Flame control method and device of a cooking hob, electronic device and intelligent kitchen appliance

Abstract

The application discloses a flame control method and device of a stove, an electronic device and intelligent kitchen electrical appliances. An infrared sensor is arranged in a preset range of the stove, and a pot on the stove is located in the sensing range of the infrared sensor. In the case that the stove is used to heat food in the pot, a real-time thermal imaging diagram of the pot is acquired in real time based on the infrared sensor. The real-time thermal imaging diagram is subjected to position region segmentation, and a position region of the food in the pot is obtained as a current food position region. According to the real-time thermal imaging diagram and the current food position region, current temperature distribution data of the food is obtained. According to the current temperature distribution data, a heating trend of the food is predicted, and target flame intensity and target flame direction of the stove are obtained. The flame of the stove is adjusted according to the target flame intensity and the target flame direction. The application can adjust the size and direction of the flame of the stove according to the thermal imaging diagram acquired by the infrared temperature measuring sensor, and improve the heating efficiency of the stove.

Description

Technical Field

[0001] This application relates to the field of kitchen appliance control technology, and in particular to a flame control method, device, electronic device, and smart kitchen appliance for a stove. Background Technology

[0002] Currently, many patents utilize infrared temperature sensors to detect the temperature at the bottom of cookware, using threshold judgments to adjust heat or automatically shut off the heat. For example, Robam Appliances' patent uses a telescopic sleeve to isolate flame interference, ensuring the accuracy of infrared temperature measurement; Shuaifeng integrated stoves' KOMS system achieves precise oil temperature monitoring.

[0003] Current technologies only focus on adjusting the heat intensity, without addressing the dynamic control of the flame direction. Manually observing the food's condition and adjusting the flame direction is delayed, especially during high-temperature cooking (such as stir-frying), where the food's surface temperature changes rapidly, and manual adjustments may miss the optimal timing. Traditional stoves cannot dynamically adjust the flame direction based on the real-time heating status of the food during cooking, resulting in poor uniformity, low energy efficiency, and complex operation. Summary of the Invention

[0004] This application provides a flame control method, device, electronic device, and smart kitchen appliance for a stove. This application can accurately locate the position of food in the cookware and adjust the flame size and direction of the stove in real time, so that the stove flame heats the food more evenly and efficiently, thereby improving the cooking efficiency of the stove.

[0005] On one hand, this application provides a flame control method for a stove, wherein an infrared sensor is installed within a preset range of the stove, and the pot on the stove is located within the sensing range of the infrared sensor. The method includes: When heating food in the pot using the stove, a real-time thermal image of the pot is acquired based on the infrared sensor. The real-time thermal image is segmented into location regions to obtain the current food location region within the cookware. Based on the real-time thermal image and the current food location area, the current temperature distribution data of the food is obtained; the real-time thermal image is marked with the temperature data of each location; Based on the current temperature distribution data, the heating trend of the food is predicted to obtain the target flame intensity and target flame direction of the stove; the heating trend represents the temperature change trend of the food. The flame of the stove is adjusted according to the target flame intensity and the target flame direction.

[0006] In one exemplary embodiment, before segmenting the real-time thermal image to obtain the location region of the food in the cookware as the current food location region, the method includes: A thermal image of the sample cooker is collected when the sample food is heated in the sample cooker; the sample thermal image is labeled with the sample location area of ​​the sample food; The sample thermal image is segmented based on a preset segmentation model to locate the position of the sample food in the sample cookware, thereby obtaining the sample position region segmentation result of the sample thermal image. Based on the difference between the sample location region segmentation result and the sample location region label, the preset segmentation model is trained to obtain the food segmentation model.

[0007] In one exemplary embodiment, before segmenting the real-time thermal image to obtain the location region of the food in the cookware as the current food location region, the method includes: A thermal image of the sample cooker is collected when the sample food is heated in the sample cooker; the sample thermal image is labeled with the sample location area of ​​the sample food; The sample thermal image is segmented based on a preset segmentation model to locate the position of the sample food in the sample cookware, thereby obtaining the sample position region segmentation result of the sample thermal image. Based on the difference between the sample location region segmentation result and the sample location region label, the preset segmentation model is trained to obtain the food segmentation model.

[0008] In one exemplary embodiment, the preset segmentation model includes a feature extraction network and a location region segmentation network. The step of segmenting the sample thermal image based on the preset segmentation model to locate the position of the sample food within the sample cookware, thereby obtaining the sample location segmentation result of the sample thermal image, includes: The thermal image of the sample is processed by the feature extraction network to obtain sample region category features; the sample region category features include at least one of sample shape features, sample texture features, sample temperature features, and sample spatial features; The location region segmentation network is used to perform location region segmentation on the category features of the sample region to obtain the sample location region segmentation result.

[0009] In one exemplary embodiment, the feature extraction network includes a shape feature extraction network, a texture feature extraction network, a temperature feature extraction network, and a spatial feature extraction network. The step of performing feature extraction processing on the sample thermal image based on the feature extraction network to obtain the sample region category features includes: Based on the shape feature extraction network, the thermal image of the sample is processed to extract shape features to obtain the shape features of the sample; Based on the texture feature extraction network, the sample thermal image is processed to extract texture features to obtain the sample texture features; Based on the temperature feature extraction network, the temperature features of the sample thermal image are extracted to obtain the sample temperature features. Based on the spatial feature extraction network, spatial features are extracted from the thermal image of the sample to obtain the spatial features of the sample. The sample region category features are determined based on the sample shape features, sample texture features, sample temperature features, and sample spatial features.

[0010] In one exemplary embodiment, before predicting the heating trend of the food based on the current temperature distribution data to obtain the target flame intensity and target flame direction of the stove, the method further includes: The sample temperature distribution data of the food sample during the heating process is collected; the sample temperature distribution data is labeled with the sample heating trend label of the food sample. Based on a preset prediction model, the temperature distribution data of the sample is predicted to obtain the predicted heating trend of the sample food. Based on the difference between the sample heating trend prediction result and the sample heating trend label, the preset prediction model is trained to obtain the food heating trend prediction model; The step of predicting the heating trend of the food based on the current temperature distribution data to obtain the target flame intensity and target flame direction of the stove includes: The current temperature distribution data is input into the food heating trend prediction model to obtain the current heating trend of the food, and the target flame intensity and target flame direction are determined based on the current heating trend.

[0011] In one exemplary embodiment, the step of segmenting the real-time thermal image to obtain the current food location region within the cookware includes: The real-time thermal image is resized to obtain a thermal image of a preset size; The thermal image of the preset size is input into the food segmentation model to obtain the current food position area in the cookware.

[0012] In one exemplary embodiment, after adjusting the flame of the stove according to the target flame intensity and the target flame direction, the method includes: Based on the infrared sensor, the real-time thermal image of the cookware is acquired, and an updated thermal image is obtained. The updated thermal image is segmented to obtain the updated location region of the food, and the updated temperature distribution data of the food is obtained based on the updated location region. The heating trend of the food is predicted based on the updated temperature distribution data to obtain the updated target flame intensity and the updated target flame direction. The flame of the stove is then adjusted based on the updated target flame intensity and the updated target flame direction. With the stove in operation, repeat the step of acquiring the real-time thermal image of the cookware based on the infrared sensor to obtain an updated thermal image.

[0013] On the other hand, a flame control device for a stove is provided, wherein an infrared sensor is installed within a preset range of the stove, and the pot on the stove is located within the sensing range of the infrared sensor. The device includes: The real-time thermal imaging acquisition module is used to acquire a real-time thermal image of the cookware based on the infrared sensor when the food in the cookware is heated using the stove. The current food location region acquisition module is used to segment the real-time thermal image to obtain the current food location region as the location region of the food in the cookware. The current temperature distribution data acquisition module is used to obtain the current temperature distribution data of the food based on the real-time thermal imaging map and the current food location area; the real-time thermal imaging map is marked with the temperature data of each location; The heating trend prediction module is used to predict the heating trend of the food based on the current temperature distribution data, and to obtain the target flame intensity and target flame direction of the stove; the heating trend represents the temperature change trend of the food. An adjustment module is used to adjust the flame of the stove according to the target flame intensity and the target flame direction.

[0014] On the other hand, an electronic device is provided, including a processor and a memory, wherein the processor is configured to store processor-executable instructions in the memory; wherein the processor is configured to execute the instructions to implement the flame control method of the stove as described above.

[0015] On the other hand, a smart kitchen appliance is provided, which adopts the flame control method of the stove as described above.

[0016] On the other hand, a computer-readable storage medium is provided, which contains at least one instruction or at least one program, which is loaded and executed by a processor to implement the flame control method of the stove described above.

[0017] The flame control method, device, electronic equipment, and smart kitchen appliance provided in this application have the following technical effects: This application sets up an infrared sensor within a preset range of the stove, with the pot on the stove located within the sensing range of the infrared sensor. When heating food in the pot using the stove, a real-time thermal image of the pot is acquired based on the infrared sensor. The real-time thermal image is segmented into positional regions to obtain the current food position region within the pot. Based on the real-time thermal image and the current food position region, the current temperature distribution data of the food is obtained. The real-time thermal image is marked with temperature data at each position. The heating trend of the food is predicted based on the current temperature distribution data to obtain the target flame intensity and target flame direction of the stove. The heating trend represents the temperature change trend of the food. The flame of the stove is adjusted according to the target flame intensity and target flame direction. This application utilizes infrared sensors installed within a preset area of ​​the stove to acquire real-time thermal images of the cookware and the food inside. Based on a pre-built data model, the thermal images are segmented, separating the cookware from the food. This allows for precise location of the food within the cookware and acquisition of temperature distribution data during heating. By predicting the food's temperature distribution, the heating trend can be forecasted, and the stove's flame size and direction can be precisely adjusted in real-time. This results in more uniform and efficient heating, reducing ineffective heating areas and significantly improving cooking efficiency. It solves the problem of cooking results being affected by the inability to manually adjust the flame in a timely manner, thus improving energy efficiency.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0019] To more clearly illustrate the technical solutions and advantages in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic flowchart of a flame control method for a stove provided in the embodiments of this specification; Figure 2 This is a schematic diagram of a process for obtaining a food segmentation model provided in the embodiments of this specification; Figure 3 This is a schematic diagram of a process for obtaining sample location segmentation results provided in an embodiment of this specification; Figure 4 This is a schematic diagram of a process for obtaining category features of a sample region, provided in an embodiment of this specification. Figure 5 This is a schematic diagram of a process for obtaining the current food location region provided in the embodiments of this specification; Figure 6 This is a schematic diagram of a process for repeatedly adjusting the flame of a stove provided in the embodiments of this specification; Figure 7 This is a schematic diagram of a flame control device for a stove provided in the embodiments of this specification; Figure 8 This is a schematic diagram of the server structure for a flame control method for a stove provided in the embodiments of this specification. Detailed Implementation

[0021] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0023] The following describes an intelligent cooking method based on this application. Figure 1 This is a flowchart illustrating a flame control method for a stove according to an embodiment of this specification. This specification provides the operational steps of the method described in the embodiment or flowchart, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiment is merely one possible execution order among many and does not represent the only possible execution order. In actual system or server product execution, the method can be executed sequentially according to the embodiment or the accompanying drawings, or in parallel (e.g., in a parallel processor or multi-threaded processing environment). Specifically, as shown... Figure 1 As shown, an infrared sensor is installed within a preset range of the stove, and the pot on the stove is located within the sensing range of the infrared sensor. The method may include: S1: When heating food in the pot using the stove, a real-time thermal image of the pot is acquired based on the infrared sensor. S2: Segment the real-time thermal image to obtain the current food location area in the cookware; S3: Based on the real-time thermal image and the current food location area, obtain the current temperature distribution data of the food; the real-time thermal image is marked with the temperature data of each location; S4: Based on the current temperature distribution data, predict the heating trend of the food to obtain the target flame intensity and target flame direction of the stove; the heating trend represents the temperature change trend of the food; S5: Adjust the flame of the stove according to the target flame intensity and the target flame direction.

[0024] In this embodiment, an infrared sensor can be installed within a preset range of the cooktop, ensuring that the pot on the cooktop is within the sensing range of the infrared sensor. The infrared sensor can acquire the temperature of the food around the pot and inside the pot in real time. Specifically, the infrared sensor can be installed on the range hood, above the pot, to acquire the temperature of the entire pot.

[0025] In this embodiment, when heating food in a pot using a stove, an infrared sensor can acquire a real-time thermal image of the pot and its surroundings. After obtaining the thermal image, the image is segmented to separate the pot from the food, determining the food's position within the pot. Based on this positional distribution, the location of the food within the pot is determined, allowing for more precise adjustment of the flame direction. After obtaining the food's temperature distribution data, the heating trend is predicted, resulting in the target flame intensity and direction. The size and direction of the flame are then adjusted to concentrate it more effectively on the food, improving heating efficiency. Specifically, the flame direction can be adjusted horizontally between 30° and 150°, with an angle adjustment accuracy of less than 1°. For example, when searing steak, the flame can be concentrated on the steak at the bottom of the pan; when stewing, the flame can be evenly distributed for better cooking results.

[0026] This application embodiment, by setting an infrared sensor within a preset area of ​​the stove, can acquire real-time thermal images of the pot and the food inside. Based on a pre-built data model, the thermal images are segmented, separating the pot from the food. This allows for precise location of the food within the pot and acquisition of temperature distribution data during the heating process. By predicting the food's temperature distribution data, the heating trend of the food can be predicted, and the flame size and direction of the stove can be precisely adjusted in real-time based on this trend. This results in more uniform and efficient heating of the food, reducing ineffective heating areas, improving energy utilization, and achieving intelligent control without additional manual intervention, thus enhancing the user's intelligent experience with the stove.

[0027] In one exemplary embodiment, such as Figure 2 As shown, before segmenting the real-time thermal image to obtain the location region of the food in the cookware as the current food location region, the method includes: S021: Collect a thermal image of the sample cooker when the sample food is heated in the sample cooker; the thermal image is labeled with the sample location area of ​​the sample food; S022: The thermal image of the sample is segmented based on a preset segmentation model to locate the position area of ​​the food sample in the sample cookware, thereby obtaining the sample position area segmentation result of the thermal image of the sample. S023: Based on the difference between the sample location region segmentation result and the sample location region label, train the preset segmentation model to obtain the food segmentation model.

[0028] In this embodiment, a large amount of data can be collected to pre-build a food segmentation model, enabling the stove to quickly locate the position of the food in the pot based on the acquired thermal imaging image during operation, thus allowing for more precise adjustment of the flame direction. A sample thermal imaging image of the sample pot can be collected when sample food is heated in the sample pot. This thermal imaging image is labeled with the sample location region of the sample food. Then, the sample thermal imaging image is segmented based on a pre-defined segmentation model to locate the position region of the sample food in the sample pot, obtaining the sample location region segmentation result of the sample thermal imaging image. The difference between the sample location region segmentation result and the sample location region label is then used to train the pre-defined segmentation model, ultimately obtaining the food segmentation model. It is essential to ensure that the collected sample data includes various cooking scenarios and lighting conditions to guarantee the model's generalization ability. Furthermore, it needs to cover different pot types (e.g., frying pan, wok, etc.), different food types (e.g., liquid, solid, granular, etc.), different heating stages (e.g., initial heating, boiling, cooking, etc.), and different cooking modes (stewing, stir-frying, deep-frying, etc.).

[0029] This application embodiment, by pre-constructing a food segmentation model, can segment the real-time acquired thermal imaging image to quickly obtain the current location area of ​​the food inside the pot, effectively improving the efficiency and accuracy of image segmentation.

[0030] In one exemplary embodiment, such as Figure 3 As shown, the preset segmentation model includes a feature extraction network and a location region segmentation network. The process of segmenting the sample thermal image based on the preset segmentation model, locating the position of the sample food within the sample cookware, and obtaining the sample location segmentation result of the sample thermal image includes: S0221: Based on the feature extraction network, perform feature extraction processing on the sample thermal image to obtain sample region category features; the sample region category features include at least one of sample shape features, sample texture features, sample temperature features, and sample spatial features; S0222: Based on the location region segmentation network, the sample region category features are segmented to obtain the sample location region segmentation result.

[0031] In this embodiment of the application, during the construction of the food segmentation model, a feature extraction network can be used to perform corresponding feature extraction processing on the acquired sample thermal imaging images to improve the accuracy of image segmentation. Then, a region segmentation network is used to perform location region segmentation processing on the sample region category features to obtain the sample location region segmentation result for subsequent training. The sample region category features may include at least one of sample shape features, sample texture features, sample temperature features, and sample spatial features, or other features capable of distinguishing cookware from food.

[0032] The embodiments of this application can effectively improve the accuracy of image segmentation by performing feature extraction processing, and more accurately segment food and cookware, thereby effectively improving the accuracy of the food segmentation model.

[0033] In one exemplary embodiment, such as Figure 4 As shown, the feature extraction network includes a shape feature extraction network, a texture feature extraction network, a temperature feature extraction network, and a spatial feature extraction network. The feature extraction process, based on the feature extraction network, performs feature extraction on the sample thermal image to obtain the sample region category features, including: S02211: Based on the shape feature extraction network, the thermal image of the sample is processed to extract shape features to obtain the shape features of the sample; S02212: Based on the texture feature extraction network, the sample thermal image is processed to extract texture features to obtain the sample texture features; S02213: Based on the temperature feature extraction network, the temperature features of the sample thermal image are extracted to obtain the sample temperature features; S02214: Based on the spatial feature extraction network, the spatial features of the sample thermal image are extracted to obtain the sample spatial features; S02215: Determine the sample region category features based on the sample shape features, sample texture features, sample temperature features, and sample spatial features.

[0034] In this embodiment of the application, for the feature extraction part, different features can be used to build corresponding feature extraction networks for feature extraction. Specifically, the feature extraction network can include a shape feature extraction network, a texture feature extraction network, a temperature feature extraction network, and a spatial feature extraction network. After the above four networks perform feature extraction processing, the sample region category features are comprehensively determined based on the extracted features, so as to more accurately segment the images of cookware and food and improve the accuracy of segmentation.

[0035] In this embodiment, the shape feature extraction network can extract shape features from the thermal image of the sample to obtain the sample shape features. Shape features can be approached from two aspects: one is contour smoothness. The contour of a cookware is usually smooth and regular, and its smoothness can be measured by calculating the curvature change of the contour, while the contour of food may be relatively irregular with a large curvature change; the other is shape compactness, which can be calculated by measuring the compactness of the region (such as the ratio of the square of the perimeter to the area). The compactness of a cookware is usually small, close to a regular shape such as a circle or square, while the compactness of food may be large and the shape irregular. Therefore, extracting the shape features of the thermal image can help to separate the cookware from the food.

[0036] In this embodiment of the application, the texture feature extraction network can extract texture features from the sample thermal image to obtain sample texture features. The texture of cookware is usually relatively regular and uniform, with low entropy and high energy, while the texture of food is relatively complex and diverse, with high entropy and low energy.

[0037] In this embodiment, the temperature feature extraction network can extract temperature features from the sample thermal imaging image to obtain the sample temperature features. It can calculate the mean and variance of the temperature in each region (cookware and food) of the thermal imaging image. Cookware typically has a higher mean temperature and a smaller variance (because it is heated more evenly), while the temperature distribution of food may be relatively complex, with a lower mean and a larger variance. The distribution of temperature gradients in the thermal imaging image can also be statistically analyzed using a temperature gradient histogram. The edges of the cookware usually have a larger temperature gradient, forming obvious peaks, while the temperature gradient inside the food area is relatively smaller and more dispersed. Temperature features can also be extracted using the rate of temperature change. A sequence of thermal imaging images is dynamically acquired using an infrared sensor, and the rate of temperature change of each pixel over time is calculated. The rate of temperature change of the cookware may be relatively stable and high, while the rate of temperature change of the food may vary depending on the composition and state of the food.

[0038] In this embodiment, the spatial feature extraction network can extract spatial features from the sample thermal image to obtain sample spatial features. Spatial feature extraction can be performed through relative position and layout. The position of the pot in the image is usually relatively fixed (e.g., located in the center of the image or a specific area), while the food is inside the pot. Whether a pixel is inside the pot can be determined by analyzing the distance between the pixel's position coordinates and the center of the pot. In addition, the layout features of the food in the pot can be considered, such as whether it is concentrated at the bottom or edge of the pot. Furthermore, spatial feature extraction can also be performed by analyzing neighborhood relationships. The relationship between a pixel and its surrounding neighboring pixels can be analyzed. For example, the area around a pot pixel is usually mainly occupied by other pot pixels, while the area around a food pixel may include pot pixels and other food pixels.

[0039] This application embodiment constructs corresponding feature extraction networks for different features to extract features accurately, thereby improving the reliability and accuracy of feature extraction. This allows for a more precise determination of the food's position in the cookware, facilitating precise control of the flame direction.

[0040] In an exemplary embodiment, before predicting the heating trend of the food based on the current temperature distribution data to obtain the target flame intensity and target flame direction of the stove, the method further includes: The sample temperature distribution data of the food sample during the heating process is collected; the sample temperature distribution data is labeled with the sample heating trend label of the food sample. Based on a preset prediction model, the temperature distribution data of the sample is predicted to obtain the predicted heating trend of the sample food. Based on the difference between the sample heating trend prediction result and the sample heating trend label, the preset prediction model is trained to obtain the food heating trend prediction model; The step of predicting the heating trend of the food based on the current temperature distribution data to obtain the target flame intensity and target flame direction of the stove includes: The current temperature distribution data is input into the food heating trend prediction model to obtain the current heating trend of the food, and the target flame intensity and target flame direction are determined based on the current heating trend.

[0041] In this embodiment of the application, a large amount of data can be collected to pre-build a food heating trend prediction model to predict the heating trend of food in the cookware. Based on the heating trend of the food, the flame size and flame direction of the stove can be determined to heat the food more accurately, reduce the area of ​​ineffective heating, and improve energy utilization.

[0042] In this embodiment, sample temperature distribution data of the food sample during the heating process can be collected. The sample temperature distribution data is labeled with the sample heating trend tag of the food sample. Then, based on a preset prediction model, the sample temperature distribution data is predicted to obtain the sample heating trend prediction result of the food sample. Then, based on the difference between the sample heating trend prediction result and the sample heating trend tag, the preset prediction model is trained to finally obtain the food heating trend prediction model. In addition, the food segmentation model and the food heating trend prediction model can be merged into a single data model. The training method can be as described above. When using it, the thermal image is first segmented to locate the position area of ​​the food in the pot. Then, the heating trend of the food is predicted based on the temperature distribution of the food to obtain the target flame intensity (target flame size) and target flame direction corresponding to the current state of the food.

[0043] In this embodiment of the application, the preset prediction model may include a heating trend feature extraction network and a heating trend prediction network. The step of predicting the sample temperature distribution data based on the preset prediction model to obtain the sample food's heating trend prediction result may include: Based on the heating trend feature extraction network, feature extraction processing is performed on the sample temperature distribution data to obtain the sample heating trend features; The heating trend prediction network is used to predict the heating trend characteristics of the sample to obtain the heating trend prediction result of the sample.

[0044] In this embodiment, the aforementioned sample heating trend characteristics may include at least one of sample heating temperature characteristics and sample thermal characteristics, or other characteristics that can predict the heating trend of food. Sample heating temperature characteristics can be extracted by monitoring the temperature at the center of the food, which typically reflects the overall degree of heating; they can also be extracted by acquiring temperature changes on the food surface, which reflects the rate at which heat is transferred to the interior of the food; or they can be extracted by acquiring the rate of temperature change of the food, which reflects the rate at which the food temperature rises or falls, and reflects the efficiency of heating or cooling. Sample thermal characteristics can be extracted based on specific heat capacity, which measures the amount of heat absorbed by food to raise its temperature by one unit; different food components have different specific heat capacities.

[0045] In this embodiment of the application, after obtaining the current temperature distribution data of the food in the cookware, the current temperature distribution data can be input into the food heating trend prediction model for prediction to obtain the current heating trend of the food, and the target flame intensity and target flame direction of the stove can be determined based on the current heating trend.

[0046] This application embodiment pre-constructs a food heating trend prediction model. After obtaining the temperature distribution data of the food in the cookware, it can quickly and accurately predict the heating trend of the food, and determine the heating direction and heating intensity of the stove flame based on the heating trend of the food, effectively improving the heating efficiency of the stove.

[0047] In one exemplary embodiment, such as Figure 5 As shown, the step of segmenting the real-time thermal image to obtain the current food location region within the cookware includes: S21: Adjust the size of the real-time thermal image to obtain a thermal image of a preset size; S22: Input the thermal image of the preset size into the food segmentation model to obtain the current food position area in the cookware.

[0048] In this embodiment of the application, after obtaining the real-time thermal image, the size of the obtained real-time thermal image can be adjusted so that its size can meet the input specifications of the food segmentation model. After inputting the thermal image of the preset size into the food segmentation model, image segmentation can be performed quickly and accurately to obtain the location area of ​​the food in the pot, so as to obtain a more accurate temperature distribution of the food, thereby accurately adjusting the flame size and flame direction of the stove.

[0049] This application embodiment adjusts the size of the acquired thermal imaging image to ensure that its size meets the input requirements of the model, thus guaranteeing the stability and consistency of the model architecture. Furthermore, unifying the image size can optimize the allocation of computing resources and memory, reducing the additional overhead and complexity caused by processing images of different sizes. In addition, unifying the input image size can also ensure that the convolution operation can be performed in a predetermined manner, thereby guaranteeing the accuracy and consistency of feature extraction.

[0050] In one exemplary embodiment, such as Figure 6 As shown, after adjusting the flame of the stove according to the target flame intensity and the target flame direction, the method includes: S61: Based on the infrared sensor, acquire the real-time thermal image of the cookware to obtain an updated thermal image; S62: Segment the updated thermal image to obtain the updated location region of the food, and obtain the updated temperature distribution data of the food based on the updated location region; S63: Based on the updated temperature distribution data, predict the heating trend of the food to obtain the updated target flame intensity and the updated target flame direction, and adjust the flame of the stove according to the updated target flame intensity and the updated target flame direction; S64: When the stove is in operation, repeat the step of acquiring the real-time thermal image of the cookware based on the infrared sensor to obtain an updated thermal image.

[0051] In this embodiment, an infrared sensor can collect thermal images of the cookware and the food inside the cookware in real time. Based on the real-time collected images, the location area of ​​the food is determined. Then, the flame intensity (flame size) and flame direction of the stove are adjusted according to the location area and temperature distribution of the food. After the adjustment is completed, the infrared sensor will continue to collect thermal images to ensure that the flame size and flame direction can be dynamically adjusted continuously during the heating process of the food. This solves the problem that the cooking effect of the food is affected by the inability of the stove flame to be adjusted in time by humans.

[0052] In this embodiment, after the flame adjustment described above, a real-time thermal image of the cookware can be acquired using an infrared sensor to obtain an updated thermal image. This updated thermal image is then segmented to obtain the updated location area of ​​the food. Based on this updated location area, updated temperature distribution data of the food is obtained. The heating trend of the food is then predicted based on the updated temperature distribution data to obtain the updated target flame intensity and direction. The flame of the stove is then adjusted again based on the updated target flame intensity and direction. While the stove is in operation, the above steps are repeated, continuously adjusting the flame size and direction in real time based on the real-time location and state of the food. If the stove is detected to be in a non-operating state, i.e., heating of the food in the cookware is stopped, the above steps of continuous updating and real-time adjustment are stopped. Specifically, the above steps may include: Based on the infrared sensor, a real-time thermal image of the cookware is obtained, and an updated thermal image is obtained. The updated thermal image is segmented to obtain the location region of the food after the update, and the temperature distribution data of the food after the update is obtained based on the location region after the update. The heating trend of food is predicted based on the updated temperature distribution data, and the target flame intensity and target flame direction are obtained after the update. The flame of the stove is then adjusted based on the updated target flame intensity and target flame direction. Based on the infrared sensor, a real-time thermal image of the cookware is obtained, and a second updated thermal image is obtained. The thermal image after the second update is segmented to obtain the location region of the food after the second update, and the temperature distribution data of the food after the second update is obtained based on the location region of the food after the second update. Based on the temperature distribution data after the second update, the heating trend of food is predicted, the target flame intensity and target flame direction after the second update are obtained, and the flame of the stove is adjusted according to the target flame intensity and target flame direction after the second update. If the stove is detected to be in a non-working state, stop the above steps.

[0053] This application embodiment uses an infrared sensor to acquire thermal images of the cookware and the food inside the cookware in real time, enabling dynamic adjustment of the size and direction of the stove flame. This solves the problem that the cooking effect is affected by the inability to adjust the stove flame in time, greatly improving the cooking efficiency of the stove, making the stove flame heat the food more evenly and efficiently, reducing the area of ​​ineffective heating, and improving energy utilization.

[0054] This application embodiment, by setting an infrared sensor within a preset area of ​​the stove, can acquire real-time thermal images of the pot and the food inside. Based on a pre-built data model, the thermal images are segmented, separating the pot from the food. This allows for precise location of the food within the pot and acquisition of temperature distribution data during heating. By predicting the food's temperature distribution data, the heating trend can be predicted, and the stove's flame size and direction can be precisely adjusted in real-time based on this trend. This results in more uniform and efficient heating of the food, reducing ineffective heating areas and significantly improving the stove's cooking efficiency. It solves the problem of cooking effects being affected by the inability to manually adjust the stove's flame in a timely manner, thus improving energy utilization.

[0055] This specification also provides an embodiment of a flame control device for a stove, such as... Figure 7 As shown, an infrared sensor is installed within a preset range of the stove, and the pot on the stove is located within the sensing range of the infrared sensor. The device may include: The real-time thermal imaging acquisition module 710 is used to acquire a real-time thermal image of the pot based on the infrared sensor when the food in the pot is heated using the stove. The current food location area acquisition module 720 is used to segment the location area of ​​the real-time thermal image to obtain the current food location area in the cookware. The current temperature distribution data acquisition module 730 is used to obtain the current temperature distribution data of the food based on the real-time thermal imaging map and the current food location area; the real-time thermal imaging map is marked with the temperature data of each location; The heating trend prediction module 740 is used to predict the heating trend of the food based on the current temperature distribution data, and obtain the target flame intensity and target flame direction of the stove; the heating trend represents the temperature change trend of the food. The adjustment module 750 is used to adjust the flame of the stove according to the target flame intensity and the target flame direction.

[0056] In one exemplary embodiment, the apparatus may further include: The sample thermal imaging acquisition module is used to acquire a sample thermal image of the sample cooker when the sample food is heated in the sample cooker; the sample thermal image is labeled with the sample location area of ​​the sample food. The sample location region segmentation result acquisition module is used to segment the sample thermal image based on a preset segmentation model, locate the location region of the sample food in the sample cookware, and obtain the sample location region segmentation result of the sample thermal image. The food segmentation model training module is used to train the preset segmentation model based on the difference between the segmentation result of the sample location region and the label of the sample location region, so as to obtain the food segmentation model.

[0057] In an exemplary embodiment, the preset segmentation model includes a feature extraction network and a location region segmentation network, and the sample location region segmentation result acquisition module may include; The sample region category feature acquisition unit is used to perform feature extraction processing on the sample thermal image based on the feature extraction network to obtain sample region category features; the sample region category features include at least one of sample shape features, sample texture features, sample temperature features, and sample spatial features; The sample location region segmentation result acquisition unit is used to perform location region segmentation processing on the category features of the sample region based on the location region segmentation network to obtain the sample location region segmentation result.

[0058] In an exemplary embodiment, the feature extraction network includes a shape feature extraction network, a texture feature extraction network, a temperature feature extraction network, and a spatial feature extraction network, and the sample region category feature acquisition unit may include; The sample shape feature acquisition subunit is used to extract shape features from the sample thermal image based on the shape feature extraction network to obtain the sample shape features. The sample texture feature acquisition subunit is used to extract texture features from the sample thermal image based on the texture feature extraction network to obtain the sample texture features. The sample temperature feature acquisition subunit is used to extract temperature features from the sample thermal image based on the temperature feature extraction network to obtain the sample temperature features. The sample spatial feature acquisition subunit is used to extract spatial features from the sample thermal image based on the spatial feature extraction network to obtain the sample spatial features. The sample region category feature determination subunit is used to determine the sample region category feature based on the sample shape feature, the sample texture feature, the sample temperature feature, and the sample spatial feature.

[0059] In one exemplary embodiment, the apparatus may further include: The sample temperature distribution data acquisition module is used to collect sample temperature distribution data of the food sample during the heating process; the sample temperature distribution data is labeled with the sample heating trend label of the food sample. The sample heating trend prediction result acquisition module is used to predict the sample temperature distribution data based on a preset prediction model to obtain the sample heating trend prediction result of the food sample. The food heating trend prediction model acquisition module is used to train the preset prediction model based on the difference between the sample heating trend prediction result and the sample heating trend label, so as to obtain the food heating trend prediction model.

[0060] In an exemplary embodiment, the current food location area acquisition module 720 may include: A size adjustment unit is used to adjust the size of the real-time thermal image to obtain a thermal image of a preset size. The current food location area acquisition unit is used to input the thermal imaging image of the preset size into the food segmentation model to obtain the location area of ​​the food in the pot as the current food location area.

[0061] In one exemplary embodiment, the apparatus may further include: The updated thermal imaging acquisition module is used to acquire the real-time thermal imaging image of the cookware based on the infrared sensor, and obtain the updated thermal imaging image. The updated temperature distribution data acquisition module is used to segment the updated thermal image to obtain the updated location region of the food, and to obtain the updated temperature distribution data of the food based on the updated location region. The update adjustment module is used to predict the heating trend of the food based on the updated temperature distribution data, obtain the updated target flame intensity and the updated target flame direction, and adjust the flame of the stove based on the updated target flame intensity and the updated target flame direction. The repeat module is used to repeat the step of acquiring the real-time thermal image of the cookware based on the infrared sensor to obtain an updated thermal image when the stove is in operation.

[0062] The apparatus and method embodiments described above are based on the same inventive concept.

[0063] This specification provides an intelligent kitchen appliance that can implement the flame control method of the stove provided in the above-described method embodiments. The intelligent kitchen appliance is the stove as described above or a kitchen appliance equipped with the stove as described above. It can predict the heating trend of food and adjust the flame size and direction of the stove in real time and accurately, so that the stove flame heats the food more evenly and efficiently, reduces the area of ​​ineffective heating, greatly improves the cooking efficiency of the stove, and achieves intelligent adjustment without manual intervention, thereby improving the user's intelligent user experience.

[0064] This specification provides an electronic device including a processor and a memory. The memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the flame control method for a stove as provided in the above method embodiments.

[0065] Embodiments of this application also provide a computer-readable storage medium, which can be disposed in a terminal to store at least one instruction or at least one program related to implementing the flame control method of the stove in the method embodiment. The at least one instruction or at least one program is loaded and executed by the processor to implement the flame control method of the stove provided in the above method embodiment.

[0066] Embodiments of this application also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the flame control method for a stove provided in the above-described method embodiments.

[0067] Optionally, in the embodiments of this specification, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0068] The memory described in the embodiments of this specification can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for the functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0069] The flame control method for stoves provided in this specification can be executed on a mobile terminal, computer terminal, server, or similar computing device. Taking running on a server as an example... Figure 8 This is a hardware structure block diagram of a server for a flame control method for a stove provided in an embodiment of this specification. Figure 8As shown, the server 800 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 810 (CPUs 810 may include, but are not limited to, microprocessors (MCUs) or programmable logic devices (FPGAs), a memory 830 for storing data, and one or more storage media 820 (e.g., one or more mass storage devices) for storing application programs 823 or data 822. The memory 830 and storage media 820 may be temporary or persistent storage. The program stored in the storage media 820 may include one or more modules, each module may include a series of instruction operations on the server. Furthermore, the CPU 810 may be configured to communicate with the storage media 820 and execute the series of instruction operations stored in the storage media 820 on the server 800. Server 800 may also include one or more power supplies 860, one or more wired or wireless network interfaces 850, one or more input / output interfaces 840, and / or one or more operating systems 821, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0070] The input / output interface 840 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of server 800. In one example, the input / output interface 840 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the input / output interface 840 may be a radio frequency (RF) module used for wireless communication with the Internet.

[0071] Those skilled in the art will understand that Figure 8 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, server 800 may also include... Figure 8 The more or fewer components shown, or having the same Figure 8 The different configurations shown.

[0072] As can be seen from the embodiments of the flame control method and device for the stove provided in this application, an infrared sensor is set within a preset range of the stove, and the pot on the stove is located within the sensing range of the infrared sensor; when heating food in the pot using the stove, a real-time thermal image of the pot is acquired based on the infrared sensor; the real-time thermal image is segmented into positional regions to obtain the current food position region in the pot; based on the real-time thermal image and the current food position region, the current temperature distribution data of the food is obtained; the real-time thermal image is marked with the temperature data of each position; the heating trend of the food is predicted based on the current temperature distribution data to obtain the target flame intensity and target flame direction of the stove; the heating trend represents the temperature change trend of the food; and the flame of the stove is adjusted according to the target flame intensity and target flame direction. This application, by setting an infrared sensor within a preset area of ​​the stove, can acquire real-time thermal images of the pot and the food inside. Based on a pre-built data model, the thermal images are segmented, separating the pot from the food. This allows for precise location of the food within the pot and acquisition of temperature distribution data during heating. By predicting the food's temperature distribution data, the heating trend can be predicted, and the stove's flame size and direction can be precisely adjusted in real-time based on this trend. This results in more uniform and efficient heating of the food, reducing ineffective heating areas and significantly improving the stove's cooking efficiency. It solves the problem of cooking results being affected by the inability to manually adjust the stove flame in a timely manner, thus improving energy utilization.

[0073] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0074] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0075] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer storage medium, such as a read-only memory, a disk, or an optical disk.

[0076] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A flame control method for a stove, characterized in that, An infrared sensor is installed within a preset range of the stove, and the pot on the stove is located within the sensing range of the infrared sensor. The method includes: When heating food in the pot using the stove, a real-time thermal image of the pot is acquired based on the infrared sensor. The real-time thermal image is segmented into location regions to obtain the current food location region within the cookware. Based on the real-time thermal image and the current food location area, the current temperature distribution data of the food is obtained; the real-time thermal image is marked with the temperature data of each location; Based on the current temperature distribution data, the heating trend of the food is predicted to obtain the target flame intensity and target flame direction of the stove; the heating trend represents the temperature change trend of the food. The flame of the stove is adjusted according to the target flame intensity and the target flame direction.

2. The method according to claim 1, characterized in that, The method for segmenting the real-time thermal image to obtain the current food location region before the food location region in the cookware is determined, includes: A thermal image of the sample cooker is collected when the sample food is heated in the sample cooker; the sample thermal image is labeled with the sample location area of ​​the sample food; The sample thermal image is segmented based on a preset segmentation model to locate the position of the sample food in the sample cookware, thereby obtaining the sample position region segmentation result of the sample thermal image. Based on the difference between the sample location region segmentation result and the sample location region label, the preset segmentation model is trained to obtain the food segmentation model.

3. The method according to claim 2, characterized in that, The preset segmentation model includes a feature extraction network and a location region segmentation network. The process of segmenting the sample thermal image based on the preset segmentation model, locating the position of the sample food within the sample cookware, and obtaining the sample location segmentation result of the sample thermal image includes: The thermal image of the sample is processed by the feature extraction network to obtain sample region category features; the sample region category features include at least one of sample shape features, sample texture features, sample temperature features, and sample spatial features; The location region segmentation network is used to perform location region segmentation on the category features of the sample region to obtain the sample location region segmentation result.

4. The method according to claim 3, characterized in that, The feature extraction network includes a shape feature extraction network, a texture feature extraction network, a temperature feature extraction network, and a spatial feature extraction network. The feature extraction process, based on the feature extraction network, performs feature extraction on the sample thermal image to obtain the sample region category features, including: Based on the shape feature extraction network, the thermal image of the sample is processed to extract shape features to obtain the shape features of the sample; Based on the texture feature extraction network, the sample thermal image is processed to extract texture features to obtain the sample texture features; Based on the temperature feature extraction network, the temperature features of the sample thermal image are extracted to obtain the sample temperature features. Based on the spatial feature extraction network, spatial features are extracted from the thermal image of the sample to obtain the spatial features of the sample. The sample region category features are determined based on the sample shape features, sample texture features, sample temperature features, and sample spatial features.

5. The method according to claim 2, characterized in that, Before predicting the heating trend of the food based on the current temperature distribution data to obtain the target flame intensity and target flame direction of the stove, the method further includes: The sample temperature distribution data of the food sample during the heating process is collected; the sample temperature distribution data is labeled with the sample heating trend label of the food sample. Based on a preset prediction model, the temperature distribution data of the sample is predicted to obtain the predicted heating trend of the sample food. Based on the difference between the sample heating trend prediction result and the sample heating trend label, the preset prediction model is trained to obtain the food heating trend prediction model; The step of predicting the heating trend of the food based on the current temperature distribution data to obtain the target flame intensity and target flame direction of the stove includes: The current temperature distribution data is input into the food heating trend prediction model to obtain the current heating trend of the food, and the target flame intensity and target flame direction are determined based on the current heating trend.

6. The method according to claim 2, characterized in that, The step of segmenting the real-time thermal image to obtain the current food location region within the cookware includes: The real-time thermal image is resized to obtain a thermal image of a preset size; The thermal image of the preset size is input into the food segmentation model to obtain the current food position area in the cookware.

7. The method according to claim 1, characterized in that, After adjusting the flame of the stove according to the target flame intensity and the target flame direction, the method includes: Based on the infrared sensor, the real-time thermal image of the cookware is acquired, and an updated thermal image is obtained. The updated thermal image is segmented to obtain the updated location region of the food, and the updated temperature distribution data of the food is obtained based on the updated location region. The heating trend of the food is predicted based on the updated temperature distribution data to obtain the updated target flame intensity and the updated target flame direction. The flame of the stove is then adjusted based on the updated target flame intensity and the updated target flame direction. With the stove in operation, repeat the step of acquiring the real-time thermal image of the cookware based on the infrared sensor to obtain an updated thermal image.

8. A flame control device for a stove, characterized in that, An infrared sensor is installed within a preset range of the stove, and the pot on the stove is located within the sensing range of the infrared sensor. The device includes: The real-time thermal imaging acquisition module is used to acquire a real-time thermal image of the cookware based on the infrared sensor when the food in the cookware is heated using the stove. The current food location region acquisition module is used to segment the real-time thermal image to obtain the current food location region as the location region of the food in the cookware. The current temperature distribution data acquisition module is used to obtain the current temperature distribution data of the food based on the real-time thermal imaging map and the current food location area; the real-time thermal imaging map is marked with the temperature data of each location; The heating trend prediction module is used to predict the heating trend of the food based on the current temperature distribution data, and to obtain the target flame intensity and target flame direction of the stove; the heating trend represents the temperature change trend of the food. An adjustment module is used to adjust the flame of the stove according to the target flame intensity and the target flame direction.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the flame control method of the stove as described in any one of claims 1-7.

10. A smart kitchen appliance, characterized in that, The intelligent kitchen appliance uses the flame control method of the stove as described in any one of claims 1-7.

Images