Control method and device of cooking equipment, storage medium and cooking equipment

Abstract

The application relates to the technical field of household electrical appliances, and discloses a control method and device of a cooking device, a storage medium and the cooking device, the method comprising the following steps: acquiring a current image of food in a cooking process and a current smell of the food collected by a smell collection device on the cooking device; performing feature extraction on the current image through a trained smell recognition model to obtain a predicted smell corresponding to the current image; determining a current maturity of the food according to the predicted smell, the current smell and a target smell acquired in advance; and controlling the cooking device according to the current maturity. Therefore, the current image of the food is subjected to feature extraction through the trained smell recognition model to obtain the predicted smell corresponding to the current image, the current maturity of the food is determined by combining the current smell of the food and the target smell acquired in advance, and finally, the cooking device is controlled according to the current maturity, so that full-automatic cooking can be realized without user setting of parameters, and user experience is improved.

Description

Technical Field

[0001] This invention relates to the field of home appliance technology, specifically to control methods, devices, storage media, and cooking equipment. Background Technology

[0002] Typically, when cooking in an oven, users judge the degree of baking by observing the browning of the food inside, and stop cooking according to their preferred level of doneness. During the final browning stage, the food's color changes rapidly, requiring users to closely monitor the oven and stop baking at the appropriate time, which is time-consuming and requires considerable attention.

[0003] To address this pain point, there are generally two approaches. One is to preset multiple baking levels in the menu for users to choose from, allowing the device to automatically cook food. However, this approach cannot cover all user scenarios and lacks sufficient cooking precision. The other approach is to use sensor arrays such as oxygen and odor sensors to predict the doneness of food. However, this solution is also limited by issues such as sensor stability and lifespan. When sensor stability is poor, the reliability of the obtained food doneness information is insufficient, which seriously affects the device's control over food during automatic cooking and reduces the user experience. Summary of the Invention

[0004] In view of this, the present invention provides a control method, device, storage medium and cooking equipment for cooking equipment, in order to solve the problem that the equipment is difficult to reasonably control the cooking process of food due to the lack of stability of related technologies.

[0005] In a first aspect, the present invention provides a method for controlling a cooking device, the method comprising:

[0006] Acquire current images of the food during the cooking process, as well as the current odor of the food collected by the odor-collecting device on the cooking equipment;

[0007] The trained odor recognition model extracts features from the current image to obtain the predicted odor corresponding to the current image.

[0008] The current ripeness of the food is determined based on the predicted odor, the current odor, and the pre-acquired target odor.

[0009] Control the cooking equipment according to the current level of maturity.

[0010] This allows for feature extraction of the current image of food during the cooking process using a trained odor recognition model, resulting in a predicted odor corresponding to the current image. By combining the current odor of the food collected by the odor collection device with the pre-acquired target odor, the current ripeness of the food is determined. Finally, based on the current ripeness, the cooking equipment is controlled, automatically adjusting the food cooking process without setting parameters, achieving fully automatic cooking and improving the user experience.

[0011] In one optional implementation, a trained odor recognition model is used to extract features from the current image to obtain a predicted odor corresponding to the current image, including:

[0012] Input the current image into the odor recognition model to obtain the texture features, shape features, and color features of the current image;

[0013] The odor of the current image is predicted based on texture, shape and color features to obtain the predicted odor corresponding to the current image.

[0014] This allows for the prediction of odors corresponding to the current image by utilizing the texture, shape, and color features of the current image. By characterizing changes in the internal fibers of food through the odor features of the image, the efficiency and accuracy of the work are greatly improved.

[0015] In one optional implementation, determining the current ripeness of the food based on the predicted odor, the current odor, and the pre-acquired target odor includes:

[0016] Based on the predicted and target odors, the first degree of ripeness of the food is obtained;

[0017] Based on the current odor and the target odor, determine the second degree of ripeness of the food;

[0018] Based on the relationship between the first and second maturity levels, the current maturity level of the food is obtained.

[0019] By using the relationship between the first and second maturity levels, the detection of food maturity can be corrected to obtain the current maturity level of the food, thereby improving the accuracy of maturity detection results.

[0020] In one alternative implementation, determining the current ripeness of the food based on the predicted odor, the current odor, and the pre-acquired target odor includes:

[0021] Based on the predicted and target odors, the first degree of ripeness of the food is obtained;

[0022] Based on the current odor and the target odor, determine the second degree of ripeness of the food;

[0023] The second maturity is quantitatively compared with the historical second maturity of the food within a historical time period to obtain a quantitative value of the difference between the second maturity and the historical second maturity.

[0024] If the detected difference quantification value is lower than the preset difference quantification threshold, it is confirmed that the odor collection device has malfunctioned, and the first maturity level is taken as the current maturity level of the food.

[0025] Therefore, if the second degree of maturity does not change within a continuous period of time, it can be confirmed that the odor collection device has malfunctioned. The first degree of maturity is taken as the current degree of maturity of the food. Even if the odor collection device is unstable, the cooking equipment can still be automatically controlled according to the current degree of maturity.

[0026] In one alternative implementation, the cooking equipment is controlled based on the current level of ripeness, including:

[0027] Based on the current doneness of the food, obtain the current cooking temperature and cooking time corresponding to the cooking equipment;

[0028] The heating and cooling devices on the cooking equipment are controlled based on the current cooking temperature and the current cooking time.

[0029] By determining the current cooking temperature and time of the cooking equipment based on the current doneness of the food, the heating and cooling devices on the cooking equipment can be controlled, enabling the cooking equipment to automatically cook according to the current doneness of the food and improving the user experience.

[0030] In one alternative implementation, the method further includes:

[0031] Acquire the target aroma of food that matches the user's taste, as well as an initial image of the food before cooking;

[0032] Based on the initial image, determine the food ingredient category, and determine the initial cooking temperature and initial cooking time corresponding to the ingredient category and target aroma;

[0033] The heating and cooling devices on the cooking equipment are controlled based on the initial cooking temperature and initial cooking time.

[0034] In one alternative implementation, the training process of the odor recognition model includes:

[0035] Obtain a training set consisting of multiple food images with odor tags;

[0036] Multiple food images in the training set are preprocessed to obtain multiple preprocessed food images; the preprocessing includes denoising, standardization and normalization.

[0037] The texture, shape, and color features of multiple preprocessed food images are extracted, and the pre-defined odor recognition model is trained based on the odor labels corresponding to the multiple preprocessed food images until the odor recognition model converges; the odor recognition model is a neural network model.

[0038] In a second aspect, the present invention provides a control device for a cooking apparatus, the device comprising:

[0039] The acquisition module is used to acquire the current image of the food during the cooking process, as well as the current odor of the food collected by the odor acquisition device on the cooking equipment;

[0040] The first processing module is used to extract features from the current image using a trained odor recognition model when a malfunction of the odor collection device is detected, and to obtain a predicted odor corresponding to the current image.

[0041] The second processing module is used to determine the current ripeness of the food based on the predicted odor, the current odor, and the pre-acquired target odor.

[0042] The third processing module is used to control the cooking equipment based on the current level of doneness.

[0043] Thirdly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the control method of the cooking apparatus according to the first aspect or any corresponding embodiment thereof.

[0044] Fourthly, the present invention provides a cooking device, which includes a controller, an image acquisition device, an odor acquisition device, a heating device, and a heat dissipation device;

[0045] The controller includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to control the cooking device according to the first aspect or any of its corresponding embodiments.

[0046] In one alternative implementation, the cooking device is a steam oven.

[0047] In one alternative implementation, the controller is an MCU, the image acquisition device is a camera, the odor acquisition device is an odor sensor, the heating device is a heating tube, and the heat dissipation device is a cooling fan. Attached Figure Description

[0048] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0049] Figure 1 This is a structural block diagram of a cooking apparatus according to an embodiment of the present invention;

[0050] Figure 2 This is a schematic diagram of the structure of a cooking device according to an embodiment of the present invention;

[0051] Figure 3 This is a flowchart illustrating a control method for a cooking apparatus according to an embodiment of the present invention;

[0052] Figure 4 This is a flowchart illustrating a control method for another cooking device according to an embodiment of the present invention;

[0053] Figure 5 This is a flowchart illustrating a control method for another cooking device according to an embodiment of the present invention;

[0054] Figure 6A This is a schematic diagram of the application process of the control method for a cooking device according to an embodiment of the present invention;

[0055] Figure 6B This is a schematic diagram of the application process of a control method for another cooking device according to an embodiment of the present invention;

[0056] Figure 7 This is a structural block diagram of the control device of a cooking apparatus according to an embodiment of the present invention;

[0057] Figure 8 This is a schematic diagram of the hardware structure of the controller according to an embodiment of the present invention. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] Typically, when cooking in an oven, users judge the doneness of the food by observing its browning, and then stop cooking according to their preferred level of doneness. During the final browning stage, the color changes rapidly, requiring users to closely monitor the oven and stop baking at the appropriate time, which is time-consuming and requires considerable attention.

[0060] To address this pain point and problem, there are generally two approaches. One is to preset multiple baking parameters in the menu for users to choose from, in order to control the equipment to automatically cook food. However, this approach has problems such as not being able to cover all user scenarios, insufficient cooking precision, unstable results, and many influencing factors. The other approach is to use sensor arrays such as oxygen sensors and odor sensors to predict the doneness of food. However, this solution is also limited by the stability of the sensors, the lifespan of the sensors, the accuracy of data modeling, and the amount of food to be cooked. When the sensor stability is poor, the reliability of the food doneness information obtained is insufficient, which seriously affects the control of the equipment when automatically cooking food, and fails to provide users with a stable and reliable method, thus reducing the user experience.

[0061] Therefore, this invention provides a control scheme for a cooking device to determine the degree of food cooking doneness, solving the problems of instability and poor results in related technologies. It also addresses the pain point of users needing to constantly monitor the oven in certain situations, making it easier for users to understand the baking status of food inside the oven.

[0062] This invention provides a cooking device, such as... Figure 1 As shown, the cooking device includes a controller 101, an image acquisition device 102, an odor acquisition device 103, a heating device 104, and a heat dissipation device 105. The image acquisition device 102 is used to acquire images within the cooking device, the odor acquisition device 103 is used to acquire odors within the cooking device, and the heating device 104 and the heat dissipation device 105 are used to coordinate the adjustment of the temperature within the cooking device. The specific working principle and process of the controller 101 can be found in the relevant description of the method embodiment below, and will not be repeated here.

[0063] It should be noted that the above modules communicate and interact with each other via the UART serial port. UART stands for Universal Asynchronous Receiver / Transmitter, which is a serial, asynchronous, full-duplex communication protocol.

[0064] Specifically, such as Figure 2 As shown, the above-mentioned cooking equipment can be a steam oven / grill combo machine, and the controller 101 is an MCU (Microcontroller Unit). Figure 2(Not shown in the image), the image acquisition device 102 is a camera, and the odor acquisition device 103 is an odor sensor. Furthermore, the controller 101 described above can be a microcontroller, MCU, or other control chip with logic processing capabilities; however, this invention is not limited thereto.

[0065] Specifically, see again Figure 2 The heat dissipation device 105 is a cooling fan, and the heating device 104 is a heating element. The heating element can be divided into a top heating element, a bottom heating element, and a boiler heating element. The bottom heating element is mainly used for secondary evaporation of the condensate at the bottom, thereby improving the utilization rate of water vapor and reducing cleaning difficulty. The controller 101 controls the circuit current of the heat dissipation device 105 and the heating device 104 by adjusting the duty cycle using a PID controller, thus achieving adjustable temperature within the cooking equipment.

[0066] Specifically, the controller 101 of the cooking equipment can also have a built-in memory module that can memorize the user's taste preferences based on artificial olfactory technology. This module allows the user to interact with the controller MCU through the operation interface on the cooking equipment display screen, query food cooking information, and receive user feedback information to improve the system performance. It can self-optimize and adjust according to the user's needs to better meet the actual application requirements.

[0067] According to an embodiment of the present invention, a control method for a cooking device is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0068] This embodiment provides a method for controlling a cooking device, which can be used as follows: Figure 1 The controller 101 of the cooking equipment shown is, for example, an MCU or a microcontroller. Figure 3 This is a flowchart of a control method for a cooking apparatus according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0069] Step S301: Obtain the current image of the food during the cooking process, as well as the current odor of the food collected by the odor collection device on the cooking equipment.

[0070] Specifically, an image acquisition device on the cooking equipment, such as a camera, is used to acquire an initial image of the food before cooking begins and a current image of the food during the cooking process. An odor acquisition device on the cooking equipment, such as an odor sensor, is used to acquire the current odor of the food.

[0071] Step S302: Extract features from the current image using the trained odor recognition model to obtain the predicted odor corresponding to the current image.

[0072] In some alternative implementations, the training process for the odor recognition model may include the following steps:

[0073] Step a1: Obtain a training set consisting of multiple food images with odor labels.

[0074] Specifically, the dataset, consisting of multiple food images with odor labels, is divided into three parts: a training set, a validation set, and a test set. The training set is used to train the model, the validation set is used to tune the model's hyperparameters, and the test set is used to evaluate the model's performance.

[0075] It should be noted that the categories of odor labels can be predefined, for example, based on six basic odor categories (floral, fruity, spice, pine resin, burnt, and foul) or ten odor categories (fragrant, sweet, sulfur compounds, fatty acids, baked goods, meat, pungent, aldehydes, rice, and vegetables).

[0076] Step a2 involves preprocessing multiple food images in the training set to obtain preprocessed food images. The preprocessing includes denoising, standardization, and normalization.

[0077] Specifically, multiple food images in the training set are subjected to denoising, standardization, and normalization operations to enhance image contrast and clarity, remove irrelevant information, improve image quality and the accuracy of odor recognition, and prepare for subsequent feature extraction.

[0078] Step a3: Extract the texture features, shape features, and color features corresponding to the preprocessed food images, and train the preset odor recognition model based on the odor labels corresponding to the preprocessed food images until the odor recognition model converges; the odor recognition model is a neural network model.

[0079] Specifically, the preset odor recognition model can be a CNN or RNN neural network model. A CNN model typically consists of multiple convolutional layers, pooling layers, and fully connected layers. Convolutional layers extract local features from the image, pooling layers reduce the dimensionality of the features, and fully connected layers can use the extracted features for simple classification or regression tasks. Before training the model, the number of layers, functions, and the number of neurons in each layer need to be preset. The model training process involves several steps. First, the model is trained using a training set, and its parameters are optimized through backpropagation to minimize the loss function. Next, the model is evaluated using a validation set, and various metrics such as accuracy, recall, and F1 score are calculated. Based on the evaluation results, the model's parameters or hyperparameters are adjusted to optimize performance. Then, based on the evaluation results and practical needs, the model is further optimized, including adjusting the network structure, adding or removing layers, changing the activation function, and adding regularization. The optimization goal is to minimize the model's loss on the training set while maximizing its generalization ability on unknown data. Finally, the optimized model is tested using a test set, and its metrics are calculated to evaluate its performance. If the test results do not meet the requirements, the model needs to be readjusted or retrained.

[0080] Furthermore, texture features of food images can be extracted using gray-level co-occurrence matrix (GLCM) or Tamura texture feature algorithms. Shape features can be extracted using boundary-based Fourier transform or wavelet transform methods, region-based SIFT (Scale Invariant Feature Transform) algorithms, or SURF (Speeded Up Robust Features) algorithms. Color features can be extracted using color histograms, color moments, and other methods. After feature extraction, methods such as PCA (Principal Component Analysis), LDA (Linear Discriminant Analysis), SVD (Singular Value Decomposition), genetic algorithms, or particle swarm optimization are used to reduce feature dimensionality and retain the most important information, thus optimizing the extracted features. Finally, the optimized features are input into a suitable classifier or odor simulation algorithm to predict the odor of the food image. Finally, the prediction results are evaluated to determine whether they meet the requirements. The evaluation uses subjective evaluation (observation by sight and smell) and objective evaluation (accuracy, F1 score, recall, etc.). If the evaluation results are not ideal, the parameters of preprocessing, feature extraction and optimization can be adjusted, and feature extraction and optimization can be performed again to improve the accuracy and reliability of the classifier or odor simulation method until satisfactory simulation effect and recognition performance are achieved.

[0081] Step S303: Determine the current ripeness of the food based on the predicted odor, the current odor, and the pre-acquired target odor.

[0082] Specifically, since odors are not limited by spatial operation, the components and concentrations of food odors can be captured by odor collection devices on cooking equipment. By observing the volatilization of odors, the intrinsic relationship between the components and concentrations of odors and the ripeness of food can be found, thereby establishing the correlation between odors and food categories and ripeness.

[0083] Step S304: Control the cooking equipment according to the current level of doneness.

[0084] Specifically, based on the current doneness of the food, the operating current of the heating and cooling devices in the cooking equipment is controlled by adjusting the duty cycle using PID, automatically adjusting the cooking process without requiring user parameter settings, thus achieving fully automatic cooking. At the same time, users can set their preferred taste, and the controller adjusts the cooking based on the current doneness of the food, using the user's selected target taste as the objective.

[0085] The cooking equipment control method provided in this embodiment extracts features from the current image of the food during the cooking process using a trained odor recognition model to obtain the predicted odor corresponding to the current image. It then combines the current odor of the food collected by the odor collection device with the pre-acquired target odor to determine the current ripeness of the food. Finally, based on the current ripeness, the cooking equipment is controlled. The cooking process can be automatically adjusted without setting parameters, achieving fully automatic cooking and improving the user experience.

[0086] This embodiment provides a method for controlling a cooking device, which can be used as follows: Figure 1 The controller 101 of the cooking equipment shown is, for example, an MCU or a microcontroller. Figure 4 This is a flowchart of a control method for a cooking apparatus according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps:

[0087] Step S401: Acquire a current image of the food during the cooking process, and the current odor of the food collected by the odor detection device on the cooking equipment. For details, please refer to [link to relevant documentation]. Figure 3 Step S301 of the illustrated embodiment will not be described again here.

[0088] Step S402: Extract features from the current image using the trained odor recognition model to obtain the predicted odor corresponding to the current image.

[0089] Specifically, step S402 includes:

[0090] Step S4021: Input the current image into the odor recognition model to obtain the texture features, shape features and color features of the current image.

[0091] Specifically, the trained odor recognition model is used to extract texture, shape, and color features from the current image. If food ripeness is detected solely based on surface color changes, a large amount of experimental data is required. In practice, various factors can introduce errors (such as lighting conditions and differences in the food itself), leading to significant errors in the results. Furthermore, strong external lighting and weak internal lighting in cooking equipment, along with glare from the internal camera, also affect the assessment of food ripeness. Therefore, extracting texture, shape, and color features from the food image reduces the impact of weak lighting and glare, thereby improving the accuracy of the final detection results.

[0092] Step S4022: Predict the odor of the current image based on texture features, shape features, and color features to obtain the predicted odor corresponding to the current image.

[0093] Specifically, based on texture, shape, and color features, odor information in images is automatically identified (each food has a different odor, and the odor changes during cooking). This allows for the characterization of changes in the internal fibers of food through the odor features of the image, greatly improving work efficiency and accuracy.

[0094] Step S403: Determine the current ripeness of the food based on the predicted odor, the current odor, and the pre-acquired target odor.

[0095] In some optional implementations, step S403 above includes:

[0096] Step b1: Based on the predicted odor and the target odor, obtain the first degree of ripeness corresponding to the food.

[0097] Step b2: Based on the current odor and the target odor, obtain the second degree of ripeness corresponding to the food.

[0098] Specifically, since odors are not limited by spatial operation, the components and concentrations of food odors can be captured by odor collection devices on cooking equipment. By observing the volatilization of odors, the intrinsic relationship between the components and concentrations of odors and the ripeness of food can be found, thereby establishing a correlation between odors and food categories and ripeness. Thus, the ripeness of food can be determined based on this correlation when the odor of the food is known.

[0099] Step b3: Based on the relationship between the first maturity and the second maturity, obtain the current maturity of the food.

[0100] Specifically, when the difference between the first degree of maturity and the second degree of maturity (which can be set according to the actual accuracy requirements) is not large, the first degree of maturity or the second degree of maturity can be used as the current maturity of the food, or the average between the first degree of maturity and the second degree of maturity can be used as the current maturity of the food.

[0101] Since the current odor of food is obtained through a sensor array such as an odor sensor, the second degree of ripeness of the food will be affected by the stability and lifespan of the sensor. Therefore, the detection of food ripeness can be corrected based on the relationship between the first degree of ripeness and the second degree of ripeness to obtain the current degree of ripeness of the food, thereby improving the accuracy of the ripeness detection results.

[0102] In some optional implementations, step S403 above includes:

[0103] Step c1: Based on the predicted odor and the target odor, obtain the first degree of ripeness corresponding to the food.

[0104] Step c2: Based on the current odor and the target odor, obtain the second degree of ripeness of the food.

[0105] Step c3: Quantitatively compare the second maturity with the historical second maturity of the food within a historical time period to obtain a quantitative value of the difference between the second maturity and the historical second maturity.

[0106] Step c4: When the detected difference quantification value is lower than the preset difference quantification threshold, it is confirmed that the odor collection device has malfunctioned, and the first maturity is taken as the current maturity of the food.

[0107] Specifically, if the second degree of maturity does not change within a continuous period of time, it can be confirmed that the odor collection device has malfunctioned. The first degree of maturity is then taken as the current degree of maturity of the food. Thus, even if the odor collection device is unstable, the cooking equipment can still be automatically controlled according to the current degree of maturity.

[0108] Step S404: Control the cooking equipment according to the current level of doneness.

[0109] Specifically, based on the current doneness of the food, the current cooking temperature and cooking time of the cooking equipment are obtained, thereby controlling the heating and cooling devices on the cooking equipment to enable the cooking equipment to automatically cook according to the current doneness of the food, thus improving the user experience.

[0110] The cooking equipment control method provided in this embodiment extracts texture, shape, and color features from the current image of food during the cooking process using a trained odor recognition model, thereby obtaining a predicted odor corresponding to the current image. Combined with the current odor of the food collected by the odor collection device and the pre-acquired target odor, the current ripeness of the food is determined. Finally, the cooking equipment is controlled according to the current ripeness. The cooking process can be automatically adjusted without setting parameters, achieving fully automatic cooking and improving the user experience.

[0111] This embodiment provides a method for controlling a cooking device, which can be used as follows: Figure 1 The controller 101 of the cooking equipment shown is, for example, an MCU or a microcontroller. Figure 5 This is a flowchart of a control method for a cooking apparatus according to an embodiment of the present invention, during execution Figure 4 Before steps S401 to S404 in the illustrated embodiment, as follows: Figure 5 As shown, the process also includes the following steps:

[0112] Step S501: Obtain the target aroma of the food that matches the user's taste, as well as an initial image of the food before cooking.

[0113] Step S502: Determine the food ingredient category based on the initial image, and determine the initial cooking temperature and initial cooking time corresponding to the ingredient category and target aroma.

[0114] Specifically, by comparing the initial image with a preset image database, the food category of the current food is automatically identified and determined. Then, based on the preset cooking curve corresponding to the food category, the initial cooking temperature and initial cooking time corresponding to the food category and the target aroma selected by the user are determined.

[0115] Step S503: Control the heating device and heat dissipation device on the cooking equipment according to the initial cooking temperature and initial cooking time.

[0116] Specifically, the heating and cooling devices on the cooking equipment are controlled according to the initial cooking temperature and initial cooking time, thereby adjusting the cooking equipment to a suitable temperature and time for cooking, eliminating the need for user parameter settings and improving the user experience.

[0117] The control method for the cooking equipment provided in this embodiment automatically identifies and determines the type of the current ingredient by comparing the acquired initial image with a preset image database. Then, based on the preset cooking curve corresponding to the ingredient type, it determines the initial cooking temperature and initial cooking time corresponding to the ingredient type and the target aroma selected by the user. This controls the heating and cooling devices on the cooking equipment, adjusting the cooking equipment to a suitable temperature and time for cooking. No user parameter settings are required, thus improving the user experience.

[0118] The control method of the cooking device according to an embodiment of the present invention will be described in detail below with reference to a specific application example, which uses a cooking device as an example. Figure 2 Take the steam oven shown as an example.

[0119] like Figure 6A As shown, after recognizing that the steam oven door is closed and the controller reads that the user clicks to start cooking, the camera uses image recognition to acquire images of the oven's interior and transmits the image data to the controller. The controller compares the images transmitted by the camera with the pre-established image database and food aroma database to automatically determine the current ingredients. Then, according to the preset cooking curve, the steam oven is adjusted to the appropriate temperature and time for cooking. During the cooking process, the odor data transmitted by the gas sensor is compared with the food aroma database. By identifying and analyzing the odor changes during the food cooking process, the controller intelligently adjusts the taste and can intelligently determine the degree of doneness of the ingredients. Based on the recorded data, the controller can reproduce the user's preferred food, achieving one-button fully automatic cooking.

[0120] like Figure 6B As shown, when the dual-function steam oven detects the opening and closing of the oven door during the cooking process, it automatically re-acquires image and odor data of the oven's interior after adjusting the appropriate temperature and time for cooking the food. Combining this with the odor sensor and camera, it confirms whether there is food inside and any changes in the type of food. By transmitting image data and using the odor from the phone, it judges the doneness of the food, enabling the dual-function steam oven to intelligently control the cooking process.

[0121] This embodiment also provides a control device for a cooking apparatus, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0122] This embodiment provides a control device for a cooking appliance, such as... Figure 7 As shown, it includes:

[0123] The acquisition module 701 is used to acquire the current image of the food during the cooking process, as well as the current odor of the food collected by the odor collection device on the cooking equipment;

[0124] The first processing module 702 is used to extract features from the current image using a trained odor recognition model when a malfunction of the odor collection device is detected, and to obtain a predicted odor corresponding to the current image.

[0125] The second processing module 703 is used to determine the current ripeness of the food based on the predicted odor, the current odor, and the pre-acquired target odor.

[0126] The third processing module 704 is used to control the cooking equipment according to the current level of doneness.

[0127] In some optional implementations, the training process of the odor recognition model in the first processing module 702 includes: acquiring a training set consisting of multiple food images with odor tags; preprocessing the multiple food images in the training set to obtain preprocessed multiple food images; the preprocessing includes denoising, standardization, and normalization; extracting the texture features, shape features, and color features corresponding to the preprocessed multiple food images respectively, and training the preset odor recognition model based on the odor tags corresponding to the preprocessed multiple food images respectively, until the odor recognition model converges; the odor recognition model is a neural network model.

[0128] In some alternative implementations, the first processing module 702 includes:

[0129] The first processing unit is used to input the current image into the odor recognition model to obtain the texture features, shape features and color features of the current image;

[0130] The second processing unit is used to predict the odor of the current image based on texture features, shape features, and color features, and obtain the predicted odor corresponding to the current image.

[0131] In some alternative implementations, the second processing module 703 includes:

[0132] The third processing unit is used to obtain the first degree of ripeness of the food based on the predicted odor and the target odor;

[0133] The fourth processing unit is used to determine the second degree of ripeness of the food based on the current odor and the target odor.

[0134] The fifth processing unit is used to obtain the current maturity of the food based on the relationship between the first maturity and the second maturity.

[0135] In some alternative implementations, the second processing module 703 includes:

[0136] The third processing unit is used to obtain the first degree of ripeness of the food based on the predicted odor and the target odor;

[0137] The fourth processing unit is used to determine the second degree of ripeness of the food based on the current odor and the target odor.

[0138] The sixth processing unit is used to quantitatively compare the second maturity with the historical second maturity of the food within a historical time period to obtain a quantitative value of the difference between the second maturity and the historical second maturity.

[0139] The seventh processing unit is used to confirm that the odor collection device has malfunctioned when the detected difference quantification value is lower than the preset difference quantification threshold, and to take the first maturity as the current maturity of the food.

[0140] In some alternative implementations, the third processing module 704 includes:

[0141] The eighth processing unit is used to obtain the current cooking temperature and current cooking time of the cooking equipment based on the current doneness of the food.

[0142] The ninth processing unit is used to control the heating and cooling devices on the cooking equipment based on the current cooking temperature and the current cooking time.

[0143] In some alternative embodiments, the device further includes:

[0144] The fourth processing module 705 is used to acquire the target aroma of food that matches the user's taste, as well as the initial image of the food before cooking;

[0145] The fifth processing module 706 is used to determine the type of food ingredients based on the initial image, and to determine the initial cooking temperature and initial cooking time corresponding to the type of food ingredients and the target aroma.

[0146] The sixth processing module 707 is used to control the heating device and the heat dissipation device on the cooking equipment according to the initial cooking temperature and the initial cooking time.

[0147] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0148] In this embodiment, the control device of the cooking equipment is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0149] This invention also provides a controller having the above-described features. Figure 7 The control device of the cooking equipment shown.

[0150] Please see Figure 8 , Figure 8 Is it like this? Figure 1 The schematic diagram of the controller 101 shown is as follows: Figure 8 As shown, the controller includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise as required. The processors can process instructions executed within the controller, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple controllers can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 Take a processor 10 as an example.

[0151] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0152] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0153] The memory 20 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 controller. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the controller via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0154] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0155] The controller also includes a communication interface 30 for communicating with other devices or communication networks.

[0156] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0157] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for controlling a cooking device, characterized in that, The method includes: Acquire a current image of the food during the cooking process, as well as the current odor of the food collected by the odor collection device on the cooking equipment; The current image is input into the odor recognition model to obtain the texture features, shape features, and color features of the current image; the odor of the current image is predicted based on the texture features, shape features, and color features to obtain the predicted odor corresponding to the current image; The current ripeness of the food is determined based on the predicted odor, the current odor, and the pre-acquired target odor. The cooking equipment is controlled according to the current level of maturity; Determining the current ripeness of the food based on the predicted odor, the current odor, and the pre-acquired target odor includes: Based on the predicted odor and the target odor, the first maturity of the food is obtained; based on the current odor and the target odor, the second maturity of the food is obtained; through the intrinsic correlation between the composition and concentration of the odor and the maturity of the food, the correlation between odor and food category and maturity of the food is established, and the maturity of the food is determined based on the correlation and odor. The current maturity of the food is obtained based on the relationship between the first maturity and the second maturity.

2. The method according to claim 1, characterized in that, Determining the current ripeness of the food based on the predicted odor, the current odor, and the pre-acquired target odor includes: Based on the predicted odor and the target odor, the first degree of ripeness corresponding to the food is obtained; The second degree of ripeness of the food is obtained based on the current odor and the target odor; The second maturity is quantitatively compared with the historical second maturity of the food within a historical time period to obtain a quantitative value of the difference between the second maturity and the historical second maturity. If the detected difference quantification value is lower than the preset difference quantification threshold, it is confirmed that the odor collection device has malfunctioned, and the first maturity is taken as the current maturity of the food.

3. The method according to any one of claims 1 to 2, characterized in that, The step of controlling the cooking equipment based on the current ripeness includes: Based on the current doneness of the food, the current cooking temperature and current cooking time corresponding to the cooking equipment are obtained; The heating and cooling devices on the cooking equipment are controlled based on the current cooking temperature and the current cooking time.

4. The method according to claim 1, characterized in that, The method further includes: Acquire the target aroma of food that matches the user's taste, as well as an initial image of the food before cooking; Based on the initial image, determine the food ingredient category, and determine the initial cooking temperature and initial cooking time corresponding to the ingredient category and the target aroma; The heating and cooling devices on the cooking equipment are controlled according to the initial cooking temperature and the initial cooking time.

5. The method according to claim 1, characterized in that, The training process of the odor recognition model includes: Obtain a training set consisting of multiple food images with odor tags; Multiple food images in the training set are preprocessed to obtain multiple preprocessed food images; the preprocessing includes denoising, standardization, and normalization. Extract the texture features, shape features, and color features corresponding to the preprocessed food images, and train a preset odor recognition model based on the odor tags corresponding to the preprocessed food images until the odor recognition model converges; the odor recognition model is a neural network model.

6. A control device for a cooking apparatus, characterized in that, The device includes: The acquisition module is used to acquire the current image of the food during the cooking process, as well as the current odor of the food collected by the odor collection device on the cooking equipment; The first processing module is used to input the current image into an odor recognition model to obtain the texture features, shape features, and color features of the current image; and to predict the odor of the current image based on the texture features, shape features, and color features to obtain a predicted odor corresponding to the current image. The second processing module is used to determine the current ripeness of the food based on the predicted odor, the current odor, and the pre-acquired target odor. The third processing module is used to control the cooking equipment according to the current ripeness. The second processing module is further configured to: Based on the predicted odor and the target odor, the first maturity of the food is obtained; based on the current odor and the target odor, the second maturity of the food is obtained; through the intrinsic correlation between the composition and concentration of the odor and the maturity of the food, the correlation between odor and food category and maturity of the food is established, and the maturity of the food is determined based on the correlation and odor. The current maturity of the food is obtained based on the relationship between the first maturity and the second maturity.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the control method of the cooking apparatus according to any one of claims 1 to 5.

8. A cooking device, characterized in that, The cooking equipment includes a controller, an image acquisition device, an odor acquisition device, a heating device, and a heat dissipation device; The controller includes a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the control method of the cooking device according to any one of claims 1 to 5.

9. The cooking apparatus according to claim 8, characterized in that, The cooking equipment is a steam oven / bake oven.

10. The cooking apparatus according to claim 8, characterized in that, The controller is an MCU, the image acquisition device is a camera, the odor acquisition device is an odor sensor, the heating device is a heating tube, and the heat dissipation device is a cooling fan.

Images