Cooking airflow control method and intelligent cooking equipment

Abstract

The invention discloses a cooking airflow control method and intelligent cooking equipment, the method is applied to the intelligent cooking equipment, the intelligent cooking equipment comprises a first airflow module, the first airflow module is used for guiding oil drops, and the method comprises the following steps: in a cooking process, obtaining multi-frame image information; performing cooking action identification on the multi-frame image information to obtain cooking action information, and performing oil drop identification on the multi-frame image information to obtain oil drop density information and oil drop track information; determining target pressure information of the first airflow module according to the cooking action information and the oil drop density information; determining first target angle information of the first airflow module according to the oil drop track information; and controlling the first airflow module to operate based on the target pressure information and the first target angle information. According to the embodiment of the invention, the operation parameters of the airflow module for guiding the oil drops can be accurately regulated and controlled, so that the oil guiding effect is improved, and the oil drop escape is effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of intelligent kitchen appliance technology, and in particular to a cooking airflow control method and intelligent cooking equipment. Background Technology

[0002] With the improvement of people's living standards and the promotion and popularization of technologies such as artificial intelligence, more and more traditional lifestyles are gradually changing. The use of home appliances is gradually moving towards intelligence, bringing more convenience to users, and the functions of various home appliances are also becoming more diversified, among which the application of intelligent cooking is increasing. In the current technology, the oil fumes and exhaust gases generated during the cooking process are discharged by range hoods, but their actual control over the oil fume path is weak, which easily leads to oil fume escape and the oil guiding effect is difficult to achieve as expected. Summary of the Invention

[0003] To address the aforementioned problems in the prior art, this invention discloses a cooking airflow control method and an intelligent cooking device, which can accurately regulate the operating parameters of the airflow module, thereby improving its oil guiding effect and effectively reducing oil droplet escape. The technical solution disclosed in this invention is as follows: According to one aspect of the disclosed embodiments of the present invention, a cooking airflow control method is provided, the method comprising: During the cooking process, acquire multiple frames of image information; Cooking action recognition is performed on the multi-frame image information to obtain cooking action information, and oil droplet recognition is performed on the multi-frame image information to obtain oil droplet density information and oil droplet trajectory information. Based on the cooking action information and the oil droplet density information, the target pressure information of the first airflow module is determined; Based on the oil droplet trajectory information, the first target angle information of the first airflow module is determined; Based on the target pressure information and the first target angle information, the operation of the first airflow module is controlled.

[0004] Optionally, the method further includes: Get the image of the cookware; Perform cookware image recognition on the cookware image to obtain the target curvature information corresponding to the bottom of the cookware; Based on a preset mapping relationship, the second target angle information corresponding to the target curvature information is determined; the preset mapping relationship is used to characterize the correspondence between the curvature information corresponding to the bottom of the cookware and the angle information of the first airflow module; Based on the first target angle information and the second target angle information, the target angle information of the first airflow module is determined; Accordingly, controlling the operation of the first airflow module based on the target pressure information and the first target angle information includes: Based on the target pressure information and the target angle information, the operation of the first airflow module is controlled.

[0005] Optionally, the method further includes: Obtain the distance information between the bottom of the pot and the stove; Based on the distance information, the target curvature information corresponding to the bottom of the cookware is calculated.

[0006] Optionally, the method further includes: Obtain the multi-frame image information, oil mist concentration time-series information, and cookware weight time-series information; The multi-frame image information and the oil mist concentration time-series information are fused to obtain the first fused information; The multi-frame image information and the timing information of the cookware weight are fused to obtain second fused information; Accordingly, the step of performing cooking action recognition on the multi-frame image information to obtain cooking action information, and performing oil droplet recognition on the multi-frame image information to obtain oil droplet density information and oil droplet trajectory information includes: The cooking action information is obtained by performing cooking action recognition on the first fused information, and the oil droplet information and the oil droplet trajectory information are obtained by performing oil droplet recognition on the second fused information.

[0007] Optionally, the method further includes: Oil droplet identification is performed on the multi-frame image information to obtain oil droplet density information, oil droplet trajectory information, and oil droplet size information; The cooking scene information is determined based on the cooking action information, the oil droplet density information, the oil droplet trajectory information, and the oil droplet size information; Based on the cooking scenario information, the third target pressure information, target flow rate information, and target frequency information of the first airflow module are determined.

[0008] Optionally, the first airflow module includes a first airflow submodule and a second airflow submodule, the target pressure information includes first target pressure information of the first airflow submodule and second target pressure information of the second airflow submodule, and determining the target pressure information of the first airflow module based on the cooking action information and the oil droplet density information includes: If the cooking action information includes preset action information, determine the first target pressure information corresponding to the preset action information; Based on the relationship between the oil droplet density information and the preset density threshold, the second target pressure information of the second airflow submodule is determined.

[0009] Optionally, the intelligent cooking device further includes a second airflow module for supplementing the combustion airflow, and the method further includes: Acquire multiple frames of flame images from the stove; The multi-frame flame images are identified to obtain flame area information, flame shape information, flame change information, and combustion efficiency information; Based on the flame area information, flame shape information, flame change information, and combustion efficiency information, the flow rate information of the second airflow module is determined; The second airflow module is controlled to operate based on the flow information.

[0010] Optionally, after controlling the operation of the first airflow module based on the target pressure information and the first target angle information, the method further includes: Obtain updated image information from multiple frames; Cooking action recognition is performed on the multi-frame updated image information to obtain updated cooking action information, and oil droplet recognition is performed on the multi-frame updated image information to obtain updated oil droplet density information and updated oil droplet trajectory information. Based on the updated cooking action information and the updated oil droplet density information, the updated pressure information of the first airflow module is determined; Based on the updated oil droplet trajectory information, the updated angle information of the first airflow module is determined; Based on the updated pressure information and the updated angle information, the first airflow module is controlled to operate.

[0011] According to another aspect of the disclosed embodiments of the present invention, an intelligent cooking device is provided, the intelligent cooking device including a first airflow module for guiding oil droplets, and the intelligent cooking device employing the cooking airflow control method as described in any of the preceding embodiments for cooking airflow control.

[0012] Optionally, the intelligent cooking device further includes an oil droplet-bearing structure. The first airflow module includes a first airflow submodule and a second airflow submodule. The first airflow submodule includes a plurality of first airflow units arranged in sequence, and the second airflow submodule includes a plurality of second airflow units arranged in sequence. The first airflow submodule is used to prevent oil droplet splashing, and the second airflow submodule is used to prevent oil droplet escape and guide oil droplets into the oil droplet-bearing structure. The intelligent cooking device further includes a second airflow module, which is used to supplement the combustion airflow.

[0013] The cooking airflow control method provided by this invention has the following technical effects: The cooking airflow control method provided by this invention is applied to an intelligent cooking device. This intelligent cooking device includes a first airflow module for guiding oil droplets. During the cooking process, the device acquires multiple frames of image information; performs cooking action recognition on the multiple frames of image information to obtain cooking action information; and performs oil droplet recognition on the multiple frames of image information to obtain oil droplet density information and oil droplet trajectory information. Based on the cooking action information and oil droplet density information, the target pressure information of the first airflow module is determined; based on the oil droplet trajectory information, the first target angle information of the first airflow module is determined; and based on the target pressure information and the first target angle information, the operation of the first airflow module is controlled. Thus, based on the multiple frames of image information during the cooking process, the cooking action, oil droplet density, and oil droplet trajectory are determined. Furthermore, the pressure of the airflow module used to guide the oil droplets is determined based on the cooking action and oil droplet density, and the angle of the airflow module is determined based on the oil droplet trajectory. The operation of the airflow module is controlled based on this pressure and angle, thereby accurately regulating the operating parameters of the airflow module, improving its oil guiding effect, effectively reducing oil droplet escape, and avoiding contamination of the cooking device.

[0014] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of airflow in a smart cooking device according to an exemplary embodiment; Figure 2 This is a schematic flowchart illustrating a cooking airflow control method according to an exemplary embodiment; Figure 3 This is a schematic flowchart illustrating a process for determining target angle information of a first airflow module according to an exemplary embodiment; Figure 4 This is a schematic flowchart illustrating the process of determining the operating parameters of a first airflow module according to an exemplary embodiment; Figure 5 This is a schematic flowchart illustrating another cooking airflow control method according to an exemplary embodiment. Detailed Implementation

[0017] To enable those skilled in the art to better understand the technical solutions disclosed in this invention, the technical solutions in the disclosed embodiments will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention 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 the invention disclosed 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 explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0019] The following describes a cooking airflow control method according to this application. This method is applied to an intelligent cooking device, which may include a first airflow module and an oil droplet-bearing structure. The first airflow module can be used to guide oil droplets. Specifically, the first airflow module may include a first airflow submodule and a second airflow submodule. The first airflow submodule can be used to prevent oil droplet splattering, and the second airflow submodule can be used to prevent oil droplet escape and guide oil droplets into the oil droplet-bearing structure, i.e., it can be used for cleaning, keeping the cooktop surface clean. The first airflow submodule may include multiple first airflow units arranged in sequence, and the second airflow submodule may include multiple second airflow units arranged in sequence. Each airflow unit can be a nozzle.

[0020] The airflow directions of the first and second airflow submodules can be found in [reference]. Figure 1 Specifically, multiple first airflow units can be fan-shaped nozzle arrays facing the curved bottom surface of the cookware, forming an inner airflow that adheres to the cookware wall. This creates an "air film" at the edge of the cookware, "pushing" oil droplets about to fly away from the edge back into the cookware, reducing contaminant escape at the source. Multiple second airflow units can consist of two concentric ring nozzle arrays, forming an outer airflow to achieve gradient pressure. Specifically, the two ring nozzle arrays can include an inner ring nozzle array and an outer ring nozzle array. The inner ring nozzle array can be close to the cookware to intercept high-speed escaping oil droplets, while the outer ring nozzle array can be close to the oil droplet-bearing structure to guide the slowed-down oil droplets into the tank with low energy consumption.

[0021] Specifically, the oil droplet-bearing structure can be an oil guide groove installed on the stove near its edge, used to collect oil droplets swept by the airflow. A continuous serrated structure can be provided at the inlet edge of the oil guide groove, which can work with the airflow to generate a low-pressure vortex at the groove opening, increasing the adsorption force. Optionally, this serrated structure can be an asymmetrical serrated structure, with a gentler slope on the guiding side (closer to the stove center) to facilitate airflow introduction, and a steeper slope on the outer side to facilitate vortex formation. In practical applications, when the high-speed outer sweeping airflow is sprayed onto the serrated edge, the continuous serrations cut and separate the originally stable airflow into a series of micro-vortices, and can generate a local low-pressure zone at the serrated gaps. This low-pressure zone will exert a strong adsorption effect on the oil droplets about to pass the groove opening, "pulling" them into the oil guide groove. In addition, the vortex can effectively agitate the oil droplets, overcome their surface tension, making them easier to separate from the airflow and merge into the oil flow, rather than agglomerating into large oil droplets adhering to the groove opening.

[0022] Optionally, the aforementioned intelligent cooking device may also include a second airflow module, which can be used to supplement the combustion airflow. The second airflow module can be located near the burner to form a supplementary airflow, which is used to supplement oxygen, improve combustion efficiency, and stabilize the flame shape.

[0023] Figure 2 This is a flowchart illustrating a cooking airflow control method according to an exemplary embodiment. This specification provides the operational steps of the method as described in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or server products, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment). Specifically, as... Figure 2 As shown, the above method may include: S201: Acquire multiple frames of image information during the cooking process.

[0024] In one specific embodiment, each frame of image information can be image information covering the pot and stove area. Specifically, it can include top-view image information covering the pot and stove area, and top-view and side-view image information covering the pot and stove area. Multiple frames of image information can be continuously acquired by a camera module based on a preset acquisition frame rate. This camera module can be set or integrated into the range hood. The preset acquisition frame rate can be set according to actual application requirements, for example, it can be set to 15-30 fps.

[0025] S203: Perform cooking action recognition on multi-frame image information to obtain cooking action information, and perform oil droplet recognition on multi-frame image information to obtain oil droplet density information and oil droplet trajectory information.

[0026] In one specific embodiment, cooking action information may include cooking actions such as adding ingredients, stir-frying, shaking the pan, and removing from the pan. Optionally, cooking action recognition can be performed on multiple frames of image information using a trained temporal action recognition network to obtain the aforementioned cooking action information. Specifically, the temporal action recognition network can be selected and set according to actual application requirements, such as a 3D-Convolutional Neural Network (3D-CNN), a Transformer network, etc. Optionally, performing cooking action recognition on multiple frames of image information can obtain cooking action information and corresponding confidence information. This allows the corresponding cooking action information to be determined when the confidence information is greater than a preset confidence threshold, i.e., when the confidence is high, thus improving the accuracy of cooking action recognition and ensuring the accuracy of subsequent processing. The preset confidence threshold can be set according to actual application requirements.

[0027] In one specific embodiment, the oil droplet density information can be the ratio of the total area of ​​oil droplet pixels to the area of ​​the stove surface region in each frame of the image, and the oil droplet trajectory information can include the direction and velocity information of the oil droplet's movement. Optionally, pixel-level oil droplet recognition can be performed on multiple frames of image information using a trained instance segmentation network or optical flow method to obtain the aforementioned oil droplet density information and oil droplet trajectory information. Specifically, the instance segmentation network can be selected and configured according to actual application requirements, for example, it can be a Mask R-CNN (Mask Region-based Convolutional Neural Network) network.

[0028] Optionally, the above method may also include: Acquire multi-frame image information, oil mist concentration time-series information, and cookware weight time-series information; The first fused information is obtained by fusing multi-frame image information and oil mist concentration time-series information. The second fused information is obtained by fusing multi-frame image information and the timing information of the pot weight.

[0029] In one specific embodiment, the time-series information of oil mist concentration can be continuously collected using an infrared sensor, and the time-series information of cookware weight can be continuously collected using a weight sensor. Optionally, the multi-frame image information, oil mist concentration time-series information, and cookware weight time-series information can be time-aligned first, and then the above-mentioned fusion processing can be performed based on a trained fusion network to obtain the first fused information and the second fused information. Specifically, the fusion network can be selected and set according to actual application requirements. Optionally, audio data can also be collected through a microphone to extract oil popping sound features, which can then be fused with different modal information such as images, oil mist concentration, and cookware weight to enhance the accuracy of subsequent cooking state judgment.

[0030] Accordingly, the above-mentioned cooking action recognition of multi-frame image information to obtain cooking action information, and oil droplet recognition of multi-frame image information to obtain oil droplet density information and oil droplet trajectory information may include: The cooking action is identified from the first fused information to obtain cooking action information, and the oil droplet is identified from the second fused information to obtain oil droplet density information and oil droplet trajectory information.

[0031] S205: Determine the target pressure information of the first airflow module based on the cooking action information and oil droplet density information.

[0032] In one specific embodiment, the target pressure information may include first target pressure information of the first airflow submodule and second target pressure information of the second airflow submodule.

[0033] Optionally, determining the target pressure information of the first airflow module based on cooking action information and oil droplet density information may include: When the cooking action information includes preset action information, determine the first target pressure information corresponding to the preset action information; Based on the relationship between oil droplet density information and preset density threshold, the second target pressure information of the second airflow submodule is determined.

[0034] In one specific embodiment, the preset action information may include cooking action information such as adding ingredients and stir-frying. Optionally, the pressure information (first target pressure information) of the first airflow submodule corresponding to the preset action information can be determined based on a preset correspondence between the cooking action information and the pressure information of the first airflow submodule. The preset correspondence can be set according to actual application requirements. Optionally, when the cooking action information includes the preset action information, the pressure information of the first airflow submodule can be adjusted to the first target pressure information.

[0035] In one specific embodiment, the pressure information (second target pressure information) of the second airflow submodule corresponding to the oil droplet density information can be determined according to the preset correspondence between the oil droplet density information and the pressure information of the second airflow submodule. The preset correspondence and preset density threshold can be set according to actual application requirements. The larger the oil droplet density, the larger the pressure information of the corresponding second airflow submodule.

[0036] Optionally, based on the relationship between the oil droplet density information and a preset density threshold, the pressure information of the inner and outer ring airflow units in the second airflow submodule can be determined. Specifically, when the oil droplet density information is greater than the preset density threshold, the pressure information of the inner ring airflow unit in the second airflow submodule can be determined to be 0.45 MPa, and the pressure information of the outer ring airflow unit can be determined to be 0.25 MPa. When the oil droplet density information is less than or equal to the aforementioned preset density threshold, the pressure information of the inner ring airflow unit in the second airflow submodule can be determined to be 0.3 MPa, and the pressure information of the outer ring airflow unit can be 0.15 MPa. Specifically, when the oil droplet density information is greater than the preset density threshold, the pulse in the second airflow submodule can be high-frequency; when the oil droplet density information is less than or equal to the preset density threshold, the pulse in the second airflow submodule can be low-frequency.

[0037] S207: Determine the first target angle information of the first airflow module based on the oil droplet trajectory information.

[0038] Specifically, the angle of the nozzle in the first airflow module can be adjusted according to the trajectory of the oil droplets, such as the direction of movement of the oil droplets, so that the air film formed by the ejected airflow can better guide the oil droplets, intercept the escaping oil droplets, and guide the oil droplets into the oil guide groove.

[0039] S209: Control the operation of the first airflow module based on the target pressure information and the first target angle information.

[0040] Specifically, the target pressure information and the first target angle information are set as the pressure information and angle information of the first airflow module, and the operation of the first airflow module is controlled based on this.

[0041] In an optional embodiment, such as Figure 3 As shown, the above method may further include: S301: Obtain the image of the cookware.

[0042] S303: Perform cookware image recognition on the cookware image to obtain the target curvature information corresponding to the bottom of the cookware.

[0043] In one specific embodiment, the target curvature information corresponding to the bottom of the pot can be calculated by analyzing and recognizing the image of the pot and fitting the contour curve of the bottom of the pot. This target curvature information can be the radius of curvature of the contour curve of the bottom of the pot.

[0044] S305: Based on the preset mapping relationship, determine the second target angle information corresponding to the target radian information.

[0045] In one specific embodiment, the aforementioned preset mapping relationship can be used to characterize the correspondence between the curvature information corresponding to the bottom of the cookware and the angle information of the first airflow module. The larger the curvature information corresponding to the bottom of the cookware, the larger the angle information of the corresponding first airflow module can be. Specifically, this preset mapping relationship can be set according to actual application requirements.

[0046] Optionally, the cookware image can be recognized to obtain the cookware type, and then the angle information of the first airflow module corresponding to the cookware type can be determined based on the correspondence. Alternatively, after determining the cookware type, the curvature feature coefficient corresponding to the cookware type can be determined based on the correspondence, and then the angle information of the first airflow module corresponding to the curvature feature coefficient can be determined based on the correspondence. Specifically, when the cookware type is a round-bottomed cookware, the angle information of the corresponding first airflow module can be 38 degrees to 40 degrees; when the cookware type is a flat-bottomed cookware, the angle information of the corresponding first airflow module can be 10 degrees to 15 degrees.

[0047] S307: Based on the first target angle information and the second target angle information, determine the target angle information of the first airflow module.

[0048] In one specific embodiment, the angle of the first airflow module can be comprehensively adjusted based on the cooking conditions and the type of cookware to determine the aforementioned target angle information.

[0049] Optionally, the above method may also include: Obtain the distance information between the bottom of the pot and the stove; Based on the distance information, the target curvature information corresponding to the bottom of the cookware is calculated.

[0050] In one specific embodiment, the distance information between multiple points on the bottom of the pot and the stove surface can be determined by a distance measuring sensor, and the target curvature information corresponding to the bottom of the pot can be calculated by multi-point height values.

[0051] Accordingly, controlling the operation of the first airflow module based on the target pressure information and the first target angle information may include: The operation of the first airflow module is controlled based on the target pressure information and the target angle information.

[0052] In an optional embodiment, such as Figure 4 As shown, the above method may further include: S401: Perform oil droplet recognition on multiple frames of image information to obtain oil droplet density information, oil droplet trajectory information, and oil droplet size information.

[0053] In one specific embodiment, oil droplet size information can be used to distinguish between large oil droplets and fine oil mist.

[0054] S403: Determine cooking scene information based on cooking action information, oil droplet density information, oil droplet trajectory information, and oil droplet size information.

[0055] In one specific embodiment, the cooking scenario information may include cooking scenarios such as stir-frying, deep-frying, stewing, and letting it sit.

[0056] S405: Based on the cooking scenario information, determine the third target pressure information, target flow information, and target frequency information of the first airflow module.

[0057] In one specific embodiment, the more intense the cooking scenario, the higher the third target pressure information, target flow information, and target frequency information of the first airflow module. For example, in the case of a stir-fry scenario, the operating parameters of the first airflow module can be high pressure, high flow, and high frequency; in the case of a stewing scenario, the operating parameters of the first airflow module can be low pressure, low flow, and low frequency.

[0058] In an optional embodiment, such as Figure 5 As shown, the above method may further include: S501: Acquire multiple frames of flame images from the stove.

[0059] S503: Recognize multiple frames of flame images to obtain flame area information, flame shape information, flame change information, and combustion efficiency information.

[0060] In one specific embodiment, flame pixel regions in an image can be identified, and the aforementioned flame area information, flame morphology information, flame change information, and combustion efficiency information can be calculated. Specifically, the flame area information can be the flame pixel area, which can be used to reflect the firepower. The flame morphology information can be the aspect ratio of the minimum bounding rectangle of the flame binary mask. If the flame morphology information is less than a first preset threshold, it indicates that the flame is diffuse and weak, suggesting possible insufficient gas pressure or insufficient secondary air supply. If the flame morphology information is greater than or equal to the first preset threshold and less than or equal to a second preset threshold, it indicates that the flame is strong and powerful, representing an ideal state. If the flame morphology information is greater than the second preset threshold, it indicates that the flame is too intense and too high, posing a risk of detaching from the burner or being blown out, possibly due to excessive gas supply or excessive gas pressure. Specifically, the first and second preset thresholds can be set according to actual application requirements; for example, the first preset threshold can be set to 1.5, and the second preset threshold can be set to 2.5.

[0061] Specifically, flame variation information can be used to characterize flame stability. This information can be expressed as the average pixel jitter distance or the rate of change of the flame edge contour area over a period of time or between consecutive frames. A higher value indicates a more stable flame. Combustion efficiency information can be used to characterize the degree of combustion completeness. Specifically, it can be expressed as the ratio between the number of blue pixels and the total number of pixels in the HSV color space. A higher value indicates more complete combustion.

[0062] S505: Determine the flow rate information of the second airflow module based on flame area information, flame shape information, flame change information, and combustion efficiency information.

[0063] In one specific embodiment, when the flame morphology information is less than a first preset morphology threshold and the combustion efficiency information is less than a preset efficiency threshold (i.e., the flame is divergent and combustion is incomplete), it is necessary to increase the supplementary air supply. Specifically, this can be achieved by increasing the current flow rate and swirl intensity of the second airflow module. When the flame change information is less than a preset change threshold, and the flame morphology information is greater than or equal to the first preset morphology threshold and less than or equal to the second preset morphology threshold (i.e., the flame is flickering or unstable), it is necessary to increase the supplementary air supply. Specifically, this can be achieved by increasing the current flow rate and swirl intensity of the second airflow module to stabilize the flame. When the flame morphology information is greater than the second preset morphology threshold (i.e., the flame is overly vigorous), it is necessary to reduce the supplementary air supply. Specifically, this can be achieved by reducing the current flow rate of the second airflow module. When the flame area information is less than a preset area threshold, and the combustion efficiency information is greater than or equal to the preset efficiency threshold and the flame morphology information is greater than a third preset morphology threshold (i.e., the low flame condition is good), it is necessary to maintain or reduce the current supplementary air supply flow rate. Specifically, this can be achieved by maintaining or slightly reducing the current flow rate of the second airflow module. The above flow rates can be adjusted by a proportional valve, and the swirl intensity can be adjusted by a swirl mechanism. Specifically, the first preset shape threshold, the second preset shape threshold, the third preset shape threshold, the preset efficiency threshold, the preset change threshold, the preset area threshold, and the preset efficiency threshold can be set according to actual application requirements.

[0064] S507: Controls the operation of the second airflow module based on flow information.

[0065] In an optional embodiment, after controlling the operation of the first airflow module based on the target pressure information and the first target angle information, the method may further include: Obtain updated image information from multiple frames; Cooking action recognition is performed on multiple frames of updated image information to obtain updated cooking action information, and oil droplet recognition is performed on multiple frames of updated image information to obtain updated oil droplet density information and updated oil droplet trajectory information. Based on the updated cooking action information and the updated oil droplet density information, the updated pressure information of the first airflow module is determined; Based on the updated oil droplet trajectory information, the updated angle information of the first airflow module is determined; The operation of the first airflow module is controlled based on updated pressure and angle information.

[0066] In one specific embodiment, the results after the execution of the control strategy can be continuously monitored (such as whether the oil droplet density decreases, whether the stove surface is clean, and whether the flame returns to stability) as feedback on the control effect, and the operating parameters of the airflow module (such as pressure value and pulse frequency) can be adjusted and updated based on the feedback signal.

[0067] Optionally, the running time of the airflow module can be delayed after cooking to further ensure the oil guiding effect.

[0068] As can be seen from the technical solutions provided in the embodiments of this specification above, during the cooking process, multiple frames of image information are acquired; cooking action recognition is performed on the multiple frames of image information to obtain cooking action information, and oil droplet recognition is performed on the multiple frames of image information to obtain oil droplet density information and oil droplet trajectory information; based on the cooking action information and oil droplet density information, the target pressure information of the first airflow module is determined; based on the oil droplet trajectory information, the first target angle information of the first airflow module is determined; and based on the target pressure information and the first target angle information, the operation of the first airflow module is controlled. Therefore, based on the multiple frames of image information during the cooking process, the cooking action, oil droplet density, and oil droplet trajectory are determined, and then the pressure of the airflow module used to guide the oil droplets is determined based on the cooking action and oil droplet density, and the angle of the airflow module is determined based on the oil droplet trajectory. The operation of the airflow module is controlled based on this pressure and angle, thereby accurately regulating the operating parameters of the airflow module, thereby improving its oil guiding effect, effectively reducing oil droplet escape, and avoiding contamination of the cooking equipment.

[0069] The present invention also provides an intelligent cooking device, which may include a first airflow module for guiding oil droplets. The intelligent cooking device can employ the aforementioned cooking airflow control method for cooking airflow control. Specifically, the intelligent cooking device can be a stove, integrated stove, etc.

[0070] Optionally, the intelligent cooking device may also include an oil droplet-bearing structure. The first airflow module may include a first airflow submodule and a second airflow submodule. The first airflow submodule may include multiple first airflow units arranged in sequence, and the second airflow submodule may include multiple second airflow units arranged in sequence. The first airflow submodule can be used to prevent oil droplet splashing, and the second airflow submodule can be used to prevent oil droplet escape and guide oil droplets into the oil droplet-bearing structure. The intelligent cooking device may also include a second airflow module, which can be used to supplement the combustion airflow.

[0071] Regarding the device in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0072] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0073] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles disclosed herein and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0074] It should be understood that the present invention is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is limited only by the appended claims.

Claims

1. A cooking airflow control method, characterized in that, The method is applied to a smart cooking device, the smart cooking device including a first airflow module, the first airflow module being used to guide oil droplets, the method comprising: During the cooking process, acquire multiple frames of image information; Cooking action recognition is performed on the multi-frame image information to obtain cooking action information, and oil droplet recognition is performed on the multi-frame image information to obtain oil droplet density information and oil droplet trajectory information. Based on the cooking action information and the oil droplet density information, the target pressure information of the first airflow module is determined; Based on the oil droplet trajectory information, the first target angle information of the first airflow module is determined; Based on the target pressure information and the first target angle information, the operation of the first airflow module is controlled.

2. The method according to claim 1, characterized in that, The method further includes: Get the image of the cookware; Perform cookware image recognition on the cookware image to obtain the target curvature information corresponding to the bottom of the cookware; Based on a preset mapping relationship, the second target angle information corresponding to the target curvature information is determined; the preset mapping relationship is used to characterize the correspondence between the curvature information corresponding to the bottom of the cookware and the angle information of the first airflow module; Based on the first target angle information and the second target angle information, the target angle information of the first airflow module is determined; Accordingly, controlling the operation of the first airflow module based on the target pressure information and the first target angle information includes: Based on the target pressure information and the target angle information, the operation of the first airflow module is controlled.

3. The method according to claim 2, characterized in that, The method further includes: Obtain the distance information between the bottom of the pot and the stove; Based on the distance information, the target curvature information corresponding to the bottom of the cookware is calculated.

4. The method according to claim 1, characterized in that, The method further includes: Obtain the multi-frame image information, oil mist concentration time-series information, and cookware weight time-series information; The multi-frame image information and the oil mist concentration time-series information are fused to obtain the first fused information; The multi-frame image information and the timing information of the cookware weight are fused to obtain second fused information; Accordingly, the step of performing cooking action recognition on the multi-frame image information to obtain cooking action information, and performing oil droplet recognition on the multi-frame image information to obtain oil droplet density information and oil droplet trajectory information includes: The cooking action information is obtained by performing cooking action recognition on the first fused information, and the oil droplet information and the oil droplet trajectory information are obtained by performing oil droplet recognition on the second fused information.

5. The method according to claim 1, characterized in that, The method further includes: Oil droplet identification is performed on the multi-frame image information to obtain oil droplet density information, oil droplet trajectory information, and oil droplet size information; The cooking scene information is determined based on the cooking action information, the oil droplet density information, the oil droplet trajectory information, and the oil droplet size information; Based on the cooking scenario information, the third target pressure information, target flow rate information, and target frequency information of the first airflow module are determined.

6. The method according to claim 1, characterized in that, The first airflow module includes a first airflow submodule and a second airflow submodule. The target pressure information includes first target pressure information of the first airflow submodule and second target pressure information of the second airflow submodule. Determining the target pressure information of the first airflow module based on the cooking action information and the oil droplet density information includes: If the cooking action information includes preset action information, determine the first target pressure information corresponding to the preset action information; Based on the relationship between the oil droplet density information and the preset density threshold, the second target pressure information of the second airflow submodule is determined.

7. The method according to claim 1, characterized in that, The intelligent cooking device further includes a second airflow module, which is used to supplement the combustion airflow. The method further includes: Acquire multiple frames of flame images from the stove; The multi-frame flame images are identified to obtain flame area information, flame shape information, flame change information, and combustion efficiency information; Based on the flame area information, flame shape information, flame change information, and combustion efficiency information, the flow rate information of the second airflow module is determined; The second airflow module is controlled to operate based on the flow information.

8. The method according to any one of claims 1 to 7, characterized in that, After controlling the operation of the first airflow module based on the target pressure information and the first target angle information, the method further includes: Obtain updated image information from multiple frames; Cooking action recognition is performed on the multi-frame updated image information to obtain updated cooking action information, and oil droplet recognition is performed on the multi-frame updated image information to obtain updated oil droplet density information and updated oil droplet trajectory information. Based on the updated cooking action information and the updated oil droplet density information, the updated pressure information of the first airflow module is determined; Based on the updated oil droplet trajectory information, the updated angle information of the first airflow module is determined; Based on the updated pressure information and the updated angle information, the first airflow module is controlled to operate.

9. A smart cooking device, characterized in that, The intelligent cooking device includes a first airflow module for guiding oil droplets, and the intelligent cooking device uses the cooking airflow control method as described in any one of claims 1 to 8 to control the cooking airflow.

10. The intelligent cooking device according to claim 9, characterized in that, The intelligent cooking device also includes an oil droplet carrying structure. The first airflow module includes a first airflow submodule and a second airflow submodule. The first airflow submodule includes a plurality of first airflow units arranged in sequence, and the second airflow submodule includes a plurality of second airflow units arranged in sequence. The first airflow submodule is used to prevent oil droplet splashing, and the second airflow submodule is used to prevent oil droplet escape and guide oil droplets into the oil droplet carrying structure. The intelligent cooking device also includes a second airflow module, which is used to supplement the combustion airflow.

Images