Auxiliary cooking method and device, electronic equipment, storage medium and program product

Abstract

The invention discloses an auxiliary cooking method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of intelligent cooking. The method comprises the steps of obtaining a target to-be-cooked menu, and determining cooking data of the target to-be-cooked menu; in the cooking process, an infrared image of a cooking pot and a cooking pot image are obtained respectively; extracting a target cooking area in the cooking pot image, mapping the target cooking area to the infrared image, and determining the surface temperature of a cooking food material based on a mapping result; and determining an internal temperature of the cooking food material based on the surface temperature, determining a current cooking state based on the internal temperature, and generating a target execution instruction based on the current cooking state. According to the scheme, the multi-point temperature distribution in the pot can be sensed in real time, the heat state of the food materials can be accurately estimated, the heating strategy is dynamically optimized based on the characteristics of the food materials, nutrition loss or burning of the food materials is avoided, and the cooking precision is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent cooking technology, and in particular to an auxiliary cooking method, device, electronic device, storage medium, and program product. Background Technology

[0002] Assisted cooking refers to the use of specialized tools, smart devices, sensing technologies, and algorithm systems to support key aspects of food preparation and cooking, such as cutting, heating, seasoning, time control, and cleaning, thereby helping users complete cooking tasks more efficiently, safely, and conveniently. Its core concept is not to completely replace manual operation, but rather to lower the barrier to entry for cooking, improve the user experience, and ensure the quality and nutritional health of dishes through human-machine collaboration.

[0003] Current cooking equipment relies on a single temperature sensor installed at the bottom of the pot to detect cooking temperature. Since the heat source is usually located at the center of the pot, and factors such as the pot's material, food distribution, and ambient heat dissipation affect the temperature field within the pot, it exhibits significant unevenness. Actual measurement data shows that the temperature difference between the center and the edge of the pot often exceeds 10°C, or even higher. The temperature detected by the bottom sensor reflects the temperature conducted from the heat source to the bottom of the pot, not the actual temperature of the food's environment. Due to the delay in heat conduction, there is often a systematic deviation of up to ±20°C between the temperature at the bottom of the pot and the temperature of the food within. While existing cooking equipment can be linked with electronic recipes, most only mechanically execute preset programs and cannot intelligently adjust the heat according to the type and quantity of ingredients. This makes it difficult to meet the precise temperature control requirements for healthy cooking, resulting in a high risk of nutrient loss or burning of food.

[0004] How to sense the temperature distribution at multiple points inside the pot in real time, accurately estimate the thermal state of the food, and dynamically optimize the heating strategy based on the characteristics of the food to avoid nutrient loss or burning and improve the precision of cooking is a key research issue in the industry. Summary of the Invention

[0005] This invention provides an auxiliary cooking method, device, electronic device, storage medium, and program product to sense the temperature distribution at multiple points inside the pot in real time, accurately estimate the thermal state of the ingredients, and dynamically optimize the heating strategy based on the characteristics of the ingredients, thereby avoiding nutrient loss or burning of the ingredients and improving the accuracy of cooking.

[0006] According to one aspect of the present invention, an auxiliary cooking method is provided, the method comprising:

[0007] Obtain the target recipe to be cooked, and determine the cooking data of the target recipe to be cooked;

[0008] During the cooking process, infrared images of the cooking pot and images of the cooking pot are acquired respectively;

[0009] Extract the target cooking area from the cooking pot image and map the target cooking area onto the infrared image; determine the surface temperature of the food being cooked based on the mapping result.

[0010] The internal temperature of the food being cooked is determined based on the surface temperature, the current cooking state is determined based on the internal temperature, and a target execution instruction is generated based on the current cooking state.

[0011] Optionally, acquiring the target recipe to be cooked and determining the cooking data of the target recipe to be cooked includes:

[0012] The system receives target user voice input data through the target wearable device, identifies the target voice input data, and determines the target recipe to be cooked based on the identification result.

[0013] Obtain the target recipe to be cooked, and extract the preset cooking process parameter set associated with the target recipe to be cooked;

[0014] The preset cooking process parameter set is parsed to obtain the cooking data of the target recipe to be cooked;

[0015] The cooking data includes: preheating temperature threshold, stir-fry trigger temperature, recommended heat level, total heating time, and operating instructions for each stage.

[0016] Optionally, the target wearable device is smart glasses; the smart glasses include an infrared camera and a visible light camera;

[0017] The process of acquiring infrared images of the cooking pot and images of the pot itself during cooking includes:

[0018] The infrared camera captures infrared thermal images of the cooking pot and generates a two-dimensional temperature matrix.

[0019] The cooking pot image is obtained by capturing an image of the appearance of the cooking pot using the visible light camera.

[0020] Optionally, after determining the cooking data of the target recipe, the method further includes:

[0021] The cooking data is displayed through the smart glasses so that the target user can view the cooking data in real time.

[0022] Optionally, extracting the target cooking area from the cooking pot image and mapping the target cooking area to the infrared image includes:

[0023] The cooking pot image is segmented, and the target cooking region is determined based on the segmentation results; wherein, the target cooking region is the region in the cooking pot image that contains cooking ingredients;

[0024] The mask value of each pixel in the target cooking area is determined, and based on the resolution of the target cooking area and the resolution of the infrared image, the mask value of each pixel in the target cooking area is mapped to the infrared image.

[0025] Optionally, determining the surface temperature of the food ingredients based on the mapping result includes:

[0026] In the infrared temperature matrix, based on the mask values ​​of each pixel in the mapped target cooking area, the temperature values ​​corresponding to all pixels are extracted to form a set of food surface temperatures.

[0027] Each temperature statistic is determined based on the set of surface temperatures of the food ingredients;

[0028] The temperature statistics include at least one of the following: average temperature, maximum temperature, minimum temperature, center temperature, edge temperature, and temperature gradient.

[0029] Optionally, determining the internal temperature of the food being cooked based on the surface temperature includes:

[0030] The temperature of the cooking pot is obtained in real time by a temperature sensor deployed at the bottom of the cooking pot, and the power data of the stove is collected.

[0031] The internal temperature of the food being cooked is obtained by using the average surface temperature at the current moment, the temperature of the cooking pot, the power data of the stove, and the internal temperature of the food being cooked at historical moments as input values ​​in a preset model for determining the internal temperature of the food being cooked.

[0032] Optionally, determining the current cooking state based on the internal temperature and generating the target execution instruction based on the current cooking state includes:

[0033] The internal temperature is dynamically compared with the target temperature-time curve of the target recipe to be cooked to determine the deviation trend between the current cooking state and the ideal path.

[0034] When it is determined that the heating rate is greater than the set threshold and the internal temperature approaches the target level of doneness, a fire control command is generated.

[0035] The firepower control command is transmitted to the stove controller via a Bluetooth communication link, so that the stove controller can adjust the firepower based on the firepower control command.

[0036] Optionally, after generating the fire control command, the following may also be included:

[0037] Generate a prompt message that matches the fire control command, and broadcast or display the prompt message through smart glasses.

[0038] According to another aspect of the present invention, an auxiliary cooking device is provided, the device comprising:

[0039] The first acquisition module is used to acquire the target recipe to be cooked and to determine the cooking data of the target recipe to be cooked;

[0040] The second acquisition module is used to acquire infrared images of the cooking pot and images of the cooking pot during the cooking process.

[0041] A surface temperature determination module is used to extract the target cooking area from the cooking pot image, map the target cooking area to the infrared image, and determine the surface temperature of the food being cooked based on the mapping result.

[0042] An internal temperature determination module is used to determine the internal temperature of the food being cooked based on the surface temperature, determine the current cooking state based on the internal temperature, and generate a target execution instruction based on the current cooking state.

[0043] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0044] At least one processor; and

[0045] A memory communicatively connected to the at least one processor; wherein,

[0046] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the assisted cooking method according to any embodiment of the present invention.

[0047] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the assisted cooking method according to any embodiment of the present invention.

[0048] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the assisted cooking method described in any embodiment of the present invention.

[0049] The technical solution of this invention involves acquiring a target recipe and determining its cooking data; during the cooking process, acquiring an infrared image of the cooking pot and an image of the cooking pot; extracting a target cooking area from the cooking pot image and mapping the target cooking area onto the infrared image; determining the surface temperature of the food based on the mapping result; determining the internal temperature of the food based on the surface temperature; determining the current cooking state based on the internal temperature; and generating a target execution command based on the current cooking state. This method can accurately determine the surface and internal temperatures of the food, perceive the temperature distribution at multiple points inside the pot in real time, accurately estimate the thermal state of the food, and dynamically optimize the heating strategy based on the characteristics of the food, thus avoiding nutrient loss or burning and improving the accuracy of cooking.

[0050] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0051] 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.

[0052] Figure 1 This is a flowchart of an auxiliary cooking method provided according to Embodiment 1 of the present invention;

[0053] Figure 2 This is a flowchart of an auxiliary cooking method provided according to Embodiment 2 of the present invention;

[0054] Figure 3 This is a flowchart of an auxiliary cooking method provided according to Embodiment 2 of the present invention;

[0055] Figure 4 This is a schematic diagram of the structure of an auxiliary cooking device provided according to Embodiment 3 of the present invention;

[0056] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the auxiliary cooking method of the present invention. Detailed Implementation

[0057] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0058] 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 described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0059] Example 1

[0060] Figure 1 This is a flowchart of an assisted cooking method according to Embodiment 1 of the present invention. This embodiment is applicable to situations where a user is assisted in cooking. The method can be executed by an assisted cooking device, which can be implemented in hardware and / or software. This assisted cooking device can be configured in wearable devices such as smart glasses, or in electronic devices such as computers, servers, or tablets. Figure 1 As shown, the method includes:

[0061] Step 110: Obtain the target recipe to be cooked and determine the cooking data of the target recipe to be cooked.

[0062] The target recipe to be cooked can be a recipe prepared by the target user, such as pan-fried medium-rare steak, scrambled eggs with tomatoes, or braised fish, etc., and this embodiment does not limit it. The target user can be any user in the household, such as an adult or a minor, and this embodiment does not limit it either.

[0063] Optionally, in this embodiment, the target recipe to be cooked can be received manually or by voice input from the target user, and the cooking data of the target recipe can be further determined. The cooking data of the target recipe may include a preheating temperature threshold, a stir-fry trigger temperature (i.e., a flipping trigger temperature), a recommended heat level, a total heating time, and operating instructions for each stage.

[0064] In one optional implementation of this embodiment, after obtaining the target recipe to be cooked, the ingredient list, operating instructions for each cooking stage, seasonings, heat level, or stir-fry trigger temperature of the target recipe to be cooked can be further obtained from a cloud server, the Internet, or a relevant database.

[0065] Step 120: During the cooking process, acquire infrared images of the cooking pot and images of the cooking pot.

[0066] Optionally, in this embodiment, after determining that the cooking data for the target recipe has been obtained, the user can be prompted to start cooking. During the cooking process, infrared images and internal images of the cooking pot, including the ingredients, can be acquired in real time.

[0067] In one optional implementation of this embodiment, the range hood may be equipped with both an infrared camera and a visible light camera. During cooking, the infrared camera can capture infrared images of the cooking pot, which can be displayed as a two-dimensional temperature matrix; the visible light camera can capture internal images of the cooking pot.

[0068] Step 130: Extract the target cooking area from the cooking pot image and map the target cooking area onto the infrared image. Determine the surface temperature of the food being cooked based on the mapping result.

[0069] Optionally, after acquiring the cooking pot image, further recognition processing can be performed on the cooking pot image to identify and extract the food area within it, thereby obtaining the target cooking area in the cooking pot image. Furthermore, the target cooking area can be mapped onto the infrared image of the cooking pot to obtain the surface temperature of the cooked food.

[0070] In one optional implementation of this embodiment, an image of the cooking pot can be acquired using a visible light camera, and a deep learning semantic segmentation model can be used to perform pixel-level classification of the acquired image, identify and extract the food region, and generate a corresponding binary mask to determine the target cooking region. Further, key points in the infrared image can be extracted from the target cooking region, and a homography transformation matrix can be estimated using a matching algorithm to achieve non-rigid alignment; alternatively, a deep learning-based registration method can be used; or, precise registration based on physical calibration can be achieved by arranging high-contrast calibration plates (such as checkerboard patterns) or thermal / optical dual-mode markers on the edge of the pot, performing camera calibration and extrinsic parameter calculations to obtain a spatial transformation relationship with sub-pixel accuracy.

[0071] Furthermore, the food mask (target cooking area) in the image of the cookware can be projected onto the infrared image plane through a transformation matrix to generate the corresponding thermal image mask area. Then, the infrared temperature matrix can be extracted by masking, and the average temperature, maximum temperature and temperature distribution statistics of the pixels in the area can be calculated. This enables real-time and accurate perception of the thermal state of the surface of the food, providing data support for intelligent temperature control, doneness judgment and automation of the cooking process.

[0072] Step 140: Determine the internal temperature of the food being cooked based on the surface temperature, determine the current cooking state based on the internal temperature, and generate a target execution instruction based on the current cooking state.

[0073] Optionally, in this embodiment, after determining the surface temperature of the food being cooked, the internal temperature of the food being cooked can be further determined based on the surface temperature, and the current cooking state can be accurately determined based on the internal temperature of the food being cooked. Furthermore, subsequent execution instructions can be generated based on the current cooking state; in this embodiment, these are referred to as target execution instructions.

[0074] In this embodiment, the target execution command can be to increase the heat level, decrease the heat level, turn off the heat, flip the food, or stir-fry quickly, etc., and this embodiment does not limit it.

[0075] In one optional implementation of this embodiment, after determining the surface temperature of the food being cooked, a physical model based on Fourier's law of heat conduction can be constructed. This model combines the thermal properties of the food, such as thermal conductivity, specific heat capacity, and density, to establish a one-dimensional unsteady-state partial differential equation for heat conduction. The measured surface temperature is used as the boundary condition, and the initial temperature as the initial value condition. The finite difference method or finite element method is then used for numerical solution to obtain the spatiotemporal distribution of the internal temperature field of the food. Based on this, by identifying key target temperature thresholds (e.g., a meat center temperature ≥70℃ to inactivate pathogens) and combining them with a preset aging kinetic model, the current cooking state (e.g., undercooked, moderately cooked, or overcooked) is determined. Furthermore, the deviation between the current state and the target cooking curve is analyzed and input into an adaptive control algorithm to generate closed-loop control commands. These commands dynamically adjust execution parameters such as heating power, stirring frequency, or cooking time, thereby achieving intelligent cooking process optimization and precise control based on multimodal perception and thermophysical modeling.

[0076] This embodiment's solution acquires a target recipe and determines its cooking data. During cooking, it acquires an infrared image of the cooking pot and an image of the cooking pot itself. It extracts the target cooking area from the cooking pot image and maps it to the infrared image, determining the surface temperature of the food based on the mapping result. Based on the surface temperature, it determines the internal temperature of the food, and based on the internal temperature, it determines the current cooking state. Based on the current cooking state, it generates a target execution command. This approach accurately determines the surface and internal temperatures of the food, allows for real-time sensing of multi-point temperature distribution within the pot, accurate estimation of the food's thermal state, and dynamic optimization of the heating strategy based on the food's characteristics. This prevents nutrient loss or burning, improving cooking precision.

[0077] Example 2

[0078] Figure 2 This is a flowchart of an auxiliary cooking method according to Embodiment 2 of the present invention. This embodiment is a further refinement of the above technical solution, and the technical solution in this embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the method includes:

[0079] Step 210: Receive target voice input data from the target user through the target wearable device, and identify the target voice input data. Determine the target recipe to be cooked based on the identification result. Obtain the target recipe to be cooked and extract the preset cooking process parameter set associated with the target recipe to be cooked. Parse the preset cooking process parameter set to obtain the cooking data of the target recipe to be cooked.

[0080] The target wearable device can be smart glasses or a smartwatch, etc., and is not limited to it in this embodiment.

[0081] Optionally, in this embodiment, the voice input data of the target user can be received through the target wearable device, which is referred to as target voice input data in this embodiment. For example, the target voice input data can be: I want to eat scrambled eggs with tomatoes, pan-fry a low-fat steak to medium-rare, or make a medium-spicy hot and sour shredded potato dish, etc., and is not limited to these in this embodiment.

[0082] In this embodiment, after receiving the target user's target voice input data, the target wearable device can further perform semantic recognition on the target voice input data and determine the target recipe to be cooked based on the semantic recognition results.

[0083] In this embodiment, after receiving the target user's target voice input data, the target wearable device can input the target voice input data into a pre-obtained speech recognition model, thereby outputting a target cooking recipe. For example, the target cooking recipe determined by the aforementioned target voice input data can be scrambled eggs with tomatoes, medium-rare steak, or moderately spicy shredded potatoes with chili and vinegar.

[0084] Furthermore, the specific content of the target recipe can be obtained from a cloud server or a local database, and a set of preset cooking process parameters associated with the target recipe can be extracted from the specific content. Furthermore, the set of preset cooking process parameters can be parsed to obtain cooking data such as the preheating temperature threshold, stir-frying trigger temperature, recommended heat level, total heating time, and operation instructions for each stage of the target recipe.

[0085] In one optional implementation of this embodiment, the smart glasses can be AI glasses, which internally deploy a pre-tuned multimodal large model. In a specific implementation, the target user wakes up the multimodal large model through the voice interaction module of the smart glasses and inputs the target recipe by voice (e.g., low-oil pan-fried steak). The large model retrieves the full process parameters of the recipe from the cloud, including the temperature curve (e.g., the surface temperature of the steak needs to be maintained at 120℃±5℃), the heat range (e.g., heat level 3-5 during the frying stage), and the operation sequence (e.g., prompting to flip when the lower surface temperature reaches 120 degrees or the upper surface reaches 100 degrees), and synchronously sends the parameters to the smart glasses (for display / prompt) and the associated cooking equipment (e.g., stove or smart cookware, etc.).

[0086] Step 220: Acquire infrared thermal images of the cooking pot using the infrared camera and generate a two-dimensional temperature matrix; acquire an image of the cooking pot's appearance using the visible light camera to obtain an image of the cooking pot.

[0087] The target wearable device is smart glasses; the smart glasses may include an infrared camera and a visible light camera.

[0088] Optionally, in this embodiment, after detecting the start of cooking, the infrared thermal image of the cooking pot can be acquired by the infrared camera of the smart glasses to generate a two-dimensional temperature matrix; at the same time, the appearance image of the cooking pot can also be acquired by the visible light camera of the smart glasses to obtain an image of the cooking pot, which is referred to as the cooking pot image in this embodiment.

[0089] In one example of this embodiment, an infrared camera deployed in the smart glasses can acquire infrared thermal images of the pot at a frequency of 2Hz, generating a two-dimensional temperature matrix (resolution ≥640×480, temperature accuracy ±0.5℃). Simultaneously, the infrared camera can also capture the spatial distribution of temperature (e.g., the temperature difference between the center and edge of the food). A visible light camera deployed in the smart glasses can acquire color images at a frame rate of 5fps.

[0090] Step 230: Extract the target cooking area from the cooking pot image and map the target cooking area onto the infrared image.

[0091] Optionally, in this embodiment, after acquiring the cooking pot image through a visible light camera, a target cooking region can be further extracted from the cooking pot image, and the target cooking region can be mapped onto the infrared image. Optionally, extracting the target cooking region from the cooking pot image and mapping the target cooking region onto the infrared image may include: segmenting the cooking pot image, determining the target cooking region based on the segmentation result; determining the mask value of each pixel in the target cooking region, and mapping the mask value of each pixel in the target cooking region onto the infrared image based on the resolution of the target cooking region and the resolution of the infrared image.

[0092] The target cooking area is the region in the cooking pot image that contains the cooking ingredients.

[0093] In an optional implementation of this embodiment, after acquiring the cooking pot image, the cooking pot image can be further segmented, and a target cooking region containing cooking ingredients can be determined based on the segmentation results. Furthermore, the mask value of each pixel in the target cooking region can be determined, and based on the resolution of the target cooking region and the resolution of the infrared image, the mask values ​​of each pixel in the target cooking region can be mapped to the infrared image.

[0094] In one example of this embodiment, an instance segmentation algorithm of a pre-trained model (e.g., a semantic segmentation model) can be used to identify food regions (e.g., outlines, locations, or areas) and mark these regions as target cooking areas (e.g., steak locations).

[0095] It is understood that, in this embodiment, the mask values ​​of each pixel in the target cooking area can be output by a pre-trained model.

[0096] In one optional implementation of this embodiment, the pre-trained model maps the coordinates of the identified target cooking area to an infrared temperature matrix to extract the surface temperature distribution of the food (e.g., the highest surface temperature of the steak is 130°C, and the edge is 110°C). Furthermore, the pre-trained model can simultaneously output the "steak bounding box" and the "steak pixel-level mask," which not only locates the overall position of the steak but also distinguishes the pixel boundaries between the steak and other areas.

[0097] Step 240: Determine the surface temperature of the cooking ingredients based on the mapping results.

[0098] Optionally, in this embodiment, after mapping the target cooking area to an infrared image, i.e., an infrared temperature matrix, the surface temperature of the food being cooked can be further determined based on the mapping result of the target cooking area.

[0099] Optionally, in this embodiment, determining the surface temperature of the cooking ingredients based on the mapping result may include: extracting the temperature values ​​corresponding to all pixels in the infrared temperature matrix according to the mask values ​​of each pixel in the mapped target cooking area to form a set of ingredient surface temperatures; and determining various temperature statistics based on the set of ingredient surface temperatures.

[0100] The temperature statistics include at least one of the following: average temperature, maximum temperature, minimum temperature, center temperature, edge temperature, and temperature gradient.

[0101] In an optional implementation of this embodiment, the temperature values ​​corresponding to all pixels can be extracted from the infrared temperature matrix based on the mask values ​​of each pixel in the mapped target cooking area to form a set of food surface temperatures. Furthermore, temperature statistics such as average temperature, maximum temperature, minimum temperature, center temperature, edge temperature, and temperature gradient can be determined based on the set of food surface temperatures.

[0102] In one example of this embodiment, the visible light camera resolution is 1920×1080; the infrared camera resolution is 640×480; and the resolution scaling ratio is Sx=W. B / W A =640 / 1920=1 / 3 (x-axis pixel scaling factor); Sy=H B / H A=480 / 1080=4 / 9 (y-axis pixel scaling factor, matching the pixel size difference between the two cameras); by using the above scaling ratio, all pixel coordinates {(uA1,vA1),(uA2,vA2),...} of the target cooking area are converted into infrared coordinates {(uB1,vB1),(uB2,vB2),...}, thus forming a set of food surface temperatures.

[0103] In an optional implementation of this embodiment, based on accurately mapping the target cooking area to an infrared image, the surface temperature of the food being cooked can be determined using the following technical solution: First, based on the spatial transformation parameters obtained from image registration (e.g., affine or perspective transformation matrix), the outline of the target cooking area is precisely projected onto the infrared image coordinate system, thereby locating the pixel set of the corresponding area; then, the infrared radiation intensity data of all pixels in the area is extracted, and converted into actual temperature values ​​according to the calibration parameters of the infrared sensor (e.g., emissivity, ambient temperature compensation, distance and angle correction coefficients); based on this, further... The process involves calculating the average temperature, maximum / minimum temperature, temperature standard deviation, and heat distribution histogram of the area to quantify the thermal uniformity of the food surface. To improve accuracy, time-series filtering (e.g., Kalman filtering) can be applied to multiple frames of images to suppress noise, and clustering algorithms can be used to identify and eliminate non-food interference points such as cookware edges or empty stove areas. In addition, deep learning models can be introduced to identify food types and dynamically adjust emissivity parameters to improve temperature measurement accuracy. Finally, the surface temperature of the food is fed back in real time through visual thermal map overlay or numerical output, providing a reliable basis for intelligent temperature control and optimization of the cooking process.

[0104] Step 250: Determine the internal temperature of the cooking ingredients based on the surface temperature.

[0105] Optionally, in this embodiment, after determining the surface temperature of the food being cooked, the internal temperature of the food can be further determined based on the surface temperature. Optionally, determining the internal temperature of the food being cooked based on the surface temperature may include: acquiring the temperature of the cooking pot in real time using a temperature sensor deployed at the bottom of the cooking pot, and collecting stove power data; inputting the current average surface temperature, the temperature of the cooking pot, the stove power data, and the historical internal temperature values ​​of the food being cooked into a preset internal temperature determination model to obtain the current internal temperature of the food being cooked.

[0106] In one optional implementation of this embodiment, a temperature sensor is deployed at the bottom of the cooking pot, allowing the temperature of the pot to be collected in real time during cooking. Simultaneously, the current operating level of the stove can be determined, and the stove's power data can be determined based on this operating level. Furthermore, the internal temperature of the food being cooked at the current moment can be obtained from a preset model that combines the currently determined average surface temperature, the temperature of the cooking pot, the stove's power data, and the historical internal temperature input values ​​of the food.

[0107] The model for determining the internal temperature of cooking ingredients can be a pre-tuned multimodal large model or other neural network models; this embodiment does not limit it.

[0108] In one optional implementation of this embodiment, the surface temperature of the food, the temperature of the bottom of the pot, and the heat can be integrated. The internal temperature of the food can be determined by a trained cooking food internal temperature determination model (for example, it can be trained based on massive historical cooking data and long-term memory historical operation data) to fit the internal temperature of the food (e.g., the center temperature of the steak is 60°C, to determine whether it is medium-rare) and the overall temperature field inside the pot (e.g., the temperature of the edge of the pot is 100°C, with no food in the area).

[0109] In this embodiment, after acquiring the relevant data, the following steps can be taken to process it: Infrared surface temperature denoising: The average temperature of 3×3 neighboring pixels is used to replace the original pixel value, filtering out isolated high / low values ​​and retaining the true temperature distribution of the food surface; Sensor data smoothing: For the bottom temperature and heat, a sliding window is used to average 5 sampling points to eliminate high-frequency fluctuations of the sensor; Time synchronization alignment: Based on the infrared time of the glasses, the bottom temperature and heat data are interpolated to the infrared temperature time through linear interpolation.

[0110] Furthermore, morphological parameters of cooking ingredients can be extracted from the segmentation results of visible light cameras. For example, area S: the actual area corresponding to a single pixel (pre-calibrated, 1 pixel = 0.1 cm² at a distance of 1 m); thickness d: pre-stored based on the type of ingredient; physical properties: specific heat capacity and thermal conductivity of common ingredients are pre-stored in a multimodal large model.

[0111] The internal temperature T_in(t) of the food can be determined by the following formula:

[0112] ;

[0113] Where α, β, γ, and δ are the weight coefficients learned by the model for determining the internal temperature of cooking ingredients through massive amounts of data (for example, in the case of pan-frying steak, α=0.4, β=0.3, γ=5, and δ=0.2, and each value can be dynamically adjusted according to the type of ingredient). Tsurf_avg(t) is the average surface temperature of the ingredient at time t; Tbottom(t) is the surface temperature; P(t) is the power of the stove; and Tin_hist(t-Δt) is the historical internal temperature at time t-Δt. This indicates the weight of historical internal temperature in the current forecast, and is usually set to a value between 0 and 1, such as 0.5.

[0114] Step 260: Determine the current cooking state based on the internal temperature, and generate the target execution instruction based on the current cooking state.

[0115] Optionally, in this embodiment, after determining the internal temperature of the food being cooked, the current cooking state can be further determined based on the determined internal temperature of the food being cooked, and a corresponding execution instruction can be generated based on the current cooking state. In this embodiment, this is referred to as the target execution instruction.

[0116] Optionally, in this embodiment, determining the current cooking state based on the internal temperature and generating a target execution command based on the current cooking state may include: dynamically comparing the internal temperature with the target temperature-time curve of the target recipe to determine the deviation trend between the current cooking state and the ideal path; generating a heat control command when it is determined that the heating rate is greater than a set threshold and the internal temperature is close to the target doneness; and transmitting the heat control command to the stove controller via a Bluetooth communication link so that the stove controller can adjust the heat based on the heat control command.

[0117] In an optional implementation of this embodiment, while determining the target recipe to be cooked, the target temperature-time curve of the target recipe to be cooked can also be determined. Through this curve, the cooking state corresponding to different times and different temperatures can be determined. For example, the cooking state corresponding to a temperature of 150 degrees and 2 minutes is a rare steak; the cooking state corresponding to a temperature of 160 degrees and 3 minutes is medium-rare.

[0118] In this embodiment, the ideal path is the target temperature-time curve involved in this embodiment, which is a function of time t and represents the temperature sequence that the ingredients should reach under ideal cooking conditions.

[0119] In this embodiment, by dynamically comparing the determined current internal temperature with the target temperature-time curve of the target recipe, the deviation trend between the current cooking state and the ideal path can be determined. For example, the instantaneous temperature deviation ΔT can be calculated, and the actual heating rate can be fitted using a sliding window (such as the most recent 5 data points) combined with linear regression or Kalman filtering algorithms, and it can be determined whether it is approaching the target doneness range (e.g., ≤5°C from the target temperature). When the heating rate is detected to exceed the set threshold (e.g., 3°C / min) and approach the target temperature, it is determined that there is an overheating risk, triggering the fire control logic. A fire reduction command is generated through a rule engine or incremental PID algorithm and encapsulated into a structured data packet. Furthermore, the command can be sent to the Bluetooth module of the cooktop via Bluetooth Low Energy service, and the cooktop controller can parse it and adjust the actuator.

[0120] In another optional implementation of this embodiment, after generating the fire control command, it may further include: generating prompt information that matches the fire control command, and broadcasting or displaying the prompt information through smart glasses.

[0121] Optionally, in this embodiment, while generating the heat control command, semantic prompts can be automatically generated based on the command content (e.g., reduce heat, increase heat) and the current cooking context (dish name, doneness stage), and multimodal encoding can be performed: the text information is used for visual display, and simultaneously converted into voice data; this prompt information is transmitted to the user's smart glasses via an established Bluetooth link (or a wireless communication link or local area network, which is not limited in this embodiment), and pop-up text is superimposed on the lens display area in an unobstructed manner, and voice prompts are simultaneously broadcast through bone conduction or speakers. Simultaneously, head posture recognition can be combined to achieve context awareness, triggering prompts only when the user is facing the stove to avoid interference. Users can also provide feedback and confirmation through voice, gestures, etc., realizing real-time visualization and voice presentation of cooking control information, improving human-machine collaboration efficiency and operational safety.

[0122] This embodiment utilizes an infrared and visible light camera integrated into smart glasses, combined with a pot bottom temperature probe and a heat sensor in the cooking equipment, to construct a multi-dimensional data acquisition system. Simultaneously, it deeply integrates image recognition, temperature distribution, and sensor data to fit a precise temperature field across the entire food surface, interior, and pot, overcoming the limitations of the linear assumptions of traditional heat conduction models. Through Bluetooth bidirectional communication, the smart glasses can control the stove's heat in real time and intelligently identify cooking anomalies, guiding user intervention through AR prompts / voice interaction. Addressing the needs for precise operation and temperature control, cooking parameters are dynamically optimized based on a precise temperature model, lowering the barrier to manual operation and enabling even non-professional users to efficiently complete standardized and healthy cooking.

[0123] Based on the above technical solution, after determining the cooking data of the target recipe to be cooked, the auxiliary cooking method may further include: displaying the cooking data through the smart glasses so that the target user can view the cooking data in real time.

[0124] In one optional implementation of this embodiment, after determining the cooking data of the target recipe (e.g., target temperature-time curve, recommended heat level, estimated remaining time, ingredient flipping prompts, and other key parameters), immersive information display can be further achieved through smart glasses. For example, the cooking data can be encapsulated into a structured instruction package and transmitted to the smart glasses terminal via Bluetooth. After receiving the data, the glasses will overlay relevant information in real time in its near-eye display area using augmented reality. For example, the current target temperature (e.g., target: 65°C), actual temperature value, heating progress bar, countdown prompts, and operation instructions (e.g., flip in 30 seconds) can be displayed in a fixed floating position in the user's field of vision. The interface layout adopts an unobstructed design, combined with icons, color coding (e.g., red warning, green normal) and dynamic animations to improve readability, and supports dynamic adjustment of the display position according to the user's line of sight or head posture. In addition, key nodes can be triggered simultaneously with voice prompts to achieve dual-channel guidance of vision and hearing.

[0125] This method allows users to continuously monitor the cooking process without taking their eyes off the food, significantly improving ease of operation and process control, and achieving true intelligent cooking assistance.

[0126] To better understand the auxiliary cooking methods involved in this embodiment, Figure 3 This is a flowchart of an auxiliary cooking method provided according to Embodiment 2 of the present invention. In a specific implementation, it may include the following contents.

[0127] Users activate the multimodal big model through the voice interaction module of the smart glasses, and input the target recipe by voice (e.g., pan-fried steak with low oil). The big model retrieves the full process parameters of the recipe from the cloud, including the temperature curve (e.g., the surface temperature of the steak needs to be maintained at 120℃±5℃), the heat range (e.g., heat level 3-5 during the pan-frying stage), and the operation sequence (e.g., prompting to flip the steak when the lower surface temperature reaches 120 degrees or the upper surface reaches 100 degrees). The parameters are then synchronously sent to the smart glasses (for display / prompt) and the associated cooking devices (stove, smart cookware).

[0128] On the smart glasses: Infrared camera: Acquires infrared thermal images of the pot at a frequency of 2Hz, generating a two-dimensional temperature matrix (resolution ≥640×480, temperature accuracy ±0.5℃), capturing the spatial distribution of temperature (e.g., temperature difference between the center and edge of the food). Visible light camera: Acquires color images at a frame rate of 5fps, identifies food regions (outline, location, area) through an instance segmentation algorithm of a pre-trained model, and marks the "cooking target area" (e.g., the location of the steak).

[0129] Cooking equipment: The bottom temperature sensor of the pot and the firepower sensor of the stove (accuracy ±100W) transmit the real-time temperature and firepower of the bottom of the pot to the smart glasses via Bluetooth, with a latency of ≤100ms.

[0130] Large Model: By integrating image and sensor data through a multimodal large model, the operation history and data changes of key nodes in the cooking process are extracted, and historical data with long context are fused for long-term memory storage.

[0131] The multimodal large model processing workflow may include the following:

[0132] Step 1: Mapping the food region-temperature matrix.

[0133] The pre-trained model maps the coordinates of the cooking target area identified by visible light to an infrared temperature matrix to extract the surface temperature distribution of the food (e.g., the highest surface temperature of a steak is 130°C, and the edge is 110°C).

[0134] Pre-trained model architecture: Based on a lightweight version of Mask R-CNN (adapted to the computing power of smart glasses), the model can simultaneously output the steak bounding box and the steak pixel-level mask, which not only locates the overall position of the steak, but also distinguishes the pixel boundaries of the steak from other areas, and forms a set of food surface temperatures.

[0135] Step 2: Multi-dimensional fitting of internal temperature of food ingredients.

[0136] By integrating the surface temperature of the ingredients (infrared), the temperature of the bottom of the pot (contact type), and the heat (energy input), a heat conduction correction model trained by a large model (based on massive cooking data) and historical operation data from long-term memory is used to fit the internal temperature of the ingredients (e.g., the center temperature of a steak is 60°C, to determine whether it is rare or medium) and the overall temperature field inside the pot (e.g., the temperature at the edge of the pot is 100°C, in areas without ingredients).

[0137] Step 3: State recognition and decision output.

[0138] Heat control: A large model is used to compare and fit the temperature curve with the recipe temperature curve, and heat control commands are sent to the stove via Bluetooth (for example, from level 5 to level 3 to maintain the surface of the steak at 120°C) to achieve closed-loop temperature control.

[0139] Status Prompts: The multimodal large-scale model combines cooking steps with long-term memory of the cooking process to identify whether the cooking needs to be continued or if the operator needs to intervene and flip the food. Based on this, the model generates corresponding prompts using speech synthesis and text generation capabilities, and displays the status through the glasses.

[0140] Abnormal status: The multimodal large model identifies a scorching warning or a food surface temperature that continues to exceed 150°C, or a no-stirring warning (the food area remains still for more than 30 seconds, and the temperature gradient is abnormal).

[0141] Normal phase: The multimodal large model performs boiling detection (intense fluctuations in liquid level + temperature reaches 100℃, prompting a switch to low heat and simultaneous automatic control).

[0142] These recognition results are displayed to the user through augmented reality on the smart glasses (e.g., a virtual arrow indicating the stir-frying position) or through voice prompts (e.g., please flip the steak over; the current side temperature of the steak has reached 115°C).

[0143] Step 4: Dynamic iteration and termination.

[0144] During the cooking process, the large model can iterate the data every second to continuously optimize temperature fitting and state recognition; when the fitted temperature matches the recipe's endpoint parameters (e.g., 70°C in the center of the steak, well-done), it will automatically trigger a prompt to turn off the heat.

[0145] Example 3

[0146] Figure 4 This is a schematic diagram of the structure of an auxiliary cooking device according to Embodiment 3 of the present invention. For example, Figure 4 As shown, the device includes: a first acquisition module 410, a second acquisition module 420, a surface temperature determination module 430, and an internal temperature determination module 440.

[0147] The first acquisition module 410 is used to acquire the target recipe to be cooked and to determine the cooking data of the target recipe to be cooked.

[0148] The second acquisition module 420 is used to acquire infrared images of the cooking pot and images of the cooking pot during the cooking process.

[0149] The surface temperature determination module 430 is used to extract the target cooking area in the cooking pot image, map the target cooking area to the infrared image, and determine the surface temperature of the food being cooked based on the mapping result.

[0150] The internal temperature determination module 440 is used to determine the internal temperature of the food being cooked based on the surface temperature, determine the current cooking state based on the internal temperature, and generate a target execution instruction based on the current cooking state.

[0151] In this embodiment, the solution acquires a target recipe for cooking through a first acquisition module and determines the cooking data of the target recipe. During the cooking process, a second acquisition module acquires an infrared image of the cooking pot and an image of the cooking pot. A surface temperature determination module extracts the target cooking area from the cooking pot image and maps the target cooking area to the infrared image, determining the surface temperature of the food based on the mapping result. An internal temperature determination module determines the internal temperature of the food based on the surface temperature, determines the current cooking state based on the internal temperature, and generates a target execution command based on the current cooking state. This approach can accurately determine the surface and internal temperatures of the food, perceive the temperature distribution at multiple points inside the pot in real time, accurately estimate the thermal state of the food, and dynamically optimize the heating strategy based on the characteristics of the food, avoiding nutrient loss or burning and improving the accuracy of cooking.

[0152] In an optional implementation of this embodiment, the first acquisition module 410 is specifically used to receive target voice input data of the target user through the target wearable device, identify the target voice input data, and determine the target recipe to be cooked based on the identification result;

[0153] Obtain the target recipe to be cooked, and extract the preset cooking process parameter set associated with the target recipe to be cooked;

[0154] The preset cooking process parameter set is parsed to obtain the cooking data of the target recipe to be cooked;

[0155] The cooking data includes: preheating temperature threshold, stir-fry trigger temperature, recommended heat level, total heating time, and operating instructions for each stage.

[0156] In an optional implementation of this embodiment, the target wearable device is smart glasses; the smart glasses include an infrared camera and a visible light camera;

[0157] The second acquisition module 420 is specifically used to acquire infrared thermal images of the cooking pot through the infrared camera and generate a two-dimensional temperature matrix;

[0158] The cooking pot image is obtained by capturing an image of the appearance of the cooking pot using the visible light camera.

[0159] In an optional implementation of this embodiment, the auxiliary cooking device further includes a display module for displaying the cooking data through the smart glasses, so that the target user can view the cooking data in real time.

[0160] In an optional implementation of this embodiment, the surface temperature determination module 430 is specifically used to segment the cooking pot image and determine the target cooking area based on the segmentation result; wherein, the target cooking area is the area in the cooking pot image that contains cooking ingredients;

[0161] The mask value of each pixel in the target cooking area is determined, and based on the resolution of the target cooking area and the resolution of the infrared image, the mask value of each pixel in the target cooking area is mapped to the infrared image.

[0162] In an optional implementation of this embodiment, the surface temperature determination module 430 is further specifically used to extract the temperature values ​​corresponding to all pixels in the infrared temperature matrix based on the mask values ​​of each pixel in the mapped target cooking area, to form a set of food surface temperatures.

[0163] Each temperature statistic is determined based on the set of surface temperatures of the food ingredients;

[0164] The temperature statistics include at least one of the following: average temperature, maximum temperature, minimum temperature, center temperature, edge temperature, and temperature gradient.

[0165] In an optional implementation of this embodiment, the internal temperature determination module 440 is specifically used to obtain the temperature of the cooking pot in real time through a temperature sensor deployed at the bottom of the cooking pot, and to collect stove power data;

[0166] The internal temperature of the food being cooked is obtained by using the average surface temperature at the current moment, the temperature of the cooking pot, the power data of the stove, and the internal temperature of the food being cooked at historical moments as input values ​​in a preset model for determining the internal temperature of the food being cooked.

[0167] In an optional implementation of this embodiment, the internal temperature determination module 440 is further specifically used to dynamically compare the internal temperature with the target temperature-time curve of the target recipe to be cooked, and determine the deviation trend between the current cooking state and the ideal path.

[0168] When it is determined that the heating rate is greater than the set threshold and the internal temperature approaches the target level of doneness, a fire control command is generated.

[0169] The firepower control command is transmitted to the stove controller via a Bluetooth communication link, so that the stove controller can adjust the firepower based on the firepower control command.

[0170] In an optional implementation of this embodiment, the auxiliary cooking device further includes a prompting module, used to generate prompting information matching the fire control command, and to broadcast or display the prompting information through smart glasses.

[0171] The auxiliary cooking device provided in the embodiments of the present invention can execute the auxiliary cooking method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0172] In the technical solutions of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user cooking data (e.g., dietary habits, historical cooking data, etc.) all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0173] Example 4

[0174] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0175] For example, Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from the storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0176] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through, for example, computer networks such as the Internet and / or various telecommunications networks.

[0177] Processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above, such as an assisted cooking method, which may include: acquiring a target recipe to be cooked and determining cooking data of the target recipe; during the cooking process, acquiring an infrared image of a cooking pot and an image of the cooking pot, respectively; extracting a target cooking area from the image of the cooking pot and mapping the target cooking area to the infrared image, determining the surface temperature of the food to be cooked based on the mapping result; determining the internal temperature of the food to be cooked based on the surface temperature, determining the current cooking state based on the internal temperature, and generating a target execution instruction based on the current cooking state.

[0178] In some embodiments, the auxiliary cooking method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the auxiliary cooking method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the auxiliary cooking method by any other suitable means (e.g., by means of firmware).

[0179] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0180] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0181] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM), optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0182] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0183] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0184] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and Virtual Private Servers (VPS) in terms of management difficulty and weak business scalability.

[0185] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0186] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0187] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements, for example, the database detection method provided in any embodiment of this application.

[0188] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, and C++, as well as conventional procedural programming languages, such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LANs or WANs—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0189] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0190] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. An auxiliary cooking method, characterized in that, The method includes: Obtain the target recipe to be cooked, and determine the cooking data of the target recipe to be cooked; During the cooking process, infrared images of the cooking pot and images of the cooking pot are acquired respectively; Extract the target cooking area from the cooking pot image and map the target cooking area onto the infrared image; determine the surface temperature of the food being cooked based on the mapping result. The internal temperature of the food being cooked is determined based on the surface temperature, the current cooking state is determined based on the internal temperature, and a target execution instruction is generated based on the current cooking state.

2. The auxiliary cooking method according to claim 1, characterized in that, The step of acquiring the target recipe to be cooked and determining the cooking data of the target recipe to be cooked includes: The system receives target user voice input data through the target wearable device, identifies the target voice input data, and determines the target recipe to be cooked based on the identification result. Obtain the target recipe to be cooked, and extract the preset cooking process parameter set associated with the target recipe to be cooked; The preset cooking process parameter set is parsed to obtain the cooking data of the target recipe to be cooked; The cooking data includes: preheating temperature threshold, stir-fry trigger temperature, recommended heat level, total heating time, and operating instructions for each stage.

3. The auxiliary cooking method according to claim 2, characterized in that, The target wearable device is smart glasses; the smart glasses include an infrared camera and a visible light camera; The process of acquiring infrared images of the cooking pot and images of the pot itself during cooking includes: The infrared camera captures infrared thermal images of the cooking pot and generates a two-dimensional temperature matrix. The cooking pot image is obtained by capturing an image of the appearance of the cooking pot using the visible light camera.

4. The auxiliary cooking method according to claim 3, characterized in that, After determining the cooking data of the target recipe to be cooked, the method further includes: The cooking data is displayed through the smart glasses so that the target user can view the cooking data in real time.

5. The auxiliary cooking method according to claim 1, characterized in that, The step of extracting the target cooking area from the cooking pot image and mapping the target cooking area onto the infrared image includes: The cooking pot image is segmented, and the target cooking region is determined based on the segmentation results; wherein, the target cooking region is the region in the cooking pot image that contains cooking ingredients; The mask value of each pixel in the target cooking area is determined, and based on the resolution of the target cooking area and the resolution of the infrared image, the mask value of each pixel in the target cooking area is mapped to the infrared image.

6. The auxiliary cooking method according to claim 5, characterized in that, The determination of the surface temperature of the food ingredients based on the mapping results includes: In the infrared temperature matrix, based on the mask values ​​of each pixel in the mapped target cooking area, the temperature values ​​corresponding to all pixels are extracted to form a set of food surface temperatures. Each temperature statistic is determined based on the set of surface temperatures of the food ingredients; The temperature statistics include at least one of the following: average temperature, maximum temperature, minimum temperature, center temperature, edge temperature, and temperature gradient.

7. The auxiliary cooking method according to claim 1, characterized in that, Determining the internal temperature of the food being cooked based on the surface temperature includes: The temperature of the cooking pot is obtained in real time by a temperature sensor deployed at the bottom of the cooking pot, and the power data of the stove is collected. The internal temperature of the food being cooked is obtained by using the average surface temperature at the current moment, the temperature of the cooking pot, the power data of the stove, and the internal temperature of the food being cooked at historical moments as input values ​​in a preset model for determining the internal temperature of the food being cooked.

8. The auxiliary cooking method according to claim 1, characterized in that, The step of determining the current cooking state based on the internal temperature and generating a target execution instruction based on the current cooking state includes: The internal temperature is dynamically compared with the target temperature-time curve of the target recipe to be cooked to determine the deviation trend between the current cooking state and the ideal path. When it is determined that the heating rate is greater than the set threshold and the internal temperature approaches the target level of doneness, a fire control command is generated. The firepower control command is transmitted to the stove controller via a Bluetooth communication link, so that the stove controller can adjust the firepower based on the firepower control command.

9. The auxiliary cooking method according to claim 8, characterized in that, After generating fire control commands, the following is also included: Generate a prompt message that matches the fire control command, and broadcast or display the prompt message through smart glasses.

10. An auxiliary cooking device, characterized in that, include: The first acquisition module is used to acquire the target recipe to be cooked and to determine the cooking data of the target recipe to be cooked; The second acquisition module is used to acquire infrared images of the cooking pot and images of the cooking pot during the cooking process. A surface temperature determination module is used to extract the target cooking area from the cooking pot image, map the target cooking area to the infrared image, and determine the surface temperature of the food being cooked based on the mapping result. An internal temperature determination module is used to determine the internal temperature of the food being cooked based on the surface temperature, determine the current cooking state based on the internal temperature, and generate a target execution instruction based on the current cooking state.

11. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the auxiliary cooking method according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the auxiliary cooking method according to any one of claims 1-9.

13. A computer program product comprising a computer program that, when executed by a processor, implements the auxiliary cooking method according to any one of claims 1-9.

Images