and ingredient location of at least one target ingredient output by the model", after the step of "obtaining the cooking ingredient image", add the step of "monitoring the network status of the server to obtain the current network status information; based on the current network status information, determine whether to use a pre-trained lightweight ingredient detection model to perform image detection on the cooking ingredient image; if not, send the cooking ingredient image to the server, so that the server can perform image detection on the cooking ingredient image based on its own locally deployed pre-trained target ingredient detection model, obtain the ingredient type and ingredient location of at least one target ingredient output by the model, and feedback the ingredient type and ingredient location of the target ingredient to the cooking device; if so, execute the pre-trained lightweight ingredient detection model to perform image detection on the cooking ingredient image, and obtain the ingredient type and ingredient location of at least one target ingredient output by the model." to improve the execution method of the ingredient image recognition task.

[0060] It should be noted that for the parts not described in detail in the embodiments of the present invention, reference can be made to the descriptions of other embodiments. Figure 2 As shown, the method comprises the following specific steps:

[0061] S210: Acquire cooking ingredient images.

[0062] S220: Monitor the network status of the server to obtain current network status information.

[0063] S230. According to the current network status information, determine whether to use the pre-trained lightweight ingredient detection model to perform image detection on the cooking ingredient image; if so, execute S240A; if not, execute S240B.

[0064] S240A: Use a pre-trained lightweight ingredient detection model to perform image detection on the cooking ingredient image, and obtain the ingredient type and ingredient location of at least one target ingredient output by the model.

[0065] S240B, sending the cooking ingredient image to the server, so that the server can perform image detection on the cooking ingredient image based on its locally deployed pre-trained target ingredient detection model, obtain the ingredient type and ingredient location of at least one target ingredient output by the model, and feedback the ingredient type and ingredient location of the target ingredient to the cooking device.

[0066] S250: Determine cooking parameters according to the type and location of each target ingredient.

[0067] S260: Execute corresponding equipment control actions based on the cooking parameters to obtain cooking results.

[0068] The current network status information may include parameter information such as network speed, network delay, network jitter, and packet loss rate. The network status information can comprehensively evaluate the network status or network quality of the device or server. The server may be a cloud server.

[0069] According to the current network status information of the server, it can be determined whether the subject of image detection is the server or the cooking device (mobile terminal). Specifically, the current network status information can be detected by using a pre-trained network quality detection model to obtain the network quality output by the model, which can be a quality category, including high network quality, high quality, medium quality, low quality and low quality; or, it can be a specific quality score, the interval can be set to 0~100, the higher the score, the higher the network quality; the lower the score, the lower the network quality.

[0070] The model training method of the network quality detection model with quality category as the output result can be: obtaining the historical network status in the historical time period as the sample training data, and determining the standard classification results corresponding to each historical network status as the sample label of the corresponding sample training data. The pre-built classification network model is trained using the sample training data and its corresponding standard classification results to obtain a trained network quality detection model. The classification network model can be a machine learning model or a neural network model, for example, the classification network model can be a decision tree, a random forest or a convolutional neural network.

[0071] It should be noted that the target ingredient detection model is deployed in the server, and the target ingredient detection model has higher performance and higher accuracy in identifying ingredients than the lightweight ingredient detection model deployed by the cooking device (mobile terminal). However, compared with the mobile terminal, the server model is more affected by network delay. Therefore, when it is detected that the network quality of the server is high, the server performs image detection on the cooking ingredient image based on the target ingredient detection model with higher performance deployed by itself, and feeds back the detected target ingredient type and location to the cooking device. When it is detected that the network quality of the server is low, the cooking device (mobile terminal) performs image detection on the cooking ingredient image based on the lightweight ingredient detection model deployed by itself, and obtains the ingredient type and location of at least one target ingredient output by the model.

[0072] Furthermore, when the network quality is poor, the cooking user is clearly prompted to use the lightweight ingredient detection model deployed on the mobile terminal for identification, and is prompted that the model identification accuracy is relatively low. At the same time, the cooking user is provided with an option to manually switch the identification execution entity according to actual needs and network status.

[0073] Furthermore, if the cooking ingredient images are recognized based on the mobile terminal, it can be prompted to check that the network is restored and then selectively re-upload the cooking ingredient images to the server for verification to provide a more accurate recognition result.

[0074] Furthermore, this embodiment also provides a method for selecting an image recognition subject. Obtain historical network status information under historical periods and its corresponding user behavior patterns. Among them, the user behavior pattern is the identification subject (server or mobile terminal) selected under the historical network status information. Input the historical network status information and the user behavior pattern into a preset classification model to obtain a predicted behavior pattern output by the model. Train the classification model according to the user behavior pattern and the predicted behavior model to obtain a trained behavior pattern prediction model. Input the current network status information of the mobile terminal and / or the current network status information of the server in the current time period into the behavior pattern prediction model to obtain the target behavior pattern output by the model, including the server or the mobile terminal.

[0075] The technical solution of this embodiment obtains the current network status information by monitoring the network status of the server; based on the current network status information, the execution subject for image detection of cooking ingredient images is determined, thereby realizing dynamic determination of the execution subject, taking into account multiple factors such as network status and model performance, improving the flexibility of image detection, and better meeting the needs of actual image detection scenarios.

[0076] Embodiment 3

[0077] Figure 3 This is a flow chart of a food cooking control method provided in Example 3 of the present invention. This embodiment is optimized and improved on the basis of the above technical solutions.

[0078] Further, the step of "determining cooking parameters according to the type and location of each target ingredient" is refined into "determining the ingredient properties of each target ingredient according to the type of each target ingredient; determining cooking parameters according to the ingredient properties and location of each target ingredient." to improve the method of determining cooking parameters.

[0079] It should be noted that for the parts not described in detail in the embodiments of the present invention, reference can be made to the descriptions of other embodiments. Figure 3 As shown, the method comprises the following specific steps:

[0080] S310: Acquire cooking ingredient images.

[0081] S320: Use a pre-trained lightweight ingredient detection model to perform image detection on the cooking ingredient image, and obtain the ingredient type and ingredient location of at least one target ingredient output by the model.

[0082] S330: Determine the ingredient properties of each target ingredient according to the ingredient type of each target ingredient.

[0083] S340: Determine cooking parameters according to the ingredient properties and ingredient positions of each target ingredient.

[0084] S350: Execute corresponding equipment control actions based on the cooking parameters to obtain cooking results.

[0085] Among them, the food attributes may include food taste, nutritional value and cooking difficulty, etc. Different types of food have different food attributes. The mapping relationship between food attributes and food types can be pre-established and stored by relevant technical personnel.

[0086] Among them, the association between ingredient attributes, ingredient locations and cooking parameters can also be pre-established and stored by relevant technical personnel.

[0087] To further improve the accuracy of determining the cooking parameters, in an optional embodiment, the cooking parameters are determined according to the ingredient properties and ingredient position of each target ingredient, including: determining the target cooking temperature and the target cooking time according to the ingredient properties of each target ingredient; determining the heating weight parameters of each heating tube deployed in the cooking device according to the ingredient position of each target ingredient; and generating cooking parameters including the target cooking temperature, the target cooking time and the heating weight parameters of the heating tube.

[0088] It should be noted that different food attributes may correspond to different cooking temperatures and cooking times. Specifically, a first mapping relationship table between food attributes and cooking temperatures is pre-established and stored, and a second mapping relationship table between food attributes and cooking times is pre-established and stored. After the food attributes of the target food are determined, the target cooking temperature corresponding to the target food can be determined based on the first mapping relationship table; and the target cooking time corresponding to the target food can be determined based on the second mapping relationship table.

[0089] Since there are multiple heating tubes in the cavity of the cooking device, for any heating tube, when the food is close to the heating tube, the heating tube should be set to a lower heating power; when the food is far from the heating tube, the heating tube should be set to a higher heating power. Therefore, the setting of the heating power of different heating tubes is related to the position of the food in the cavity.

[0090] Among them, the heating weight parameter of the heating tube can be the power weight corresponding to the heating power of the heating tube. When the distance between the food and the heating tube is close, the corresponding power weight is low; when the distance between the food and the heating tube is far, the corresponding power weight is high.

[0091] For example, if there are heating tubes A, B, and C, according to the position of the food, it can be known that the distance between the target food and heating tube A is a, the distance between the target food and heating tube B is b, and the distance between the target food and heating tube C is c, and the distance a is greater than the distance b and greater than the distance c. Accordingly, the heating weight parameter of the heating tube A is set to be greater than the heating weight parameter of the heating tube B and greater than the heating weight parameter of the heating tube C.

[0092] It is understandable that the number of identified target ingredients may be one or more. When the number of target ingredients is multiple, and the cooking parameters corresponding to each target ingredient are different, the target ingredient with the larger cooking parameter setting is selected as the final cooking parameter. Exemplarily, if there is a target ingredient A with a cooking temperature of Ca, a cooking time of Ta, and a heating weight parameter Wa for the heating tube; and a target ingredient B with a cooking temperature of Cb, a cooking time of Tb, and a heating weight parameter Wb for the heating tube. The larger value of the cooking temperature Ca and the cooking temperature Cb is used as the final target cooking temperature. The larger value of the cooking time Ta and the cooking time Tb is used as the final target cooking time. Compare and extract the maximum values ​​of the heating weight parameters corresponding to each heating tube in the heating weight parameter Wa and the heating weight parameter Wb of the heating tube, and generate a new heating weight parameter Wc for the heating tube as the final heating weight parameter of the heating tube.

[0093] The above embodiment improves the accuracy of determining the cooking parameters by considering the food properties and food positions in the process of determining the cooking parameters and determining the heating weight parameters of the heating tubes based on the positional relationship between the food positions and the heating tubes.

[0094] It should be noted that due to the different altitudes, air pressures and boiling points in different regions, the temperature and time required for the food to be fully cooked also vary to a certain extent. Therefore, this embodiment also provides a temperature and time automatic compensation method to improve the accuracy of determining the cooking temperature and cooking time of the food.

[0095] In an optional embodiment, the target cooking temperature and the target cooking time are determined according to the ingredient properties of each target ingredient, including: determining the initial cooking temperature and the initial cooking time according to the ingredient properties of each target ingredient; determining the geographic location parameter information according to the communication address information of its own device; determining the temperature compensation parameter and the time compensation parameter according to the geographic location parameter information; determining the target cooking temperature according to the temperature compensation parameter and the initial cooking temperature; and determining the target cooking time according to the time compensation parameter and the initial cooking time.

[0096] Among them, the geographic location parameter information may include the region to which the device belongs, and the altitude, air pressure and boiling point corresponding to the region. Different geographic location parameter information corresponds to different temperature compensation parameters and time compensation parameters, which can be determined based on a preset mapping relationship table. The mapping relationship table can be pre-generated and stored locally. Alternatively, it can also be predicted based on a pre-trained parameter compensation model, specifically, the pre-built network model can be trained using historical geographic location parameter information to obtain a prediction network model for predicting temperature parameter compensation and time parameter compensation.

[0097] It should be noted that in order to further improve the efficiency of determining the compensation parameters, the execution subject of the above-mentioned determination of the time compensation parameters and the temperature compensation parameters can be executed by the server (cloud). Specifically, the cooking device (mobile terminal) uploads the communication address information of its own device to the server according to its own networking module. The server converts the communication address information of the mobile terminal into a regional address to obtain the corresponding mobile terminal's region. According to the region to which the mobile terminal belongs, the altitude parameter mapping table is queried to obtain the temperature compensation parameters and time compensation parameters of the region to which the mobile terminal belongs. Among them, the altitude parameter mapping table is pre-constructed by the cloud and stored locally, which records the altitude, boiling point, air pressure, temperature compensation parameters and time compensation parameters of different regions. The mobile terminal feeds back the determined temperature compensation parameters and time compensation parameters to the cooking device (mobile terminal), and the cooking device determines the target cooking temperature according to the temperature compensation parameters and the initial cooking temperature; and determines the target cooking time according to the time compensation parameters and the initial cooking time.

[0098] The above technical solution reduces the error in determining the target cooking time and target cooking temperature and improves the accuracy of determining the target cooking time and target cooking temperature by determining the temperature compensation parameters and time compensation parameters based on the geographical location information of the cooking equipment, thereby ensuring that the ingredients can be fully cooked.

[0099] Embodiment 4

[0100] Figure 4 This is a flowchart of a food cooking control method provided in Embodiment 4 of the present invention. This embodiment provides a preferred example based on the above embodiment. This embodiment uses the cloud as the server end and the cooking device as the mobile end. Figure 4 As shown, the method comprises the following specific steps:

[0101] This embodiment adopts a deep learning framework based on Pytoch, and uses a model that integrates the YOLO-V8 model structure and the CBAM (convolutional block attention module) structure as the basic training model, that is, the detection network model. The specific structure of the detection network model includes a YOLO-V8 network module and a CBAM. The YOLO-V8 network module includes a backbone network, a neck network, and a detection head; wherein the input end of the CBAM is connected to the output end of the backbone network; and the output end of the CBAM is connected to the input end of the neck network. Specifically, the model training method of the target food detection model used for food image target recognition and category detection is as follows:

[0102] Obtain food sample images of different ingredients in different cooking equipment, and annotate the food types and food positions in the food sample images to obtain food sample images with labels of standard food types and standard food positions. Input the food sample images into the backbone network of the YOLO-V8 network module for feature extraction to obtain a multi-scale feature map; input the multi-scale feature map into the convolutional block attention module for feature map weighting processing to obtain a weighted feature map; input the weighted feature map into the neck network of the YOLO-V8 network module for feature map fusion processing to obtain a fused feature map; input the fused feature map into the detection head of the YOLO-V8 network module for feature processing to obtain predicted food types and predicted food positions; train the detection network model according to the standard food types, standard food positions, predicted food types and predicted food positions of the food sample images until the model training end conditions are met to obtain the target food detection model.

[0103] The target food detection model is deployed on the server side, and the target food detection model is lightweighted to obtain a lightweight food detection model, and the lightweight food detection model is deployed on the mobile side. The server side can make full use of the high performance of the model to identify food, but the model is easily affected by network delays, etc.; while the model detection accuracy of the lightweight model on the mobile side is relatively low, but it is not easily affected by network delays.

[0104] Therefore, this embodiment also provides an intelligent decision-making method for the execution location of image recognition of cooking ingredient images, thereby realizing dynamic identification of the execution location of the ingredient image detection task. Specifically, the network status of the server and the network status of the mobile terminal are monitored respectively to obtain the current network status of the server and the current network status of the mobile terminal. According to the current network status of the server and the current network status of the mobile terminal, the network quality of the server and the network quality of the mobile terminal are determined respectively; according to the network quality of the server and the network quality of the mobile terminal, the execution location of the ingredient image detection task is determined.

[0105] Specifically, based on machine learning or deep learning technology, classification model training can be performed by learning user behavior patterns in historical time periods (the selection results of executing food image detection tasks on the server or mobile terminal) and the network status under the user behavior pattern, so as to obtain a trained behavior pattern network model for determining the execution location of the mobile terminal or server.

[0106] When the network condition is poor, the user can be clearly prompted that the lightweight food detection model on the mobile terminal will be used for identification, and informed that the recognition accuracy may decrease. At the same time, the user is provided with the option to manually switch the recognition mode according to actual needs and network conditions. If the mobile terminal recognition is inaccurate, it can be prompted to check the network and selectively re-upload the cooking detection image to the server for verification after the network is restored to provide more accurate results. For images that are misidentified, a correction mechanism is provided to allow users to manually correct or re-identify.

[0107] If executed on a mobile terminal, a pre-trained lightweight food detection model is used to perform image detection on the cooking food image, and the food type and food location of at least one target food output by the model are obtained. If executed on a server terminal, a pre-trained target food detection model is used to perform image detection on the cooking food image, and the food type and food location of at least one target food output by the model are obtained, and the food type and food location are fed back to the mobile terminal.

[0108] The mobile terminal determines the food attributes of each target food according to the food type of each target food. Among them, the food attributes may include food taste, nutritional value and cooking difficulty. The mapping relationship between the food type and the corresponding food attribute can be pre-generated by relevant technical personnel and stored locally in the form of a mapping relationship database table.

[0109] According to the food properties of each target food, the cooking temperature and cooking time are determined. Among them, different food properties correspond to the same or different cooking temperatures and cooking times. According to the food position of each target food, the heating weight parameter of each heating tube deployed in the cooking device is determined. Since there are multiple heating tubes in the cavity of the cooking device, for any heating tube, when the food is close to the position of the heating tube, the heating tube should be set with a lower heating power; when the food is far away from the position of the heating tube, the heating tube should be set with a higher heating power. Therefore, the setting of the heating power of different heating tubes is related to the food position of the food in the cavity. Among them, the heating weight parameter of the heating tube can be the power weight corresponding to the heating power of the heating tube. When the distance between the food and the heating tube is close, the corresponding power weight is low; when the distance between the food and the heating tube is far, the corresponding power weight is high.

[0110] Due to the different altitudes, air pressures, and boiling points across the country, the temperature and time required for food to be fully cooked vary. Therefore, the cooking temperature and cooking time are compensated based on the automatic compensation algorithm on the server side, and the compensated parameters are sent to the mobile side. Specifically, the mobile side sends the communication address information of its own device to the server side, and the server side converts the communication address information of the mobile side into regional address information, and determines the geographical location parameter information of the area to which the regional address information belongs by table lookup; based on the geographical location parameter information, determine the temperature compensation parameter and time compensation parameter, which can be implemented by table lookup. Perform temperature compensation on the cooking temperature according to the temperature compensation parameter to obtain the target cooking temperature; and perform time compensation on the cooking time according to the time compensation parameter to obtain the target cooking time. Generate cooking parameters including target cooking temperature, target cooking time, and heating weight parameters of the heating tube.

[0111] Embodiment 5

[0112] Figure 5 The present invention provides a structural diagram of a food cooking control device provided in Embodiment 5. The food cooking control device provided in the embodiment of the present invention can be used to accurately determine the cooking parameters of the cooking equipment so as to control the cooking of the food based on the cooking parameters. The food cooking control device can be implemented in the form of hardware and / or software, such as Figure 5 As shown, the device specifically includes: a food image acquisition module 501, an image detection module 502, a cooking parameter determination module 503 and a control execution module 504.

[0113] The food image acquisition module 501 is used to acquire cooking food images;

[0114] An image detection module 502 is used to perform image detection on the cooking ingredient image using a pre-trained lightweight ingredient detection model to obtain an ingredient type and an ingredient location of at least one target ingredient output by the model;

[0115] A cooking parameter determination module 503, for determining cooking parameters according to the type and location of each target ingredient;

[0116] The control execution module 504 is used to execute corresponding equipment control actions based on the cooking parameters to obtain cooking results.

[0117] The technical solution of the present invention comprehensively considers the type and location of ingredients in the process of determining cooking parameters. At the same time, image detection of cooking ingredient images is performed based on a pre-trained lightweight ingredient detection model, thereby achieving effective and accurate identification of ingredients, rather than completely controlling cooking based on cooking parameters corresponding to pre-selected pre-made recipes. This improves the flexibility of the cooking process and the accurate determination of cooking parameters, thereby improving cooking quality.

[0118] Optionally, the device further includes a model training module; the model training module includes:

[0119] An ingredient sample image acquisition unit is used to acquire ingredient sample images of different ingredients in different cooking devices, and to mark the ingredient types and positions in the ingredient sample images to obtain ingredient sample images with labels of standard ingredient types and standard ingredient positions;

[0120] A model training unit, used to perform model training on a pre-built detection network model using the food sample image to obtain a trained target food detection model;

[0121] The model quantization processing unit is used to perform model quantization processing on the target food detection model to obtain a lightweight food detection model.

[0122] Optionally, the model structure of the detection network model includes a YOLO-V8 network module and a convolutional block attention module; the YOLO-V8 network module includes a backbone network, a neck network and a detection head; wherein the input end of the convolutional block attention module is connected to the output end of the backbone network; the output end of the convolutional block attention module is connected to the input end of the neck network; accordingly, the model training unit is specifically used for:

[0123] Input the food sample image into the backbone network of the YOLO-V8 network module for feature extraction to obtain a multi-scale feature map;

[0124] Inputting the multi-scale feature map into the convolution block attention module for feature map weighting processing to obtain a weighted feature map;

[0125] Inputting the weighted feature map into the neck network of the YOLO-V8 network module to perform feature map fusion processing to obtain a fused feature map;

[0126] Input the fused feature map into the detection head of the YOLO-V8 network module for feature processing to obtain the predicted food type and predicted food location;

[0127] The detection network model is trained according to the standard food type, standard food position, predicted food type and predicted food position of the food sample image until the model training end condition is met to obtain a target food detection model.

[0128] Optionally, the device further comprises:

[0129] A network status detection module, configured to monitor the network status of the server to obtain current network status information before performing image detection on the cooking ingredient image using the pre-trained lightweight ingredient detection model to obtain the ingredient type and ingredient location of at least one target ingredient output by the model;

[0130] An image detection judgment module, used to judge whether to use a pre-trained lightweight food detection model to perform image detection on the cooking food image according to the current network status information;

[0131] a server-side detection module, for, if the pre-trained lightweight food detection model is not used to perform image detection on the cooking food image, sending the cooking food image to the server, so that the server can perform image detection on the cooking food image based on its own locally deployed pre-trained target food detection model, obtain the food type and food location of at least one target food output by the model, and feed back the food type and food location of the target food to the cooking device;

[0132] The mobile terminal detection module is used to execute the image detection of the cooking ingredient image using the pre-trained lightweight ingredient detection model if the pre-trained lightweight ingredient detection model is used to perform image detection on the cooking ingredient image, and obtain the ingredient type and ingredient location of at least one target ingredient output by the model.

[0133] Optionally, the cooking parameter determination module 503 includes:

[0134] An ingredient attribute determination unit, used to determine the ingredient attribute of each of the target ingredients according to the ingredient type of each of the target ingredients;

[0135] The cooking parameter determination unit is used to determine the cooking parameters according to the ingredient properties and ingredient positions of each of the target ingredients.

[0136] Optionally, the cooking parameter determination unit comprises:

[0137] A target parameter determination subunit, used to determine a target cooking temperature and a target cooking time according to the food properties of each of the target food ingredients;

[0138] a heating weight determination subunit, configured to determine a heating weight parameter of each heating tube deployed in the cooking device according to the food position of each target food;

[0139] The cooking parameter determination subunit is used to generate cooking parameters including a target cooking temperature, a target cooking time and a heating weight parameter of the heating tube.

[0140] Optionally, the target parameter determination subunit is used to:

[0141] Determining an initial cooking temperature and an initial cooking time according to the food properties of each of the target food ingredients;

[0142] Determine geographic location parameter information based on the communication address information of its own device;

[0143] Determining temperature compensation parameters and time compensation parameters according to the geographic location parameter information;

[0144] determining a target cooking temperature according to the temperature compensation parameter and the initial cooking temperature; and,

[0145] A target cooking time is determined according to the time compensation parameter and the initial cooking time.

[0146] The food cooking control device provided in the embodiment of the present invention can execute the food cooking control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0147] Embodiment 6

[0148] Figure 6 A schematic diagram of a cooking device 60 that can be used to implement an embodiment of the present invention is shown. The cooking device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The cooking device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0149] like Figure 6As shown, the cooking device 60 includes at least one processor 61, and a memory connected to the at least one processor 61, such as a read-only memory (ROM) 62, a random access memory (RAM) 63, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 61 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 62 or the computer program loaded from the storage unit 68 to the random access memory (RAM) 63. In the RAM 63, various programs and data required for the operation of the cooking device 60 can also be stored. The processor 61, the ROM 62, and the RAM 63 are connected to each other through a bus 64. An input / output (I / O) interface 65 is also connected to the bus 64.

[0150] A number of components in the cooking device 60 are connected to the I / O interface 65, including: an input unit 66, such as a keyboard, a mouse, etc.; an output unit 67, such as various types of displays, speakers, etc.; a storage unit 68, such as a disk, an optical disk, etc.; and a communication unit 69, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 69 allows the cooking device 60 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0151] The processor 61 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 61 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 61 executes the various methods and processes described above, such as the food cooking control method.

[0152] In some embodiments, the food cooking control method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 68. In some embodiments, part or all of the computer program can be loaded and / or installed on the cooking device 60 via the ROM 62 and / or the communication unit 69. When the computer program is loaded into the RAM 63 and executed by the processor 61, one or more steps of the food cooking control method described above can be performed. Alternatively, in other embodiments, the processor 61 can be configured to execute the food cooking control method in any other suitable manner (e.g., by means of firmware).

[0153] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0154] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0155] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0156] To provide interaction with a user, the systems and techniques described herein may be implemented on a cooking device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the cooking device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0157] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0158] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0159] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0160] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A food cooking control method, characterized in that: include: Get cooking ingredients images; Using a pre-trained lightweight food detection model to perform image detection on the cooking food image, and obtaining the food type and food location of at least one target food output by the model; Determining cooking parameters according to the type and location of each target ingredient; Corresponding equipment control actions are executed based on the cooking parameters to obtain cooking results.

2. The food cooking control method according to claim 1, characterized in that: The model training method of the lightweight food detection model is as follows: Obtaining food sample images of different food materials in different cooking devices, and marking the types and locations of food materials in the food sample images to obtain food sample images with labels of standard food types and standard food locations; Using the food sample image to perform model training on a pre-built detection network model to obtain a trained target food detection model; The target food detection model is subjected to model quantization processing to obtain a lightweight food detection model.

3. The food cooking control method according to claim 2, characterized in that: The model structure of the detection network model includes a YOLO-V8 network module and a convolutional block attention module; the YOLO-V8 network module includes a backbone network, a neck network and a detection head; wherein the input end of the convolutional block attention module is connected to the output end of the backbone network; the output end of the convolutional block attention module is connected to the input end of the neck network; Accordingly, the method of using the food sample image to perform model training on a pre-built detection network model to obtain a trained target food detection model includes: Input the food sample image into the backbone network of the YOLO-V8 network module for feature extraction to obtain a multi-scale feature map; Inputting the multi-scale feature map into the convolution block attention module for feature map weighting processing to obtain a weighted feature map; Inputting the weighted feature map into the neck network of the YOLO-V8 network module to perform feature map fusion processing to obtain a fused feature map; Input the fused feature map into the detection head of the YOLO-V8 network module for feature processing to obtain the predicted food type and predicted food location; The detection network model is trained according to the standard food type, standard food position, predicted food type and predicted food position of the food sample image until the model training end condition is met to obtain a target food detection model.

4. The food cooking control method according to claim 1, characterized in that: Before the pre-trained lightweight food detection model is used to perform image detection on the cooking food image to obtain the food type and food location of at least one target food output by the model, the method further includes: Monitor the network status of the server and obtain the current network status information; According to the current network status information, determining whether to use a pre-trained lightweight food detection model to perform image detection on the cooking food image; If not, the cooking ingredient image is sent to the server, so that the server can perform image detection on the cooking ingredient image based on a pre-trained target ingredient detection model locally deployed by the server, obtain the ingredient type and ingredient location of at least one target ingredient output by the model, and feed back the ingredient type and ingredient location of the target ingredient to the cooking device; If so, the pre-trained lightweight food detection model is used to perform image detection on the cooking food image to obtain the food type and food location of at least one target food output by the model.

5. The food cooking control method according to claim 1, characterized in that: The step of determining the cooking parameters according to the type and location of each target ingredient includes: Determining the food properties of each of the target foods according to the food types of each of the target foods; The cooking parameters are determined according to the ingredient properties and the ingredient position of each of the target ingredients.

6. The food cooking control method according to claim 5, characterized in that: The step of determining the cooking parameters according to the food properties and food positions of the target food ingredients includes: Determining a target cooking temperature and a target cooking time according to the food properties of each of the target foods; Determining heating weight parameters of heating tubes of each heating tube deployed in the cooking device according to the food position of each target food; Cooking parameters including a target cooking temperature, a target cooking time, and a heating weight parameter of the heating tube are generated.

7. The food cooking control method according to claim 6, characterized in that: The step of determining the target cooking temperature and the target cooking time according to the food properties of each of the target food ingredients comprises: Determining an initial cooking temperature and an initial cooking time according to the food properties of each of the target food ingredients; Determine geographic location parameter information based on the communication address information of its own device; Determining temperature compensation parameters and time compensation parameters according to the geographic location parameter information; determining a target cooking temperature according to the temperature compensation parameter and the initial cooking temperature; and, A target cooking time is determined according to the time compensation parameter and the initial cooking time.

8. A food cooking control device, characterized in that: include: An ingredient image acquisition module, used to acquire cooking ingredient images; An image detection module, used to perform image detection on the cooking ingredient image using a pre-trained lightweight ingredient detection model, and obtain an ingredient type and an ingredient location of at least one target ingredient output by the model; A cooking parameter determination module, used to determine cooking parameters according to the type and location of each target ingredient; The control execution module is used to execute corresponding equipment control actions based on the cooking parameters to obtain cooking results.

9. A cooking device, characterized in that: The cooking device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the food cooking control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the food cooking control method according to any one of claims 1 to 7 when executed.

Images