Cooking control method and system

Abstract

The application discloses a cooking control method and system, which comprises the following steps: when the distance between a mobile terminal and a communication tag on a smart cooking device is less than a preset distance threshold, the mobile terminal calls a cooking application; a cloud end receives an image of a cooking material collected by the cooking application, and identifies the image of the cooking material to obtain a target material type and a target detection frame; the mobile terminal reconstructs a target detection point in the target detection frame to obtain three-dimensional attribute information of the cooking material; the three-dimensional attribute information comprises actual weight information; the mobile terminal determines a target recipe of the cooking material based on the target material type and the actual weight information, adjusts initial cooking parameters in the target recipe according to the actual weight information to obtain target cooking parameters, and the smart cooking device cooks the cooking material based on the target cooking parameters. The application can realize precise intelligent cooking and improve cooking effect.

Description

Technical Field

[0001] This invention relates to the field of intelligent electrical appliance technology, and in particular to a cooking control method and system. 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. While bringing more convenience to users, the functions of various home appliances are also becoming more diversified, and the application of smart appliances is increasing. In the current technology, users can obtain standardized recipes through applications installed on mobile terminals and complete cooking according to the instructions. Usually, users need to manually start the cooking application, select the corresponding recipe, and manually adjust the cooking parameters. The operation process is relatively cumbersome, the user threshold is high, and it is easy to lead to poor cooking results, making it difficult to achieve precise automated intelligent cooking. Summary of the Invention

[0003] To address the aforementioned problems in the prior art, this invention discloses a cooking control method and system that can achieve precise and intelligent cooking, thereby improving cooking results. The technical solution disclosed in this invention is as follows: According to one aspect of the disclosed embodiments of the present invention, a cooking control method is provided, the method comprising: When the distance between the mobile terminal and the communication tag is less than a preset distance threshold, the mobile terminal invokes a cooking application; the communication tag is set on the smart cooking device. The cloud receives images of the ingredients to be cooked collected by the cooking application, and identifies the images of the ingredients to be cooked to obtain the target ingredient type and target detection box of the ingredients to be cooked; the images of the ingredients to be cooked are collected by the cooking application through the mobile terminal; The mobile terminal reconstructs the target detection points in the target detection frame to obtain the three-dimensional attribute information of the food to be cooked; the three-dimensional attribute information includes actual weight information. The mobile terminal determines the target recipe for the ingredients to be cooked based on the target ingredient type and the actual weight information. The mobile terminal adjusts the initial cooking parameters in the target recipe based on the actual weight information to obtain the target cooking parameters; The intelligent cooking device cooks the ingredients to be cooked based on the target cooking parameters.

[0004] Optionally, the target recipe includes preset weight information and cooking method information, and the initial cooking parameters include initial cooking temperature information and initial cooking time information. Adjusting the initial cooking parameters in the target recipe based on the actual weight information to obtain the target cooking parameters includes: The ratio between the actual weight information and the preset weight information is determined as the weight adjustment coefficient; the weight adjustment coefficient is used to characterize the degree of deviation between the actual weight information and the preset weight information. Based on the weight adjustment coefficient, the initial cooking temperature information is adjusted to obtain the target cooking temperature information; Based on the weight adjustment coefficient and the cooking method information, the initial cooking time information is adjusted to obtain the target cooking time information.

[0005] Optionally, adjusting the initial cooking temperature information based on the weight adjustment coefficient to obtain the target cooking temperature information includes: The difference between the weight adjustment coefficient and the preset value is multiplied by the thermal property coefficient of the intelligent cooking device, and the resulting product is used as the exponent information of the natural base to obtain the natural index. The difference between the preset value and the natural index is multiplied by the upper limit temperature adjustment information to obtain the target temperature adjustment information; The initial cooking temperature information and the target temperature adjustment information are added together to obtain the target cooking temperature information.

[0006] Optionally, adjusting the initial cooking time information based on the weight adjustment coefficient and the cooking method information to obtain the target cooking time information includes: Based on a preset mapping relationship, the cooking method coefficient corresponding to the cooking method information is determined; the preset mapping relationship is used to characterize the correspondence between the cooking method information and the cooking method coefficient. Using the weight adjustment coefficient as the base and the cooking method coefficient as the exponent, the target index is obtained; The target cooking time information is obtained by multiplying the target index and the initial cooking time information.

[0007] Optionally, reconstructing the target detection points in the target detection box to obtain the three-dimensional attribute information of the food to be cooked includes: Extract the transformation matrix corresponding to the target detection point; the transformation matrix is ​​used to characterize the position information of the food to be cooked at the target detection point relative to the world coordinate system; The three-dimensional coordinate information of the target detection point in the world coordinate system is determined from the transformation matrix; The actual weight information is calculated based on the three-dimensional coordinate information.

[0008] Optionally, the target detection points include a first boundary detection point and a second boundary detection point, and the calculation of the actual weight information based on the three-dimensional coordinate information includes: Based on the first three-dimensional coordinate information of the first boundary detection point and the second three-dimensional coordinate information of the second boundary detection point in each three-dimensional direction, the distance between the first boundary detection point and the second boundary detection point is calculated to obtain the target distance; The target distances in each of the three dimensions are determined as the length, width, and height information of the three-dimensional detection frame corresponding to the food to be cooked. The length information, the width information, and the height information are multiplied together to obtain the volume information corresponding to the ingredient to be cooked. The density information and volume information of the food to be cooked are multiplied together to obtain the actual weight information.

[0009] Optionally, the target recipe includes preset weight information, and determining the target recipe for the ingredient to be cooked based on the target ingredient type and the actual weight information includes: Obtain users' health data; The quantity ratio information between the target ingredient type and the preset ingredient type in the target recipe is determined as the ingredient matching index corresponding to the ingredient to be cooked; Based on the degree of matching between the actual weight information and the preset weight information, the weight matching index corresponding to the ingredient to be cooked is determined. Based on the degree of matching between the health data and the target recipe, the health matching index corresponding to the ingredients to be cooked is determined; The food matching index, the weight matching index, and the health matching index are weighted and summed to obtain a comprehensive matching index. Based on the comprehensive matching index, the candidate recipes for the ingredients to be cooked are sorted to obtain the target recipe.

[0010] Optionally, the method further includes: If the ingredient matching index is less than a first preset matching threshold, and / or the weight matching index is less than a second preset matching threshold, the corresponding recipe will not be considered as a candidate recipe.

[0011] Optionally, the intelligent cooking device is at least one of a food processor, a steam oven, a pressure cooker, and an air fryer.

[0012] According to another aspect of the disclosed embodiments of the present invention, a cooking control system is provided. The system includes an intelligent cooking device, a mobile terminal, a cloud, and a control module. The intelligent cooking device is communicatively connected to the mobile terminal, and the mobile terminal is communicatively connected to the cloud. The control module is communicatively connected to the intelligent cooking device, the mobile terminal, and the cloud, respectively. The control module is used to control the intelligent cooking device, the mobile terminal, and the cloud to execute the cooking control method as described in any of the above embodiments. The mobile terminal is used to invoke a cooking application when the distance between the mobile terminal and the communication tag is less than a preset distance threshold; and to capture images of the ingredients to be cooked and send them to the cloud; the communication tag is set on the smart cooking device; The cloud is used to receive images of the ingredients to be cooked, identify the images of the ingredients to be cooked, obtain the target ingredient type and target detection box of the ingredients to be cooked, and send the target detection box to the mobile terminal; The mobile terminal is also used to reconstruct the target detection points in the target detection frame to obtain the three-dimensional attribute information of the food to be cooked; the three-dimensional attribute information includes actual weight information; and is used to determine the target recipe of the food to be cooked based on the target food type and the actual weight information; and is used to adjust the initial cooking parameters in the target recipe according to the actual weight information to obtain the target cooking parameters, and send them to the smart cooking device. The intelligent cooking device is used to cook the ingredients to be cooked based on the target cooking parameters.

[0013] The cooking control method and system provided by this invention have the following technical effects: The cooking control method provided by this invention includes the following steps: when the distance between a mobile terminal and a communication tag is less than a preset distance threshold, the mobile terminal invokes a cooking application, wherein the communication tag is set on a smart cooking device; further, the cloud receives images of the ingredients to be cooked collected by the cooking application, and identifies the images of the ingredients to be cooked to obtain the target ingredient type and target detection box of the ingredients to be cooked, wherein the images of the ingredients to be cooked are collected by the cooking application through the mobile terminal; then, the mobile terminal reconstructs the target detection points in the target detection box to obtain the three-dimensional attribute information of the ingredients to be cooked; the three-dimensional attribute information includes actual weight information, and based on the target ingredient type and actual weight information, a target recipe for the ingredients to be cooked is determined, and the initial cooking parameters in the target recipe are adjusted according to the actual weight information to obtain target cooking parameters; then, the smart cooking device cooks the ingredients to be cooked based on the target cooking parameters.

[0014] Therefore, by using near-field communication tags to simplify device interaction and application activation paths, and combining cloud-based image recognition and terminal 3D reconstruction technologies, the actual weight of ingredients can be accurately calculated while accurately identifying the types of ingredients. This allows cooking parameters to be precisely matched with ingredient quantities, achieving precise and intelligent cooking and improving cooking results.

[0015] 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

[0016] 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.

[0017] Figure 1 This is a schematic flowchart illustrating a cooking control method according to an exemplary embodiment; Figure 2 This is a schematic diagram illustrating a process for determining the actual weight information of ingredients to be cooked, according to an exemplary embodiment. Figure 3 This is a schematic diagram illustrating a process for determining a target recipe according to an exemplary embodiment; Figure 4 This is a schematic diagram illustrating a process for determining a target cooking coefficient according to an exemplary embodiment. Detailed Implementation

[0018] 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.

[0019] 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.

[0020] The following describes a cooking control method according to this application. Figure 1 This is a flowchart illustrating a cooking 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 1 As shown, the above method may include: S101: When the distance between the mobile terminal and the communication tag is less than a preset distance threshold, the mobile terminal calls the cooking application.

[0021] In one specific embodiment, the smart cooking device can be any device requiring cooking control. Specifically, the smart cooking device can include a food processor, steam oven, pressure cooker, and air fryer. A communication tag can be attached to the smart cooking device; specifically, the communication tag can be a Near Field Communication (NFC) tag. The mobile terminal can be a portable smart device carried by the user, possessing short-range wireless communication and distance measurement capabilities, including but not limited to smartphones, tablets, smartwatches, and smart bracelets. In this embodiment, the mobile terminal has a built-in distance detection module that can receive broadcast signals from the communication tag and calculate the real-time straight-line distance between itself and the communication tag based on Time of Flight (ToF), Received Signal Strength Indication (RSSI), or Angle of Arrival (AoA) algorithms. The cooking application can be a software program running on the mobile terminal for implementing cooking-related functions, specifically including but not limited to smart kitchen appliance control clients, recipe recommendation applications, ingredient traceability management applications, and kitchen safety monitoring applications. Specifically, the preset distance threshold can be set according to actual application needs. In practical applications, mobile devices can be brought close to the NFC tag installed in the cooking equipment (such as through a tap-to-operate method) to launch the cooking app.

[0022] S103: The cloud receives images of the ingredients to be cooked collected by the cooking application, identifies the images of the ingredients to be cooked, and obtains the target ingredient type and target detection box of the ingredients to be cooked.

[0023] In one specific embodiment, the image of the food to be cooked can be acquired by a cooking application via a mobile terminal. The cloud can be a distributed cloud server cluster deployed on the internet side, equipped with a deep learning model for food recognition, or an edge computing node deployed within a home LAN (such as a smart router or home private cloud), possessing high-performance computing power and dynamic model update capabilities. The target food type can be the classification result of the food to be cooked output by the cloud recognition model, specifically the food variety, such as tomatoes, beef brisket, Northeast rice, soy sauce, and prawns. The target detection box can be a bounding box output by the cloud recognition model on the image of the food to be cooked, used to locate the food's position. It is usually a rectangular bounding box (or a polygonal bounding box adapted to irregular foods), and the box can be accompanied by a food type label and a recognition confidence score (value range 0-1, higher values ​​represent higher recognition accuracy). When there are multiple independent foods in the image, the model outputs multiple sets of target detection boxes, consistent with the number of foods, to achieve parallel recognition and differentiation of multiple foods, avoiding interference from background clutter.

[0024] In practical applications, images containing the target food are acquired through the mobile terminal's camera, and then uploaded to a cloud server. The cloud server performs food identification and target detection on the uploaded images, and returns a list of food types (such as "tomato" and "egg"), the coordinates of the detection box (x_min, y_min, x_max, y_max) for each food in the image, and a pixel-level segmentation mask for the food region.

[0025] S105: The mobile terminal reconstructs the target detection points in the target detection box to obtain the three-dimensional attribute information of the food to be cooked.

[0026] In one specific embodiment, the target detection points can be key feature points selected within the target detection box that can characterize the spatial position of the food to be cooked. The selection strategy can be adaptively adjusted according to the shape of the food. For example, for regularly packaged foods (such as boxed milk and bagged rice), the four corner points, the midpoint of the bottom edge, or the geometric center point of the detection box can be selected; for irregularly packaged foods (such as tomatoes, beef brisket, and leafy vegetables), the contact point between the food and the supporting surface, the geometric centroid point, or the extreme value of surface curvature can be selected; for long and strip-shaped foods (such as cucumbers and carrots), the two end points and the midpoint can be selected. The target detection points are the bridge connecting two-dimensional image information and three-dimensional spatial coordinates, and their number can be configured from 1 to N according to the accuracy requirements (higher accuracy three-dimensional reconstruction can be achieved when N≥3).

[0027] In one specific embodiment, the three-dimensional attribute information may include the size information and actual weight information of the food to be cooked, and the actual weight can be estimated by the size information of the food obtained from the three-dimensional reconstruction.

[0028] Optional, such as Figure 2 As shown, the reconstruction of target detection points within the target detection box to obtain the three-dimensional attribute information of the food to be cooked can include: S201: Extract the transformation matrix corresponding to the target detection point.

[0029] In one specific embodiment, the transformation matrix can be a 4×4 homogeneous transformation matrix used to realize the mapping from the two-dimensional image coordinate system to the three-dimensional world coordinate system. This transformation matrix can be used to characterize the position information of the food to be cooked at the target detection point relative to the world coordinate system.

[0030] S203: Determine the three-dimensional coordinate information of the target detection point in the world coordinate system from the transformation matrix.

[0031] In one specific embodiment, the three-dimensional coordinate information can be the spatial position parameters of the target detection point in the world coordinate system, specifically represented as a triple of (X, Y, Z), where X and Y represent the planar position of the food on the table, and Z represents the vertical height of the food from the table, which is the core input parameter for calculating the volume of the food.

[0032] In practical applications, the transformation matrix can be represented as follows:

[0033] Extracting the fourth column to form (X, Y, Z) yields the aforementioned three-dimensional coordinate information.

[0034] S205: The actual weight information is calculated based on the three-dimensional coordinate information.

[0035] In one specific embodiment, the target detection point may include a first boundary detection point and a second boundary detection point. The first boundary detection point may be a feature point corresponding to the minimum coordinate value of the food to be cooked on a single axis (X / Y / Z axis), used to mark the lower limit of the boundary of the food on that axis. The second boundary detection point may be a feature point corresponding to the maximum coordinate value of the food to be cooked on a single axis (X / Y / Z axis), used to mark the upper limit of the boundary of the food on that axis.

[0036] The length, width, and height of the food to be cooked can be estimated based on the distances between boundary points in each of the three dimensions.

[0037] Optionally, the actual weight information calculated based on the three-dimensional coordinate information may include: Based on the first three-dimensional coordinate information of the first boundary detection point and the second three-dimensional coordinate information of the second boundary detection point in each three-dimensional direction, the distance between the first boundary detection point and the second boundary detection point is calculated to obtain the target distance; The target distances in each of the three dimensions are determined as the length, width, and height information of the three-dimensional detection box corresponding to the food to be cooked. The length, width, and height information are multiplied to obtain the volume information of the ingredient to be cooked. The density and volume information of the ingredients to be cooked are multiplied together to obtain the actual weight information.

[0038] In one specific embodiment, the target distance can be the Euclidean distance between the first boundary detection point and the second boundary detection point. The 3D detection box can be the smallest circumscribed cuboid that encloses the food to be cooked, with its length, width, and height corresponding to the target distances in the X / Y / Z axis directions, respectively. This is used to approximately represent the 3D space occupied by the food. For irregular food, the 3D detection box can be obtained by fitting a point cloud convex hull algorithm to ensure that it covers the entire effective volume of the food.

[0039] In practical applications, after receiving the food coordinate information returned from the cloud, the mobile terminal draws the food region on the local image based on the coordinate information, reconstructs the (x, y) coordinates of the corresponding detection points in the image coordinate system, and then determines the position of the detection points based on the aforementioned two-dimensional coordinates. For key points within the food region, its 4×4 transformation matrix (worldTransform) is extracted. The three-dimensional coordinates (X, Y, Z) of the point in the world coordinate system are obtained through the first three elements of the fourth column of the matrix. Here, the rotation component of the transformation matrix represents the object's posture, and the translation vector represents the object's position. Using the extracted world coordinates of the food's key points, the physical dimensions of the food are calculated using the Euclidean distance between two points in three-dimensional space. From this, the length L, width W, and height H are calculated, and then multiplied to obtain the volume V, and the weight m is obtained.

[0040] S107: The mobile terminal determines the target recipe for the ingredients to be cooked based on the target ingredient type and actual weight information.

[0041] In one specific embodiment, the target recipe can be a recipe determined from multiple candidate recipes. The ingredients to be cooked are then cooked based on this recipe. The target recipe can include preset weight information and cooking method information. The preset weight information can be the weight information related to the ingredients to be cooked recorded in the target recipe, which can serve as standard weight information. The actual weight information can be the weight information obtained by detecting the ingredients to be cooked. The cooking method information can include cooking methods such as stir-frying, stewing, and baking.

[0042] Optional, such as Figure 3 As shown, the target recipe for determining the ingredients to be cooked based on the target ingredient type and actual weight information can include: S301: Obtain the user's health data.

[0043] Specifically, a user's health data can be a set of de-identified tags extracted locally on the mobile terminal, which can include hard constraint tags and soft constraint tags. Hard constraint tags can include allergens (such as peanuts, seafood) and dietary restrictions (such as avoiding spicy foods after surgery, religious dietary restrictions), and have veto power. Soft constraint tags can include dietary preferences (such as liking spicy food, vegetarianism) and chronic disease tendencies (such as low-sugar for diabetes, low-salt for hypertension), and can be used to optimize recipe sorting rather than forcibly filtering. Optionally, the raw health data is not uploaded to the cloud, but only participates in matching calculations in a local secure environment.

[0044] S303: Determine the quantitative ratio information between the target ingredient type and the preset ingredient type in the target recipe as the ingredient matching index corresponding to the ingredient to be cooked.

[0045] Specifically, the preset ingredient types are the ingredient types recorded in the target recipe. The quantity of the target ingredient type is divided by the quantity of the preset ingredient type, and the resulting ratio is used as the ingredient matching index.

[0046] S305: Based on the degree of matching between actual weight information and preset weight information, determine the weight matching index corresponding to the ingredients to be cooked.

[0047] Specifically, the higher the value of the weight matching index, the better the match between the actual weight of the ingredients and the standard portion size in the recipe.

[0048] S307: Based on the degree of matching between health data and target recipes, determine the health matching indicators corresponding to the ingredients to be cooked.

[0049] Specifically, mobile devices can use locally stored health data to perform compliance checks and preference scoring on candidate recipes, resulting in a health matching index. Hard constraint filtering involves iterating through the ingredient lists and seasoning methods of candidate recipes; if any allergen or dietary restriction from the user's health data is present, the health matching index is directly set to 0, and the candidate recipe is filtered out of the candidate pool. Soft constraint scoring involves counting the number of soft constraint tags that match the user's preferences for candidate recipes that pass the hard constraint check, and then normalizing the score to obtain the health matching index. The higher the health matching index value, the more closely the recipe matches the user's dietary preferences and health needs.

[0050] S309: The ingredient matching index, weight matching index, and health matching index are weighted and summed to obtain the comprehensive matching index.

[0051] Specifically, based on the weight information corresponding to the ingredient matching index, weight matching index, and health matching index, each of these three indices is multiplied, and the three products are then added together to obtain the comprehensive matching index. The higher the value of the comprehensive matching index, the better the match between the corresponding recipe and the ingredients to be cooked.

[0052] S311: Based on comprehensive matching indicators, sort the candidate recipes for the ingredients to be cooked to obtain the target recipe.

[0053] Specifically, the target recipe can be the candidate recipe that best matches the ingredients to be cooked. Specifically, each candidate recipe can be sorted from highest to lowest based on its overall matching index, and the candidate recipe with the highest ranking can be selected as the target recipe.

[0054] In the above embodiments, the three-dimensional weighted matching mechanism solves the single-dimensional limitations of traditional recipe recommendation schemes, which only consider the types of ingredients and ignore the appropriate portion sizes, and only consider taste preferences and ignore health constraints. At the same time, since health data processing, indicator calculation, and ranking decisions are all completed on the local terminal, the security of users' sensitive privacy data is guaranteed, and the interaction lag caused by cloud round-trip latency is avoided. Even in weak network or no network environment, recipe recommendation can still be completed independently, which significantly improves the accuracy of recommendation and the robustness of the system.

[0055] Optionally, the above method may also include: If the ingredient matching index is less than the first preset matching threshold, and / or the weight matching index is less than the second preset matching threshold, the corresponding recipe will not be considered as a candidate recipe.

[0056] Specifically, if the ingredients to be cooked do not cover 50% of the ingredients required by the recipe, and / or the actual weight of the ingredients to be cooked does not meet the standard proportions in the recipe, then the corresponding recipe will not be considered as a candidate recipe and will not participate in the calculation of the comprehensive matching index and recipe ranking. Specifically, the first preset matching threshold and the second preset matching threshold can be set according to actual application needs. The first preset matching threshold can be set to 50%.

[0057] S109: The mobile terminal adjusts the initial cooking parameters in the target recipe based on the actual weight information to obtain the target cooking parameters.

[0058] In one specific embodiment, the initial cooking parameters may include initial cooking temperature information and initial cooking time information, which are the cooking temperature and cooking time recorded in the target recipe, respectively. The target cooking parameters may be the actual cooking parameters required when cooking the ingredients to be cooked, including target cooking temperature information and target cooking time information.

[0059] Optional, such as Figure 4 As shown, the target cooking parameters are obtained by adjusting the initial cooking parameters in the target recipe based on the actual weight information, and may include: S401: The ratio between the actual weight information and the preset weight information is determined as the weight adjustment coefficient.

[0060] In one specific embodiment, the actual weight information and the preset weight information are divided to obtain a weight adjustment coefficient, which can be used to characterize the degree of deviation between the actual weight information and the preset weight information.

[0061] S403: Based on the weight adjustment coefficient, the initial cooking temperature information is adjusted to obtain the target cooking temperature information.

[0062] Optionally, adjusting the initial cooking temperature information based on the weight adjustment coefficient to obtain the target cooking temperature information may include: The difference between the weight adjustment coefficient and the preset value is multiplied by the thermal property coefficient of the smart cooking device, and the resulting product is used as the exponential information of the natural base to obtain the natural index. The difference between the preset value and the natural index is multiplied by the upper limit temperature adjustment information to obtain the target temperature adjustment information; The initial cooking temperature information and the target temperature adjustment information are added together to obtain the target cooking temperature information.

[0063] Specifically, the thermodynamic property coefficient can be a thermal response rate constant. Pre-calibrated and embedded in the local terminal firmware based on the heating power, heat transfer efficiency, and thermal inertia of the food in the intelligent cooking device, it can characterize the rate at which temperature adjusts with weight deviation. Specifically, a larger k1 value indicates a faster temperature increase with increasing weight, suitable for electromagnetic heating devices with fast thermal response; a smaller k1 value indicates a smoother temperature adjustment, suitable for devices with high thermal inertia such as ovens and slow cookers. The upper limit temperature adjustment information can be the maximum temperature adjustment range (e.g., 10°C ~ 20°C), and the preset value can be 1. Specifically, the target cooking temperature information can be calculated using the following formula: T = T0 + ΔT × (1 - e^(-k1 × (k-1))) Where T represents the target cooking temperature information, T0 represents the initial cooking temperature information, ΔT represents the upper limit temperature adjustment information, k represents the weight adjustment coefficient, and k1 represents the thermal property coefficient.

[0064] S405: Based on the weight adjustment coefficient and cooking method information, adjust the initial cooking time information to obtain the target cooking time information.

[0065] Optionally, adjusting the initial cooking time information based on the weight adjustment coefficient and cooking method information to obtain the target cooking time information may include: Based on the preset mapping relationship, determine the cooking method coefficient corresponding to the cooking method information; Using the weight adjustment factor as the base and the cooking method factor as the exponent, the target index is obtained. The target cooking time information is obtained by multiplying the target index and the initial cooking time information.

[0066] In one specific embodiment, the cooking method coefficient can be used to characterize the degree of nonlinear influence of the heat transfer characteristics of different cooking processes on the duration scaling, and the preset mapping relationship can be used to characterize the correspondence between cooking method information and cooking method coefficient. Specifically, when the cooking method is stir-frying, the corresponding cooking method coefficient can be 0.7; when the cooking method is stewing, the corresponding cooking method coefficient can be 0.85; and when the cooking method is baking, the corresponding cooking method coefficient can be 0.6.

[0067] Specifically, the target cooking time information mentioned above can be calculated using the following formula: D = D0 × k^k2 Where D represents the target cooking time information, D0 represents the initial cooking time information, k represents the weight adjustment coefficient, and k2 represents the cooking method coefficient.

[0068] S111: Intelligent cooking equipment cooks ingredients based on target cooking parameters.

[0069] In one specific implementation, a user taps their mobile device against an NFC tag to launch a cooking app, then takes a picture of the ingredients on a cutting board, with the mobile device approximately 30cm away from the ingredients. The mobile device's camera captures an image of the ingredients, including two tomatoes and three eggs, and uploads it to the cloud. The cloud identifies and returns the coordinate information of the ingredients: the detection frame for Tomato 1 is (120, 80, 280, 240), the detection frame for Tomato 2 is (300, 100, 440, 230), etc. Based on the coordinate information returned by the cloud, the mobile device draws the ingredient area on the local image, reconstructing the (x, y) coordinates of each detection point. A 4×4 transformation matrix is ​​extracted from the key points within the ingredient area. The left boundary point of Tomato 1, worldPoint=(-0.085, 0.036, -0.30), i.e., X=-8.5cm, Y=3.6cm, Z=-30cm. Physical dimensions calculated based on Euclidean distance: Tomato 1: Length L = 8.5cm, Width W = 7.2cm, Height H = 6.8cm, Weight approximately 195g; two tomatoes total approximately 390g; Eggs: Approximately 55g each, three eggs total approximately 165g. Ingredient attribute integration: {Tomato: 8.5cm × 7.2cm × 6.8cm × 195g × 2, Eggs: 5.5cm × 4.2cm × 4.0cm × 55g × 3} User health profile desensitization tags: {Hard constraint: None, Soft constraint: Low sodium preference}; 3D matching search results: Scrambled eggs with tomatoes (Score = 0.85) > Tomato egg drop soup (Score = 0.72) > Braised beef brisket with tomatoes (Score = 0.38). Portion size coefficient k = 390 / 350 = 1.11, cooking temperature T ≈ 183°C, cooking time D ≈ 5.4min. The cooking parameters (temperature 183°C, duration 5.4 min) are sent to the smart cooking machine.

[0070] In one specific implementation, a user is allergic to seafood. The refrigerator contains shrimp and tofu. The user taps their mobile device against an NFC tag to activate a cooking app and take a photo. The coordinates of the ingredients are obtained via cloud recognition, and the physical dimensions are calculated locally using a transformation matrix: shrimp L≈10cm×3cm×2.5cm, approximately 150g; tofu L≈10cm×8cm×4cm, approximately 350g. The user's health profile is defined as {hard constraint: seafood allergy}. A three-dimensional matching search is performed: all recipes containing shrimp are completely excluded due to the hard constraint "seafood allergy," and only tofu recipes without seafood are recommended: Mapo Tofu (Score=0.85) > Home-style Tofu (Score=0.70). The portion size coefficient k=350 / 300=1.17, the cooking temperature T≈103°C, and the cooking time D≈17.2min. This hard constraint mechanism ensures that users with seafood allergies will never be recommended recipes containing shrimp, even if the ingredient recognition results include shrimp.

[0071] As can be seen from the technical solutions provided in the embodiments of this specification above, when the distance between the mobile terminal and the communication tag is less than a preset distance threshold, the mobile terminal calls the cooking application, wherein the communication tag is set on the smart cooking device; further, the cloud receives the image of the food to be cooked collected by the cooking application, and identifies the image of the food to be cooked to obtain the target food type and target detection box of the food to be cooked, wherein the image of the food to be cooked is collected by the cooking application through the mobile terminal; then, the mobile terminal reconstructs the target detection points in the target detection box to obtain the three-dimensional attribute information of the food to be cooked; the three-dimensional attribute information includes actual weight information, and based on the target food type and actual weight information, the target recipe of the food to be cooked is determined, and the initial cooking parameters in the target recipe are adjusted according to the actual weight information to obtain the target cooking parameters; then, the smart cooking device cooks the food to be cooked based on the target cooking parameters.

[0072] Therefore, by using near-field communication tags to simplify device interaction and application activation paths, and combining cloud-based image recognition and terminal 3D reconstruction technologies, the actual weight of ingredients can be accurately calculated while accurately identifying the types of ingredients. This allows cooking parameters to be precisely matched with ingredient quantities, achieving precise and intelligent cooking and improving cooking results.

[0073] The present invention also provides a cooking control system, which includes an intelligent cooking device, a mobile terminal, a cloud platform, and a control module. The intelligent cooking device is communicatively connected to the mobile terminal, and the mobile terminal is communicatively connected to the cloud platform. The control module is communicatively connected to the intelligent cooking device, the mobile terminal, and the cloud platform respectively. The control module is used to control the intelligent cooking device, the mobile terminal, and the cloud platform to execute the above-mentioned cooking control method.

[0074] The mobile terminal can be used to invoke a cooking application when the distance between the mobile terminal and the communication tag is less than a preset distance threshold; and to capture images of the ingredients to be cooked and send them to the cloud; the communication tag is set on the smart cooking device. The cloud can be used to receive images of ingredients to be cooked, identify the images of ingredients to be cooked, obtain the target ingredient type and target detection box of the ingredients to be cooked, and send the target detection box to the mobile terminal; The mobile terminal can also be used to reconstruct the target detection points in the target detection box to obtain the three-dimensional attribute information of the food to be cooked; the three-dimensional attribute information includes actual weight information; and is used to determine the target recipe of the food to be cooked based on the target food type and actual weight information; and is used to adjust the initial cooking parameters in the target recipe according to the actual weight information to obtain the target cooking parameters and send them to the smart cooking device. Intelligent cooking equipment can be used to cook ingredients based on target cooking parameters.

[0075] Optionally, the mobile terminal can also be used to determine the ratio between the actual weight information and the preset weight information as a weight adjustment coefficient; the weight adjustment coefficient is used to characterize the degree of deviation between the actual weight information and the preset weight information; based on the weight adjustment coefficient, the initial cooking temperature information is adjusted to obtain the target cooking temperature information; based on the weight adjustment coefficient and the cooking method information, the initial cooking time information is adjusted to obtain the target cooking time information.

[0076] Optionally, the mobile terminal can also be used to multiply the difference between the weight adjustment coefficient and the preset value by the thermal attribute coefficient of the smart cooking device, and use the resulting product as the exponential information of the natural base to obtain the natural exponent; multiply the difference between the preset value and the natural exponent by the upper limit temperature adjustment information to obtain the target temperature adjustment information; and add the initial cooking temperature information and the target temperature adjustment information to obtain the target cooking temperature information.

[0077] Optionally, the mobile terminal can also be used to determine the cooking method coefficient corresponding to the cooking method information based on a preset mapping relationship; the preset mapping relationship is used to characterize the correspondence between the cooking method information and the cooking method coefficient; the weight adjustment coefficient is used as the base and the cooking method coefficient is used as the exponent to obtain the target exponent; the target exponent and the initial cooking time information are multiplied to obtain the target cooking time information.

[0078] Optionally, the mobile terminal can also be used to extract the transformation matrix corresponding to the target detection point; the transformation matrix is ​​used to characterize the position information of the food to be cooked at the target detection point relative to the world coordinate system; the three-dimensional coordinate information of the target detection point in the world coordinate system is determined from the transformation matrix; and the actual weight information is calculated based on the three-dimensional coordinate information.

[0079] Optionally, the mobile terminal can also be used to calculate the distance between the first boundary detection point and the second boundary detection point based on the first three-dimensional coordinate information of the first boundary detection point and the second three-dimensional coordinate information of the second boundary detection point in each three-dimensional direction, to obtain the target distance; determine the target distance in each three-dimensional direction as the length, width, and height information of the three-dimensional detection box corresponding to the food to be cooked; multiply the length, width, and height information to obtain the volume information corresponding to the food to be cooked; and multiply the density and volume information corresponding to the food to be cooked to obtain the actual weight information.

[0080] Optionally, the mobile terminal can also be used to acquire the user's health data; determine the ratio between the target ingredient type and the preset ingredient type in the target recipe as the ingredient matching index for the ingredient to be cooked; determine the weight matching index for the ingredient to be cooked based on the degree of matching between the actual weight information and the preset weight information; determine the health matching index for the ingredient to be cooked based on the degree of matching between the health data and the target recipe; perform weighted summation on the ingredient matching index, weight matching index, and health matching index to obtain a comprehensive matching index; and rank the candidate recipes for the ingredient to be cooked based on the comprehensive matching index to obtain the target recipe.

[0081] Optionally, the mobile terminal can also be used to exclude the corresponding recipe from the candidate recipe if the ingredient matching index is less than a first preset matching threshold and / or the weight matching index is less than a second preset matching threshold.

[0082] 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.

[0083] 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.

[0084] 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 control method, characterized in that, The method includes: When the distance between the mobile terminal and the communication tag is less than a preset distance threshold, the mobile terminal invokes a cooking application; the communication tag is set on the smart cooking device. The cloud receives images of the ingredients to be cooked collected by the cooking application, and identifies the images of the ingredients to be cooked to obtain the target ingredient type and target detection box of the ingredients to be cooked; the images of the ingredients to be cooked are collected by the cooking application through the mobile terminal; The mobile terminal reconstructs the target detection points in the target detection frame to obtain the three-dimensional attribute information of the food to be cooked; the three-dimensional attribute information includes actual weight information. The mobile terminal determines the target recipe for the ingredients to be cooked based on the target ingredient type and the actual weight information. The mobile terminal adjusts the initial cooking parameters in the target recipe based on the actual weight information to obtain the target cooking parameters; The intelligent cooking device cooks the ingredients to be cooked based on the target cooking parameters.

2. The method according to claim 1, characterized in that, The target recipe includes preset weight information and cooking method information. The initial cooking parameters include initial cooking temperature information and initial cooking time information. The target cooking parameters are obtained by adjusting the initial cooking parameters in the target recipe based on the actual weight information, including: The ratio between the actual weight information and the preset weight information is determined as the weight adjustment coefficient; the weight adjustment coefficient is used to characterize the degree of deviation between the actual weight information and the preset weight information. Based on the weight adjustment coefficient, the initial cooking temperature information is adjusted to obtain the target cooking temperature information; Based on the weight adjustment coefficient and the cooking method information, the initial cooking time information is adjusted to obtain the target cooking time information.

3. The method according to claim 2, characterized in that, The step of adjusting the initial cooking temperature information based on the weight adjustment coefficient to obtain the target cooking temperature information includes: The difference between the weight adjustment coefficient and the preset value is multiplied by the thermal property coefficient of the intelligent cooking device, and the resulting product is used as the exponent information of the natural base to obtain the natural index. The difference between the preset value and the natural index is multiplied by the upper limit temperature adjustment information to obtain the target temperature adjustment information; The initial cooking temperature information and the target temperature adjustment information are added together to obtain the target cooking temperature information.

4. The method according to claim 2, characterized in that, The step of adjusting the initial cooking time information based on the weight adjustment coefficient and the cooking method information to obtain the target cooking time information includes: Based on a preset mapping relationship, the cooking method coefficient corresponding to the cooking method information is determined; the preset mapping relationship is used to characterize the correspondence between the cooking method information and the cooking method coefficient. Using the weight adjustment coefficient as the base and the cooking method coefficient as the exponent, the target index is obtained; The target cooking time information is obtained by multiplying the target index and the initial cooking time information.

5. The method according to claim 1, characterized in that, The process of reconstructing the target detection points in the target detection box to obtain the three-dimensional attribute information of the food to be cooked includes: Extract the transformation matrix corresponding to the target detection point; the transformation matrix is ​​used to characterize the position information of the food to be cooked at the target detection point relative to the world coordinate system; The three-dimensional coordinate information of the target detection point in the world coordinate system is determined from the transformation matrix; The actual weight information is calculated based on the three-dimensional coordinate information.

6. The method according to claim 5, characterized in that, The target detection points include a first boundary detection point and a second boundary detection point, and the actual weight information calculated based on the three-dimensional coordinate information includes: Based on the first three-dimensional coordinate information of the first boundary detection point and the second three-dimensional coordinate information of the second boundary detection point in each three-dimensional direction, the distance between the first boundary detection point and the second boundary detection point is calculated to obtain the target distance; The target distances in each of the three dimensions are determined as the length, width, and height information of the three-dimensional detection frame corresponding to the food to be cooked. The length information, the width information, and the height information are multiplied together to obtain the volume information corresponding to the ingredient to be cooked. The density information and volume information of the food to be cooked are multiplied together to obtain the actual weight information.

7. The method according to claim 1, characterized in that, The target recipe includes preset weight information. Determining the target recipe for the ingredients to be cooked based on the target ingredient type and the actual weight information includes: Obtain users' health data; The quantity ratio information between the target ingredient type and the preset ingredient type in the target recipe is determined as the ingredient matching index corresponding to the ingredient to be cooked; Based on the degree of matching between the actual weight information and the preset weight information, the weight matching index corresponding to the ingredient to be cooked is determined. Based on the degree of matching between the health data and the target recipe, the health matching index corresponding to the ingredients to be cooked is determined; The food matching index, the weight matching index, and the health matching index are weighted and summed to obtain a comprehensive matching index. Based on the comprehensive matching index, the candidate recipes for the ingredients to be cooked are sorted to obtain the target recipe.

8. The method according to claim 7, characterized in that, The method further includes: If the ingredient matching index is less than a first preset matching threshold, and / or the weight matching index is less than a second preset matching threshold, the corresponding recipe will not be considered as a candidate recipe.

9. The method according to claim 1, characterized in that, The intelligent cooking device is at least one of a food processor, a steam oven, a pressure cooker, and an air fryer.

10. A cooking control system, characterized in that, The system includes an intelligent cooking device, a mobile terminal, a cloud platform, and a control module. The intelligent cooking device is communicatively connected to the mobile terminal, and the mobile terminal is communicatively connected to the cloud platform. The control module is communicatively connected to the intelligent cooking device, the mobile terminal, and the cloud platform respectively. The control module is used to control the intelligent cooking device, the mobile terminal, and the cloud platform to execute the cooking control method as described in any one of claims 1 to 9. The mobile terminal is used to invoke a cooking application when the distance between the mobile terminal and the communication tag is less than a preset distance threshold. And for capturing images of the ingredients to be cooked and sending them to the cloud; the communication tag is set on the smart cooking device; The cloud is used to receive images of the ingredients to be cooked, identify the images of the ingredients to be cooked, obtain the target ingredient type and target detection box of the ingredients to be cooked, and send the target detection box to the mobile terminal; The mobile terminal is also used to reconstruct the target detection points in the target detection frame to obtain the three-dimensional attribute information of the food to be cooked; the three-dimensional attribute information includes actual weight information; and to determine the target recipe of the food to be cooked based on the target food type and the actual weight information. And for adjusting the initial cooking parameters in the target recipe based on the actual weight information to obtain the target cooking parameters, and sending them to the smart cooking device; The intelligent cooking device is used to cook the ingredients to be cooked based on the target cooking parameters.

Images