Intelligent cooking method and device

Abstract

The invention discloses an intelligent cooking method and device, and the method comprises the steps: obtaining an initial cooking parameter of food in response to a cooking instruction triggered by a target object; the cooking instruction comprises the target cooking degree of the food; controlling the cooking equipment to cook food according to the initial cooking parameters; in the cooking process, real-time state data of the food are collected, the cooking state of the food is analyzed in real time, and the real-time cooking degree of the food is obtained; when the real-time cooking degree does not reach the target cooking degree, adjusting the initial cooking parameters in real time, and controlling the cooking equipment to continuously cook the food according to the adjusted cooking parameters to obtain an updated real-time cooking degree; and when the updated real-time cooking degree reaches the target cooking degree, stopping cooking the food. The cooking state of the food can be analyzed in real time, the cooking parameters are dynamically adjusted according to the real-time state of the food, intelligent cooking is achieved, and the cooking precision is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent cooking, and in particular to an intelligent cooking method and device. Background Art

[0002] Existing steam oven products mainly rely on users to manually set cooking time and temperature, and actively monitor the status of food during the cooking process. These steam ovens usually have basic temperature and time control functions, but cannot automatically adjust cooking parameters according to the actual state of food. In addition, users need to check the cooking status of the food by themselves to decide whether to add time or adjust the cooking conditions.

[0003] The steam ovens commonly used in society currently have some disadvantages, including the following aspects:

[0004] (1) Manual setting of cooking parameters with low accuracy: Users need to manually set the time and temperature based on experience, which lacks scientific basis and leads to unstable cooking results.

[0005] (2) Static cooking parameters and lack of dynamic adjustment: Existing steam ovens cannot adjust cooking parameters in real time according to the state of food, which easily leads to overcooking or undercooking.

[0006] (3) Visual inspection of food status, high risk of misjudgment: Relying on users to visually inspect food status, which is highly subjective and prone to misjudgment, affecting cooking quality.

[0007] (4) Lack of real-time status feedback and adjustment suggestions: It is impossible to provide real-time feedback and adjustment suggestions on the food status during the cooking process, making it difficult for users to adjust cooking parameters in a timely manner.

[0008] (5) Complex operation and poor user experience: Frequent manual intervention and adjustment are required, and the operation is complex, which increases the user burden. Summary of the invention

[0009] The present application provides an intelligent cooking method and device, which can analyze the cooking status of food in real time and dynamically adjust cooking parameters according to the real-time status of food, thereby realizing intelligent cooking and improving cooking accuracy.

[0010] In one aspect, the present application provides an intelligent cooking method, the method comprising:

[0011] In response to a cooking instruction triggered by a target object, obtaining initial cooking parameters of the food; the cooking instruction includes a target degree of doneness of the food;

[0012] Controlling the cooking equipment to cook the food according to the initial cooking parameters;

[0013] During the cooking process, real-time state data of the food is collected, the cooking state of the food is analyzed in real time, and the real-time doneness of the food is obtained;

[0014] When the real-time doneness does not reach the target doneness, the initial cooking parameters are adjusted in real time, and the cooking device is controlled to continue cooking the food according to the adjusted cooking parameters to obtain an updated real-time doneness;

[0015] When the updated real-time doneness reaches the target doneness, cooking of the food is stopped.

[0016] In an exemplary embodiment, the method further comprises:

[0017] Acquiring sample food status data of the sample food; the sample food status data is marked with a sample doneness label;

[0018] Performing recognition processing on the sample food state data based on the initial preset model to obtain a sample doneness recognition result of the sample food state data;

[0019] According to the difference between the sample state maturity recognition result and the sample maturity label, the initial preset model is trained to obtain a maturity recognition model;

[0020] The collecting of the real-time state data of the food, performing real-time analysis on the cooking state of the food, and obtaining the real-time doneness of the food includes:

[0021] The real-time status data of the food is collected, and the real-time status data is input into the doneness recognition model to obtain the real-time doneness of the food.

[0022] In an exemplary embodiment, the initial preset model includes an initial feature extraction network and an initial doneness recognition network, and the sample food state data is identified and processed based on the initial preset model to obtain a sample doneness recognition result of the sample food state data, including:

[0023] Performing feature extraction processing on the sample food state data based on the initial feature extraction network to obtain sample state features;

[0024] Based on the initial maturity recognition network, maturity recognition processing is performed on the sample state features to obtain the sample maturity recognition result.

[0025] In an exemplary embodiment, the initial feature extraction network includes an initial color feature extraction network, an initial shape feature extraction network, and an initial browning degree extraction network, and the feature extraction processing of the sample food state data based on the initial feature extraction network to obtain the sample state feature includes:

[0026] Based on the initial color feature extraction network, color feature extraction processing is performed on the sample food state data to obtain sample color features;

[0027] Based on the initial shape feature extraction network, shape feature extraction processing is performed on the sample food state data to obtain sample shape features;

[0028] Based on the initial browning degree extraction network, extracting the browning degree characteristics of the sample food state data to obtain the sample browning degree characteristics;

[0029] The sample color feature, the sample shape feature and the sample browning degree feature are determined as the sample state feature.

[0030] In an exemplary embodiment, the method further comprises:

[0031] Acquire first sample cooking data; the first sample cooking data is marked with a sample cooking time tag; the first sample cooking data includes initial state information of the sample food and the target doneness;

[0032] Performing time prediction processing on the first sample cooking data based on a first preset model to obtain a sample cooking time prediction result of the first sample cooking data;

[0033] According to the difference between the sample cooking time prediction result and the sample cooking time label, training the first preset model to obtain a cooking time prediction model;

[0034] Inputting the initial state information and the target doneness into the cooking time prediction model to obtain an initial cooking time;

[0035] The initial cooking parameters are determined according to the initial cooking time.

[0036] In an exemplary embodiment, the method further comprises:

[0037] Acquire second sample cooking data; the second sample cooking data is marked with a sample cooking temperature label; the second sample cooking data includes initial state information of the sample food and the target doneness;

[0038] Performing temperature prediction processing on the second sample cooking data based on a second preset model to obtain a sample cooking temperature prediction result of the second sample cooking data;

[0039] According to the difference between the sample cooking temperature prediction result and the sample cooking temperature label, training the second preset model to obtain a cooking temperature prediction model;

[0040] Inputting the initial state information and the target doneness into the cooking temperature prediction model to obtain an initial cooking temperature;

[0041] The initial cooking parameters are determined according to the initial cooking temperature.

[0042] In an exemplary embodiment, the cooking instruction includes a first doneness confirmation instruction, and the obtaining of initial cooking parameters of the food in response to the cooking instruction triggered by the target object includes:

[0043] In response to the first doneness confirmation instruction triggered by the target object, determining a first target doneness of the food;

[0044] Controlling a collection device to collect information of the food to obtain initial state information of the food;

[0045] determining a first initial cooking parameter according to the initial state information and the first target doneness;

[0046] The step of inputting the initial state information and the target doneness into the cooking temperature prediction model to obtain the initial cooking temperature includes:

[0047] Inputting the initial state information and the first target doneness into the cooking temperature prediction model to obtain a first initial cooking temperature;

[0048] The determining the initial cooking parameters according to the initial cooking temperature comprises:

[0049] The first initial cooking parameter is determined according to the first initial cooking temperature.

[0050] In an exemplary embodiment, the cooking instruction includes a second doneness confirmation instruction and a cooking parameter determination instruction, and the obtaining of the initial cooking parameters of the food in response to the cooking instruction triggered by the target object includes:

[0051] In response to the second doneness confirmation instruction triggered by the target object, determining a second target doneness of the food;

[0052] In response to the cooking parameter determination instruction triggered by the target object, determining a second initial cooking time and a second initial cooking temperature of the food;

[0053] A second initial cooking parameter is determined according to the second target doneness, the second initial cooking time, and the second initial cooking temperature.

[0054] In an exemplary embodiment, the method further comprises:

[0055] When the cooking time reaches the second initial cooking time, obtaining the current real-time degree of doneness;

[0056] If the current real-time doneness does not reach the second target doneness, calculating the additional cooking time required for the food to reach the target doneness;

[0057] In response to the supplementary cooking instruction triggered by the target object, the cooking device is controlled to adjust the cooking time to the supplementary cooking time and continue cooking.

[0058] Another aspect provides an intelligent cooking system, the intelligent cooking system comprising a sensing device and a processing device;

[0059] The sensing device is used to collect real-time status data of the food during the cooking process;

[0060] The processing device is used to perform real-time analysis on the real-time state of the food to obtain the real-time doneness of the food.

[0061] Another aspect provides an intelligent cooking device, the device comprising:

[0062] An initial cooking parameter acquisition module, used to acquire initial cooking parameters of food in response to a cooking instruction triggered by a target object; the cooking instruction includes a target degree of doneness of the food;

[0063] A cooking module, used for controlling the cooking device to cook the food according to the initial cooking parameters;

[0064] A real-time doneness acquisition module is used to collect the real-time state data of the food during the cooking process, perform real-time analysis on the cooking state of the food, and obtain the real-time doneness of the food;

[0065] an updated real-time doneness acquisition module, used for adjusting the initial cooking parameters in real time when the real-time doneness does not reach the target doneness, and controlling the cooking device to continue cooking the food according to the adjusted cooking parameters to obtain an updated real-time doneness;

[0066] The cooking stop module is used to stop cooking the food when the updated real-time doneness reaches the target doneness.

[0067] On the other hand, a steam oven is provided, which is used to implement the intelligent cooking method as described above.

[0068] On the other hand, an electronic device is provided, comprising a processor, wherein the processor is used for storing a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the intelligent cooking method as described above.

[0069] On the other hand, a computer-readable storage medium is provided, wherein the computer-readable storage medium contains at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by a processor to implement the above-mentioned intelligent cooking method.

[0070] The intelligent cooking method and device provided by this application have the following technical effects:

[0071] The present application obtains the initial cooking parameters of the food in response to the cooking instruction triggered by the target object; the cooking instruction includes the target doneness of the food; the cooking device is controlled to cook the food according to the initial cooking parameters; during the cooking process, the real-time state data of the food is collected, the cooking state of the food is analyzed in real time, and the real-time doneness of the food is obtained; when the real-time doneness does not reach the target doneness, the initial cooking parameters are adjusted in real time, and the cooking device is controlled to continue cooking the food according to the adjusted cooking parameters to obtain an updated real-time doneness; when the updated real-time doneness reaches the target doneness, the cooking of the food is stopped. The present application can analyze the cooking state of the food in real time and dynamically adjust the cooking parameters according to the real-time state of the food, thereby realizing intelligent cooking, improving cooking accuracy, and reducing food waste caused by improper cooking.

[0072] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions and advantages of the embodiments of this specification or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0074] Figure 1 It is a flowchart of an intelligent cooking method provided by an embodiment of this specification;

[0075] Figure 2 It is a schematic diagram of a process for determining initial cooking parameters according to a cooking time prediction model provided by an embodiment of this specification;

[0076] Figure 3 It is a schematic diagram of a process for determining initial cooking parameters according to a cooking temperature prediction model provided by an embodiment of this specification;

[0077] Figure 4 is a schematic diagram of a process for determining a first initial cooking parameter provided by an embodiment of this specification;

[0078] Figure 5 is a schematic diagram of a flow chart for determining a second initial cooking parameter provided by an embodiment of this specification;

[0079] Figure 6 It is a schematic diagram of a cooking process according to the supplementary cooking time provided in an embodiment of this specification;

[0080] Figure 7 It is a schematic diagram of a comprehensive timing flow of a cooking process provided by an embodiment of this specification;

[0081] Figure 8 It is a structural diagram of a server for intelligent cooking provided in an embodiment of this specification. DETAILED DESCRIPTION

[0082] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0083] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0084] The embodiments of the present specification provide an intelligent cooking system, which may include at least a sensing device and a processing device.

[0085] In an embodiment of the present application, the sensing device may include various sensors, such as a temperature sensor, a humidity sensor, a weight sensor, and a visual sensor, etc. The sensing device is used to collect real-time status data of food before cooking and during cooking, so that the processing device can perform real-time analysis on the data.

[0086] In an embodiment of the present application, the processing device connects these sensors, and is used to obtain data such as temperature, humidity, weight, and image of the food collected by the sensors in real time, and perform real-time analysis on these data, and dynamically adjust the cooking time and cooking temperature according to the analysis results to ensure that the food can reach the expected state.

[0087] The following introduces an intelligent cooking method of the present application. Figure 1 is a flow chart of an intelligent cooking method provided in an embodiment of this specification. Figure 7 It is a comprehensive timing diagram of intelligent cooking provided by the embodiment of this specification. This specification provides method operation steps as described in the embodiment or flow chart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the actual system or server product is executed, it can be executed in sequence or in parallel (for example, in a parallel processor or multi-threaded processing environment) according to the method shown in the embodiment or the accompanying drawings. Specifically, Figure 1 As shown, the method may include:

[0088] S1: In response to a cooking instruction triggered by a target object, obtaining initial cooking parameters of food; the cooking instruction includes a target degree of doneness of the food.

[0089] In an embodiment of the present application, multiple sensors are installed in the cooking device, and the sensors may include a temperature sensor, a humidity sensor, a weight sensor, and a visual sensor. A processing device is used to connect these sensors to obtain the temperature, humidity, weight, and image data of the food in the cooking device in real time.

[0090] The embodiment of the present application obtains the initial state data of the food through the sensor, so as to determine the initial cooking parameters of the food when performing intelligent cooking based on the initial state data.

[0091] In an exemplary embodiment, if Figure 2 As shown, the method may also include:

[0092] S011: Acquire first sample cooking data; the first sample cooking data is marked with a sample cooking time tag; the first sample cooking data includes initial state information of the sample food and the target doneness.

[0093] S012: Perform time prediction processing on the first sample cooking data based on a first preset model to obtain a sample cooking time prediction result of the first sample cooking data.

[0094] S013: According to the difference between the sample cooking time prediction result and the sample cooking time label, the first preset model is trained to obtain a cooking time prediction model.

[0095] S014: Inputting the initial state information and the target doneness into the cooking time prediction model to obtain an initial cooking time.

[0096] S015: Determine the initial cooking parameters according to the initial cooking time.

[0097] In an embodiment of the present application, a model trained by a machine learning algorithm is used to obtain a cooking time prediction model, which can predict the optimal cooking time of food in a cooking device based on food data collected by a sensor.

[0098] The embodiment of the present application can quickly and accurately predict the optimal cooking time of food through a cooking time prediction model, thereby determining cooking parameters, which can effectively reduce errors caused by human prediction and improve cooking accuracy.

[0099] In an exemplary embodiment, if Figure 3 As shown, the method may also include:

[0100] S021: Acquire second sample cooking data; the second sample cooking data is marked with a sample cooking temperature label; the second sample cooking data includes initial state information of the sample food and the target doneness.

[0101] S022: Perform temperature prediction processing on the second sample cooking data based on a second preset model to obtain a sample cooking temperature prediction result of the second sample cooking data.

[0102] S023: According to the difference between the sample cooking temperature prediction result and the sample cooking temperature label, the second preset model is trained to obtain a cooking temperature prediction model.

[0103] S024: Inputting the initial state information and the target doneness into the cooking temperature prediction model to obtain an initial cooking temperature.

[0104] S025: Determine the initial cooking parameters according to the initial cooking temperature.

[0105] In an exemplary embodiment, determining the initial cooking parameters according to the initial cooking time may include:

[0106] Inputting the initial state information and the target doneness into the cooking temperature prediction model to obtain an initial cooking temperature;

[0107] The initial cooking parameters are determined according to the initial cooking time and the initial cooking temperature.

[0108] In an embodiment of the present application, a model trained by a machine learning algorithm is used to obtain a cooking temperature prediction model, which can predict the optimal cooking temperature of food in a cooking device based on food data collected by a sensor.

[0109] The embodiment of the present application uses a cooking temperature prediction model to quickly and accurately predict the optimal cooking temperature of food, thereby determining cooking parameters, which can effectively reduce errors caused by human prediction and improve cooking accuracy.

[0110] In the embodiment of the present application, a cooking time prediction model and a cooking temperature prediction model are obtained by AI algorithm training, which can respectively predict the optimal cooking time and the optimal cooking temperature. In addition, a cooking parameter prediction model can also be obtained by algorithm training. Through this cooking parameter prediction model, the optimal cooking time and the optimal cooking temperature can be predicted at the same time, thereby obtaining the initial cooking parameters.

[0111] The embodiment of the present application obtains the temperature, humidity, weight and image data of the food through sensors in the cooking equipment, and then predicts the optimal cooking temperature and time of the food based on a model trained by a machine learning algorithm, thereby reducing the errors caused by human prediction and effectively improving cooking accuracy.

[0112] In an exemplary embodiment, if Figure 4 As shown, the cooking instruction includes a first doneness confirmation instruction, and the cooking instruction triggered in response to the target object obtains the initial cooking parameters of the food, including:

[0113] S111: In response to the first doneness confirmation instruction triggered by the target object, determining a first target doneness of the food.

[0114] In an embodiment of the present application, when the target object chooses to perform intelligent cooking, the expected degree of doneness of the food, such as medium-rare, can be selected on the cooking device.

[0115] The embodiment of the present application determines the target doneness of the food through instructions triggered by the target object, thereby determining the cooking parameters of the food and performing the cooking process.

[0116] S112: Controlling a collection device to collect information of the food to obtain initial state information of the food.

[0117] In an embodiment of the present application, after confirming the target doneness of the food selected by the target object, the initial state data of the food is collected through collection devices such as temperature sensors, humidity sensors, weight sensors and visual sensors to obtain the initial state information of the food.

[0118] The embodiment of the present application arranges various sensors in the cooking device to collect and obtain the initial state data of the food, thereby obtaining the initial cooking parameters of the food.

[0119] S113: Determine first initial cooking parameters according to the initial state information and the first target doneness.

[0120] The step of inputting the initial state information and the target doneness into the cooking temperature prediction model to obtain the initial cooking temperature includes:

[0121] Inputting the initial state information and the first target doneness into the cooking temperature prediction model to obtain a first initial cooking temperature;

[0122] The determining the initial cooking parameters according to the initial cooking temperature comprises:

[0123] The first initial cooking parameter is determined according to the first initial cooking temperature.

[0124] In an exemplary embodiment, determining the initial cooking parameters according to the initial cooking time includes:

[0125] Inputting the initial state information and the target doneness into the cooking temperature prediction model to obtain an initial cooking temperature;

[0126] The initial cooking parameters are determined according to the initial cooking time and the initial cooking temperature.

[0127] In an exemplary embodiment, determining the first initial cooking parameter according to the initial state information and the first target doneness includes:

[0128] Inputting the initial state information and the first target doneness into the cooking temperature time model to obtain a first initial cooking time;

[0129] Inputting the initial state information and the first target doneness into the cooking temperature prediction model to obtain a first initial cooking temperature;

[0130] The first initial cooking parameter is determined according to the first initial cooking time and the first initial cooking temperature.

[0131] In an embodiment of the present application, after obtaining the initial state information of the food, the initial optimal cooking time and initial optimal cooking temperature of the food are calculated through a cooking time prediction model and a cooking temperature prediction model, and the predicted initial optimal cooking time and initial optimal cooking temperature are used as initial cooking parameters.

[0132] The embodiment of the present application uses the initial state information of the food, the target degree of doneness, and the algorithm prediction model to quickly and accurately obtain the optimal initial cooking parameters, which can effectively reduce the errors caused by human prediction and improve cooking accuracy.

[0133] In an embodiment of the present application, if the target object chooses to perform intelligent cooking, he only needs to select the expected degree of doneness of the food on the control panel of the cooking device. The collection device in the cooking device will collect the initial state data of the food, and use the model trained by the algorithm to predict the optimal cooking time and optimal cooking temperature of the food, which will be used as the initial cooking parameters of the food, thereby improving the cooking accuracy.

[0134] In an exemplary embodiment, if Figure 5 As shown, the cooking instruction includes a second doneness confirmation instruction and a cooking parameter determination instruction, and the cooking instruction triggered in response to the target object obtains the initial cooking parameters of the food, including:

[0135] S121: In response to the second doneness confirmation instruction triggered by the target object, determining a second target doneness of the food.

[0136] In an embodiment of the present application, when the target object does not choose to perform intelligent cooking, the expected doneness of the food, such as medium or other doneness, can be selected on the cooking device, and the expected doneness input by the target object can be used as the target doneness of the food.

[0137] S122: In response to the cooking parameter determination instruction triggered by the target object, determine a second initial cooking time and a second initial cooking temperature of the food.

[0138] In the embodiment of the present application, when the target object does not choose to perform intelligent cooking, the target object can input the cooking time and cooking temperature in addition to the expected doneness of the food.

[0139] S123: Determine second initial cooking parameters according to the second target doneness, the second initial cooking time, and the second initial cooking temperature.

[0140] In the embodiment of the present application, the target doneness, cooking time and cooking temperature input by the target object are directly used as the initial cooking parameters of the food.

[0141] In an embodiment of the present application, if the target object does not choose to perform intelligent cooking, the target object can select the expected doneness, cooking time and cooking temperature of the food on the cooking device control panel, and the above parameters input by the target object will be used as the initial cooking parameters of the food.

[0142] In the embodiment of the present application, the cooking instructions triggered by the target object can select different cooking methods to cook food. The target object can choose to input the expected doneness for intelligent cooking, or set parameters for cooking by itself, enriching the diversity of cooking method choices for the target object.

[0143] S2: Controlling the cooking device to cook the food according to the initial cooking parameters.

[0144] In an embodiment of the present application, if the target object chooses to input the expected doneness for intelligent cooking, the cooking device is controlled to cook the food according to the parameters predicted by the algorithm; if the target object chooses to input the expected doneness, cooking time and cooking temperature by himself, the cooking device is controlled to cook the food according to the cooking parameters entered by the target object.

[0145] S3: During the cooking process, real-time status data of the food is collected, and the cooking status of the food is analyzed in real time to obtain the real-time doneness of the food.

[0146] In an exemplary embodiment, the method may further include:

[0147] Acquiring sample food status data of the sample food; the sample food status data is marked with a sample doneness label;

[0148] Performing recognition processing on the sample food state data based on the initial preset model to obtain a sample doneness recognition result of the sample food state data;

[0149] According to the difference between the sample state maturity recognition result and the sample maturity label, the initial preset model is trained to obtain a maturity recognition model;

[0150] The collecting of the real-time state data of the food, performing real-time analysis on the cooking state of the food, and obtaining the real-time doneness of the food includes:

[0151] The real-time status data of the food is collected, and the real-time status data is input into the doneness recognition model to obtain the real-time doneness of the food.

[0152] In an embodiment of the present application, real-time status data of food can be collected through sensors and high-definition cameras in the cooking equipment. The sensors may include temperature sensors, humidity sensors, weight sensors, and visual sensors, etc.

[0153] In an embodiment of the present application, sample food status data is obtained, a sample doneness recognition result is obtained based on the sample food status data, a doneness recognition model is trained, and after the real-time status data of the food is input into the above-mentioned doneness recognition model, the cooking status of the food can be analyzed in real time to obtain the real-time doneness of the food in the cooking equipment.

[0154] The embodiment of the present application establishes a doneness recognition model and inputs the acquired real-time status data of the food into the doneness recognition model, so as to quickly obtain the real-time doneness of the food and quickly and accurately identify the current cooking status of the food so as to timely adjust the cooking parameters according to the real-time doneness of the food.

[0155] In an exemplary embodiment, the initial preset model includes an initial feature extraction network and an initial doneness recognition network, and the sample food state data is identified and processed based on the initial preset model to obtain a sample doneness recognition result of the sample food state data, including:

[0156] Performing feature extraction processing on the sample food state data based on the initial feature extraction network to obtain sample state features;

[0157] Based on the initial maturity recognition network, maturity recognition processing is performed on the sample state features to obtain the sample maturity recognition result.

[0158] In an embodiment of the present application, an initial feature extraction network is used to perform feature extraction processing on sample food state data to obtain sample state features, and then a doneness recognition processing is performed on the sample state features according to an initial doneness recognition network to obtain a sample doneness recognition result.

[0159] The embodiment of the present application obtains the sample state characteristics to obtain the sample doneness recognition result, and then facilitates model training based on the difference between the sample state doneness recognition result and the sample doneness label to obtain a doneness recognition model, so as to quickly and accurately obtain the cooking state of food during the cooking process, reduce errors caused by human judgment, and adjust cooking parameters in time according to the cooking state of the food, improve cooking accuracy, and avoid food waste and energy consumption.

[0160] In an exemplary embodiment, the initial feature extraction network includes an initial color feature extraction network, an initial shape feature extraction network, and an initial browning degree extraction network. The feature extraction process is performed on the sample food state data based on the initial feature extraction network to obtain the sample state feature, including:

[0161] Based on the initial color feature extraction network, color feature extraction processing is performed on the sample food state data to obtain sample color features;

[0162] Based on the initial shape feature extraction network, shape feature extraction processing is performed on the sample food state data to obtain sample shape features;

[0163] Based on the initial browning degree extraction network, extracting the browning degree characteristics of the sample food state data to obtain the sample browning degree characteristics;

[0164] The sample color feature, the sample shape feature and the sample browning degree feature are determined as the sample state feature.

[0165] In an embodiment of the present application, the initial feature extraction network includes an initial color feature extraction network, an initial shape feature extraction network, and an initial browning degree extraction network. The color features, shape features, browning degree features, etc. of the sample food are extracted through the initial color feature extraction network, the initial shape feature extraction network, and the initial browning degree extraction network to obtain the state features of the sample.

[0166] The embodiment of the present application performs feature extraction processing on sample food state data through an initial feature extraction network to obtain sample state features. The sample state features include color features, shape features, and browning degree features, thereby enriching the feature data when obtaining the food state, making it easier to obtain more accurate sample doneness identification results based on the sample state features, and to establish a more reliable and accurate doneness identification model.

[0167] In an exemplary embodiment, inputting the real-time status data into the doneness recognition model to obtain the real-time doneness of the food may include:

[0168] Inputting the real-time state data into the maturity recognition model, performing feature extraction processing on the real-time state data based on the target feature extraction network of the maturity recognition model to obtain target state features;

[0169] The target doneness recognition network based on the doneness recognition model performs doneness recognition processing on the target state features to obtain the real-time doneness of the food.

[0170] In an exemplary embodiment, the target feature extraction network includes a target color feature extraction network, a target shape feature extraction network, and a target browning degree extraction network. The target feature extraction network based on the doneness recognition model performs feature extraction processing on the real-time state data to obtain target state features, which may include:

[0171] Based on the target color feature extraction network, color feature extraction processing is performed on the real-time status data to obtain target color features;

[0172] Based on the target shape feature extraction network, shape feature extraction processing is performed on the real-time state data to obtain target shape features;

[0173] Based on the target browning degree extraction network, extracting the browning degree feature of the real-time status data to obtain the target browning degree feature;

[0174] The target color feature, the target shape feature and the target browning degree feature are determined as the target state feature.

[0175] In an embodiment of the present application, food state features in the cooking equipment are extracted, such as color, shape, degree of browning, etc., and the real-time doneness of the food is obtained based on a doneness recognition model.

[0176] The embodiment of the present application establishes a doneness recognition model through AI algorithm training, and then applies the obtained doneness recognition model to the cooking process. The food status information collected by the collection device in the cooking equipment is input into the above-mentioned doneness recognition model, so as to obtain the real-time doneness of the food. Then, based on the obtained real-time doneness, it is possible to quickly and accurately determine whether the food has reached the expected doneness, so as to facilitate timely adjustment of the cooking parameters of the food, and realize rapid cooking of the food while ensuring that the cooked food tastes good.

[0177] S4: When the real-time doneness does not reach the target doneness, the initial cooking parameters are adjusted in real time, and the cooking device is controlled to continue cooking the food according to the adjusted cooking parameters to obtain an updated real-time doneness.

[0178] In an exemplary embodiment, if the target object chooses to input the expected degree of doneness for intelligent cooking before cooking begins, the various sensors in the cooking equipment will continuously monitor and collect real-time temperature, humidity, weight and food surface image data during the cooking process. The processing device will analyze these data in real time and dynamically adjust the cooking time and cooking temperature based on the results of the analysis. If the analysis results obtained from the data collected by the sensor indicate that the cooking state of the food deviates from expectations, the cooking state will be automatically adjusted to ensure that the food reaches the expected degree of doneness of the target user.

[0179] The embodiment of the present application monitors and analyzes food in real time during the cooking process and dynamically adjusts cooking parameters to ensure that the food reaches the expected degree of doneness, reduces food waste due to improper cooking, avoids unnecessary energy consumption, and improves the cooking quality of food.

[0180] In an exemplary embodiment, if Figure 6 As shown, the method may also include:

[0181] S41: When the cooking time reaches the second initial cooking time, the current real-time doneness is obtained.

[0182] In an embodiment of the present application, the cooking parameters (including cooking time) at the beginning of cooking are set by the target object. When the cooking time reaches the cooking time set by the target object, the real-time doneness of the food at the current moment is obtained.

[0183] The embodiment of the present application obtains the current real-time doneness of the food and compares it with the target doneness to determine whether additional cooking is needed.

[0184] S42: If the current real-time doneness does not reach the second target doneness, calculate the additional cooking time required for the food to reach the target doneness.

[0185] In an embodiment of the present application, if the food in the cooking device does not reach the target doneness within the set cooking time, the additional cooking time required for the food to reach the target doneness is calculated based on the current state of the food, and a supplementary cooking time suggestion is issued to the target object. The supplementary cooking time suggestion includes the supplementary cooking time calculated above, and the supplementary time suggestion can be prompted through a display screen or sound.

[0186] The embodiment of the present application calculates and obtains the additional cooking time required for food in the cooking device to reach the target degree of doneness, and can make scientific and reasonable additional time suggestions to the target object to ensure that the food can reach the target degree of doneness set by the target object.

[0187] S43: In response to the supplementary cooking time instruction triggered by the target object, controlling the cooking device to adjust the cooking time to the supplementary cooking time and continue cooking.

[0188] In an embodiment of the present application, if the target object chooses to input the target doneness, cooking time and cooking temperature by himself, cooking is performed according to the above parameters input by the target object. During the cooking process, the camera in the cooking device periodically captures the surface image of the food, the sensor collects temperature, humidity and weight data, analyzes the collected data, extracts the surface state characteristics of the food, and obtains the current doneness according to the doneness recognition model. When the cooking time reaches the set value, it is determined whether the current doneness of the food has reached the expected doneness. If the food has not reached the expected doneness, the additional cooking time required to reach the expected doneness is calculated, and a prompt message is generated. If the target object chooses to accept the additional time suggestion, the cooking device continues to cook according to the additional cooking time, and continues to perform real-time monitoring and analysis during the cooking process.

[0189] In the embodiment of the present application, if the target object chooses to adjust the additional cooking time suggested by the additional time suggestion, the cooking will continue according to the time set by the target object, and the state of the food will still be monitored and analyzed in real time during the cooking process. The above steps S41-S43 will continue to be executed until the doneness of the food reaches the target doneness.

[0190] The embodiment of the present application can provide additional time suggestions for the target object by real-time monitoring and analysis of the cooking process. Even if the target object chooses to input the cooking parameters by himself, the cooking process can be monitored in real time, and scientific additional time suggestions for cooking can be provided to ensure that the food reaches the expected degree of doneness, avoid food waste due to improper cooking, and improve cooking accuracy.

[0191] S5: When the updated real-time doneness reaches the target doneness, stop cooking the food.

[0192] In an embodiment of the present application, when the real-time doneness reaches the expected doneness of the target object, the cooking device stops the cooking process and generates a prompt message, which is prompted through the display screen or sound of the cooking device to indicate that cooking is completed.

[0193] The embodiment of the present application compares the obtained real-time doneness with the target doneness. When the real-time doneness reaches the target doneness, the cooking process is ended, and a prompt message is generated to indicate the end of the cooking process, which can be a display screen prompt or a sound prompt, or a display screen and a sound prompt.

[0194] It can be seen from the technical solutions provided by the above embodiments of the present specification that the embodiments of the present specification obtain initial cooking parameters of food in response to cooking instructions triggered by a target object; the cooking instructions include the target doneness of the food; the cooking equipment is controlled to cook the food according to the initial cooking parameters; during the cooking process, real-time status data of the food is collected, and the cooking status of the food is analyzed in real time to obtain the real-time doneness of the food; when the real-time doneness does not reach the target doneness, the initial cooking parameters are adjusted in real time, and the cooking equipment is controlled to continue cooking the food according to the adjusted cooking parameters to obtain updated real-time doneness; when the updated real-time doneness reaches the target doneness, cooking of the food is stopped. In this application, food data is collected by sensors and AI algorithm prediction is used to obtain the cooking time and cooking temperature of the food, thereby reducing the operational burden of the target object and avoiding the risk of misjudgment; by real-time monitoring and analysis of the cooking status during the cooking process, and dynamic adjustment of the cooking parameters in a timely manner; it can effectively ensure that the food is always in the best cooking state and improve cooking accuracy and consistency; when the target object chooses to input the cooking parameters by himself, the cooking status can also be monitored and analyzed in real time during the cooking process, and it can be determined whether the cooking time needs to be increased before the end of cooking, and scientific time-added suggestions can be provided to effectively ensure that the food reaches the expected degree of doneness; through precise control and real-time adjustment of cooking parameters, the cooking quality can be effectively improved, food waste caused by improper cooking can be reduced, and unnecessary energy consumption can be avoided, thereby achieving energy saving and environmental protection.

[0195] The embodiment of this specification also provides a smart cooking device, the device comprising:

[0196] An initial cooking parameter acquisition module, used to acquire initial cooking parameters of food in response to a cooking instruction triggered by a target object; the cooking instruction includes a target degree of doneness of the food;

[0197] A cooking module, used for controlling the cooking device to cook the food according to the initial cooking parameters;

[0198] A real-time doneness acquisition module is used to collect the real-time state data of the food during the cooking process, perform real-time analysis on the cooking state of the food, and obtain the real-time doneness of the food;

[0199] an updated real-time doneness acquisition module, used for adjusting the initial cooking parameters in real time when the real-time doneness does not reach the target doneness, and controlling the cooking device to continue cooking the food according to the adjusted cooking parameters to obtain an updated real-time doneness;

[0200] The cooking stop module is used to stop cooking the food when the updated real-time doneness reaches the target doneness.

[0201] In an exemplary embodiment, the initial cooking parameter acquisition module may further include a first initial cooking parameter determination module, and the first initial cooking parameter determination module includes:

[0202] A first sample cooking data acquisition unit, used to acquire first sample cooking data; the first sample cooking data is marked with a sample cooking time tag; the first sample cooking data includes initial state information of the sample food and the target doneness;

[0203] a sample cooking time prediction result acquisition unit, configured to perform time prediction processing on the first sample cooking data based on a first preset model to obtain a sample cooking time prediction result of the first sample cooking data;

[0204] a cooking time prediction model acquisition unit, configured to train the first preset model according to the difference between the sample cooking time prediction result and the sample cooking time label to obtain a cooking time prediction model;

[0205] an initial cooking time acquisition unit, configured to input the initial state information and the target doneness into the cooking time prediction model to obtain an initial cooking time;

[0206] The first initial cooking parameter determination unit is used to determine the initial cooking parameter according to the initial cooking time.

[0207] In an exemplary embodiment, the initial cooking parameter acquisition module may further include a second initial cooking parameter determination module, and the second initial cooking parameter determination module includes:

[0208] a second sample cooking data acquisition unit, configured to acquire second sample cooking data; the second sample cooking data is marked with a sample cooking temperature label; the second sample cooking data includes initial state information of the sample food and the target doneness;

[0209] a sample cooking temperature prediction result acquisition unit, configured to perform temperature prediction processing on the second sample cooking data based on a second preset model to obtain a sample cooking temperature prediction result of the second sample cooking data;

[0210] a cooking temperature prediction model acquisition unit, configured to input the initial state information and the target degree of doneness into the cooking temperature prediction model to obtain an initial cooking temperature;

[0211] The second initial cooking parameter determination unit is used to determine the initial cooking parameter according to the initial cooking temperature.

[0212] In an exemplary embodiment, the initial cooking parameter acquisition module may include:

[0213] a first target doneness determination unit, configured to determine a first target doneness of the food in response to the first doneness confirmation instruction triggered by the target object;

[0214] an initial state information acquisition unit, used for controlling a collection device to collect information of the food, and obtaining initial state information of the food;

[0215] The first initial cooking parameter acquiring unit is used to determine the first initial cooking parameter according to the initial state information and the first target doneness.

[0216] In an exemplary embodiment, the initial cooking parameter acquisition module may further include:

[0217] a second target doneness determination unit, configured to determine a second target doneness of the food in response to the second doneness confirmation instruction triggered by the target object;

[0218] a second initial cooking time and temperature determining unit, configured to determine a second initial cooking time and a second initial cooking temperature of the food in response to the cooking parameter determination instruction triggered by the target object;

[0219] The second initial cooking parameter acquiring unit is used to determine the second initial cooking parameter according to the second target doneness, the second initial cooking time and the second initial cooking temperature.

[0220] In an exemplary embodiment, the real-time doneness acquisition module may include:

[0221] A sample food status data acquisition submodule is used to acquire sample food status data of the sample food; the sample food status data is marked with a sample doneness label;

[0222] A sample doneness recognition result acquisition submodule is used to perform recognition processing on the sample food state data based on an initial preset model to obtain a sample doneness recognition result of the sample food state data;

[0223] A doneness recognition model acquisition submodule, used to train the initial preset model according to the difference between the sample state doneness recognition result and the sample doneness label to obtain a doneness recognition model;

[0224] The real-time doneness acquisition submodule is used to collect the real-time status data of the food, input the real-time status data into the doneness recognition model, and obtain the real-time doneness of the food.

[0225] In an exemplary embodiment, the initial preset model includes an initial feature extraction network and an initial maturity recognition network, and the sample maturity recognition result acquisition submodule may include:

[0226] A sample state feature acquisition unit, used for performing feature extraction processing on the sample food state data based on the initial feature extraction network to obtain sample state features;

[0227] The sample maturity recognition result acquisition unit is used to perform maturity recognition processing on the sample state feature based on the initial maturity recognition network to obtain the sample maturity recognition result.

[0228] In an exemplary embodiment, the initial feature extraction network includes an initial color feature extraction network, an initial shape feature extraction network, and an initial browning degree extraction network, and the sample state feature acquisition unit may include:

[0229] A sample color feature acquisition subunit, used for performing color feature extraction processing on the sample food state data based on the initial color feature extraction network to obtain sample color features;

[0230] A sample shape feature acquisition subunit, used to extract shape features of the sample food state data based on the initial shape feature extraction network to obtain sample shape features;

[0231] A sample browning degree feature acquisition subunit is used to extract the browning degree feature of the sample food state data based on the initial browning degree extraction network to obtain the sample browning degree feature;

[0232] The sample state feature determination subunit is used to determine the sample color feature, the sample shape feature and the sample browning degree feature as the sample state feature.

[0233] In an exemplary embodiment, the updated real-time doneness acquisition module may include:

[0234] a current real-time degree of doneness obtaining unit, configured to obtain the current real-time degree of doneness when the cooking time reaches the second initial cooking time;

[0235] a supplementary cooking time acquisition unit, configured to calculate the supplementary cooking time required for the food to reach the target doneness if the current real-time doneness does not reach the second target doneness;

[0236] The supplementary cooking unit is used to control the cooking device to adjust the cooking time to the supplementary cooking time and continue cooking in response to the supplementary cooking instruction triggered by the target object.

[0237] The device and method embodiments in the device embodiments described above are based on the same inventive concept.

[0238] The embodiment of the present specification provides a steam oven, in which a sensor device, a processing device, etc. are provided, and the steam oven can implement the intelligent cooking method provided in the above method embodiment.

[0239] An embodiment of the present specification provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the intelligent cooking method provided in the above method embodiment.

[0240] An embodiment of the present application also provides a computer-readable storage medium, which can be set in a terminal to store at least one instruction or at least one program related to the intelligent cooking method in the method embodiment. The at least one instruction or at least one program is loaded and executed by the processor to implement the intelligent cooking method provided by the above method embodiment.

[0241] The embodiment of the present application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes to implement the intelligent cooking method provided by the above method embodiment.

[0242] Optionally, in the embodiments of this specification, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0243] The memory described in the embodiments of this specification can be used to store software programs and modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0244] The smart cooking method embodiments provided in the embodiments of this specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Figure 8 1 is a hardware structure block diagram of a server of an intelligent cooking method provided in an embodiment of this specification. Figure 8As shown, the server 800 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 810 (the central processing unit 810 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 830 for storing data, and one or more storage media 820 (such as one or more mass storage devices) for storing application programs 823 or data 822. Among them, the memory 830 and the storage medium 820 can be short-term storage or permanent storage. The program stored in the storage medium 820 may include one or more modules, each of which may include a series of instruction operations on the server. Furthermore, the central processing unit 810 can be configured to communicate with the storage medium 820 and execute a series of instruction operations in the storage medium 820 on the server 800. The server 800 may also include one or more power supplies 860, one or more wired or wireless network interfaces 850, one or more input and output interfaces 840, and / or one or more operating systems 821, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0245] The input / output interface 840 may be used to receive or send data via a network. The specific example of the network may include a wireless network provided by a communication provider of the server 800. In one example, the input / output interface 840 includes a network adapter (Network Interface Controller, NIC), which may be connected to other network devices via a base station so as to communicate with the Internet. In one example, the input / output interface 840 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0246] It can be understood by those skilled in the art that Figure 8 The structure shown is for illustration only and does not limit the structure of the above electronic device. Figure 8 More or fewer components as shown, or with Figure 8 Different configurations shown.

[0247] It can be seen from the above-mentioned embodiments of the intelligent cooking method and device provided by the present application that the present application obtains the initial cooking parameters of the food in response to the cooking instructions triggered by the target object; the cooking instructions include the target doneness of the food; the cooking equipment is controlled to cook the food according to the initial cooking parameters; during the cooking process, the real-time status data of the food is collected, and the cooking status of the food is analyzed in real time to obtain the real-time doneness of the food; when the real-time doneness does not reach the target doneness, the initial cooking parameters are adjusted in real time, and the cooking equipment is controlled to continue cooking the food according to the adjusted cooking parameters to obtain updated real-time doneness; when the updated real-time doneness reaches the target doneness, cooking of the food is stopped. This application collects food data through sensors and uses AI algorithms for prediction to obtain the cooking time and cooking temperature of food, thereby reducing the operational burden of the target object and avoiding the risk of misjudgment; by real-time monitoring and analysis of the cooking status during the cooking process and timely dynamic adjustment of the cooking parameters; it can effectively ensure that the food is always in the best cooking state and improve cooking accuracy and consistency; when the target object chooses to input the cooking parameters by himself, it can also monitor and analyze the cooking status in real time during the cooking process, determine whether the cooking time needs to be increased before the end of cooking, and provide scientific time-added suggestions to effectively ensure that the food reaches the expected degree of doneness; through precise control and real-time adjustment of cooking parameters, it can effectively improve the cooking quality, reduce food waste caused by improper cooking, avoid unnecessary energy consumption, and achieve energy saving and environmental protection.

[0248] It should be noted that the above sequence of the embodiments of this specification is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0249] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0250] A person skilled in the art will appreciate that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0251] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. An intelligent cooking method, characterized in that: The method comprises: In response to a cooking instruction triggered by a target object, obtaining initial cooking parameters of the food; the cooking instruction includes a target degree of doneness of the food; Controlling the cooking equipment to cook the food according to the initial cooking parameters; During the cooking process, real-time state data of the food is collected, the cooking state of the food is analyzed in real time, and the real-time doneness of the food is obtained; When the real-time doneness does not reach the target doneness, the initial cooking parameters are adjusted in real time, and the cooking device is controlled to continue cooking the food according to the adjusted cooking parameters to obtain an updated real-time doneness; When the updated real-time doneness reaches the target doneness, cooking of the food is stopped.

2. The method according to claim 1, characterized in that The method further comprises: Acquiring sample food status data of the sample food; the sample food status data is marked with a sample doneness label; Performing recognition processing on the sample food state data based on the initial preset model to obtain a sample doneness recognition result of the sample food state data; According to the difference between the sample state maturity recognition result and the sample maturity label, the initial preset model is trained to obtain a maturity recognition model; The collecting of the real-time state data of the food, performing real-time analysis on the cooking state of the food, and obtaining the real-time doneness of the food includes: The real-time status data of the food is collected, and the real-time status data is input into the doneness recognition model to obtain the real-time doneness of the food.

3. The method according to claim 2, characterized in that The initial preset model includes an initial feature extraction network and an initial doneness recognition network. The sample food state data is identified and processed based on the initial preset model to obtain a sample doneness recognition result of the sample food state data, including: Performing feature extraction processing on the sample food state data based on the initial feature extraction network to obtain sample state features; Based on the initial maturity recognition network, maturity recognition processing is performed on the sample state features to obtain the sample maturity recognition result.

4. The method according to claim 3, characterized in that The initial feature extraction network includes an initial color feature extraction network, an initial shape feature extraction network and an initial browning degree extraction network. The feature extraction process is performed on the sample food state data based on the initial feature extraction network to obtain the sample state feature, including: Based on the initial color feature extraction network, color feature extraction processing is performed on the sample food state data to obtain sample color features; Based on the initial shape feature extraction network, shape feature extraction processing is performed on the sample food state data to obtain sample shape features; Based on the initial browning degree extraction network, extracting the browning degree characteristics of the sample food state data to obtain the sample browning degree characteristics; The sample color feature, the sample shape feature and the sample browning degree feature are determined as the sample state feature.

5. The method according to claim 1, characterized in that The method further comprises: Acquire first sample cooking data; the first sample cooking data is marked with a sample cooking time tag; the first sample cooking data includes initial state information of the sample food and the target doneness; Performing time prediction processing on the first sample cooking data based on a first preset model to obtain a sample cooking time prediction result of the first sample cooking data; According to the difference between the sample cooking time prediction result and the sample cooking time label, training the first preset model to obtain a cooking time prediction model; Inputting the initial state information and the target doneness into the cooking time prediction model to obtain an initial cooking time; The initial cooking parameters are determined according to the initial cooking time.

6. The method according to claim 5, characterized in that The method further comprises: Acquire second sample cooking data; the second sample cooking data is marked with a sample cooking temperature label; the second sample cooking data includes initial state information of the sample food and the target doneness; Performing temperature prediction processing on the second sample cooking data based on a second preset model to obtain a sample cooking temperature prediction result of the second sample cooking data; According to the difference between the sample cooking temperature prediction result and the sample cooking temperature label, training the second preset model to obtain a cooking temperature prediction model; Inputting the initial state information and the target doneness into the cooking temperature prediction model to obtain an initial cooking temperature; The initial cooking parameters are determined according to the initial cooking temperature.

7. The method according to claim 6, characterized in that The cooking instruction includes a first doneness confirmation instruction, and the cooking instruction triggered in response to the target object, obtaining the initial cooking parameters of the food, includes: In response to the first doneness confirmation instruction triggered by the target object, determining a first target doneness of the food; Controlling a collection device to collect information of the food to obtain initial state information of the food; determining a first initial cooking parameter according to the initial state information and the first target doneness; The step of inputting the initial state information and the target doneness into the cooking temperature prediction model to obtain the initial cooking temperature includes: Inputting the initial state information and the first target doneness into the cooking temperature prediction model to obtain a first initial cooking temperature; The determining the initial cooking parameters according to the initial cooking temperature comprises: The first initial cooking parameter is determined according to the first initial cooking temperature.

8. The method according to claim 1, characterized in that The cooking instruction includes a second doneness confirmation instruction and a cooking parameter determination instruction, and the cooking instruction triggered in response to the target object, obtaining the initial cooking parameters of the food, includes: In response to the second doneness confirmation instruction triggered by the target object, determining a second target doneness of the food; In response to the cooking parameter determination instruction triggered by the target object, determining a second initial cooking time and a second initial cooking temperature of the food; A second initial cooking parameter is determined according to the second target doneness, the second initial cooking time, and the second initial cooking temperature.

9. The method according to claim 8, characterized in that The method further comprises: When the cooking time reaches the second initial cooking time, obtaining the current real-time degree of doneness; If the current real-time doneness does not reach the second target doneness, calculating the additional cooking time required for the food to reach the target doneness; In response to the supplementary cooking instruction triggered by the target object, the cooking device is controlled to adjust the cooking time to the supplementary cooking time and continue cooking.

10. An intelligent cooking device, characterized in that: The device comprises: An initial cooking parameter acquisition module, used to acquire initial cooking parameters of food in response to a cooking instruction triggered by a target object; the cooking instruction includes a target degree of doneness of the food; A cooking module, used for controlling the cooking device to cook the food according to the initial cooking parameters; A real-time doneness acquisition module is used to collect the real-time state data of the food during the cooking process, perform real-time analysis on the cooking state of the food, and obtain the real-time doneness of the food; an updated real-time doneness acquisition module, used for adjusting the initial cooking parameters in real time when the real-time doneness does not reach the target doneness, and controlling the cooking device to continue cooking the food according to the adjusted cooking parameters to obtain an updated real-time doneness; The cooking stop module is used to stop cooking the food when the updated real-time doneness reaches the target doneness.

Images