Temperature control method and system for Chinese food cooking based on multi-modal characterization recognition

Abstract

The invention discloses a temperature control method and system for Chinese food cooking based on multi-modal representation recognition, and relates to the technical field of temperature control for Chinese food cooking, and the method comprises the steps: carrying out the data collection through a sensor, and carrying out the preprocessing; analyzing the food state change, monitoring the food state change in real time, and performing multi-dimensional feature fusion; capturing texture dynamic characteristics, monitoring a cooking image, introducing a feedback variable, and controlling and adjusting the temperature; environment variables are monitored, and preference setting is carried out; analyzing the big data and user historical data; according to the method, comprehensive monitoring of multi-dimensional data such as temperature, humidity and color is realized through fusion processing of a multi-modal sensor, and accuracy and real-time performance of cooking data are ensured; by combining multiple technologies such as multi-modal sensor data fusion, big data analysis, time and space attenuation modeling and user preference setting, the food state is dynamically analyzed, the cooking stage is accurately judged, the temperature control strategy is optimized, and the extensive control problem of a traditional method is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control of Chinese food cooking, and in particular to a temperature control method of Chinese food cooking based on multimodal characterization and recognition. Background Art

[0002] With the rapid development of artificial intelligence technology, sensor technology and big data analysis technology, intelligent household appliances have been widely used in modern kitchens. Among them, precise control of temperature during cooking has become a research hotspot; Temperature is a key parameter in Chinese cooking, which directly affects the physical and chemical changes of ingredients, such as protein denaturation, enzyme activation and inactivation, and the release of food flavors; At present, most of the smart cooking devices available on the market use a single sensor for temperature monitoring and temperature control through preset programs; Although these methods have improved the convenience of cooking to a certain extent, the adaptability and accuracy of existing technologies are still greatly limited when faced with the diverse cooking methods and complex types of ingredients of Chinese cuisine; During actual use, we found that most of the existing temperature control methods for Chinese cooking use data from a single sensor, and its model cannot fully capture the multimodal information in the cooking process, such as temperature, humidity, optical characteristics and other multi-dimensional parameters, resulting in insufficient scientificity in the temperature control strategy and prone to problems of over- or under-heating. Secondly, most smart cooking devices only perform temperature control based on simple threshold judgments, and are unable to perform phased regulation based on the dynamic changes in food status, making it difficult to adapt to the complex and nonlinear temperature requirements in the Chinese cooking process.

[0003] Therefore, the present invention proposes a temperature control method for Chinese food cooking based on multimodal representation and recognition. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a temperature control method for Chinese food cooking based on multimodal characterization and recognition to solve the problem that the existing methods cannot fully capture the multimodal information in the cooking process and cannot perform phased regulation in combination with the dynamic changes in the food state.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a method for controlling temperature of Chinese food cooking based on multimodal characterization and recognition, comprising: Use sensors to collect data and perform preprocessing; Analyze food status changes, monitor food status changes in real time, and perform multi-dimensional feature fusion; Capture texture dynamic features, monitor cooking images, introduce feedback variables, and adjust temperature control; Monitor environment variables and set preferences; Analyze big data and user historical data to generate temperature control suggestions for visual display.

[0007] As a preferred solution of the temperature control method for Chinese food cooking based on multimodal characterization and recognition described in the present invention, wherein: temperature data is collected, infrared temperature sensors are deployed to monitor and complete food surface temperature measurement, and invasive temperature sensors are deployed to monitor and complete food internal temperature measurement; Collect gas concentration data, deploy steam concentration sensors and oil fume sensors, and monitor water vapor evaporation and oil fume generation; Collect image data, deploy RGB cameras to capture changes in food ingredients, install infrared thermal imaging cameras to capture temperature distribution in different areas, and identify the uniform heating status; Collect environmental data, deploy air pressure sensors, air velocity sensors, and temperature and humidity sensors to monitor the temperature, humidity, and airflow in the kitchen, and provide a basis for dynamic temperature compensation; Sensor S i Provide a set of measurement data D i (t), time No. The temperature data collected at different times are matched with time, and the data points are matched with the collected timestamps.

[0008] As a preferred solution of the temperature control method for Chinese food cooking based on multimodal characterization and recognition according to the present invention, the analyzing of food state changes and real-time monitoring of food state changes specifically include: Clean the collected image data and normalize the image data; Based on the convolutional neural network structure, a convolution layer is set to perform convolution operation with the input image through a mean filter; The convolution operation is to perform convolution calculation on the input image to generate convolution features: ; in, Represents the feature map output after the convolution operation, is the pixel value of the offset position (m, n) of the input image pixel value (i, j), where (i+m, j+n) represent the row and column positions of the convolution kernel on the input image, respectively. is a fixed filter matrix; A nonlinear activation function is applied to the output pixel after convolution, nonlinear features are introduced, and the activation function output at each time step is integrated, which is expressed as: ; ; in, Represents the output value after applying the ReLU activation function, Represents the cumulative value of food status change from time 0 to time t.

[0009] As a preferred solution of the temperature control method for Chinese food cooking based on multimodal characterization and recognition according to the present invention, the multidimensional feature fusion comprises: Set up a pooling layer to perform pooling on the cumulative value of food state changes after integral calculation to reduce the amount of calculation and enhance the abstractness of the features. The output value range after pooling is [0, ∞); The range of the image is divided during the pooling operation by the sliding window division method, in which the gradient amplitude within the pooling window is calculated and the adjustment factor is set based on the gradient amplitude and , expressed as: ; ; in is a small constant, It is used to adjust the feedback strength of a local area according to the changes of the image in the local area. represents the gradient value of the local area, Used to adjust spatial feedback; Perform regional weighted processing on the feature map output after the convolution operation to form a regionalized feature map; Specifically, the formula Represents the pixel value of the local area in the input feature map. The feature map is a feature representation extracted from the input image and is expressed as: ; in, and Represents the relative coordinates within the window, and the pooling window size is , introducing an exponential decay factor , Represents the input feature map Each pixel value within the pooling window is and is the regulating factor, Output feature map Middle position The final value of the feature map is calculated by selecting a local area and calculating the pixel value of the area. Indicates that the input feature map is The local area centered on is the size of the local area; Perform multi-dimensional feature fusion on the image color channels, perform pooling on each channel separately, and fuse the results, expressed as: ; in, Represents the total number of channels of input data, Indicates the number of a specific channel, specifically an index from 1 to C. For multi-channel input data No. The pixel value of each channel is the number of channels of the input data. is the pixel value in the input feature map, , It is the fusion of multi-dimensional features after pooling.

[0010] As a preferred solution of the temperature control method for Chinese food cooking based on multimodal characterization and recognition of the present invention, wherein: the capturing of texture dynamic features and monitoring of cooking images: Fusion features based on extracted multi-dimensional features , the extracted features are classified and regressed through the fully connected layer; The extracted multi-dimensional features are fused into features The image data in the image is converted into a single-channel grayscale image, and a grayscale co-occurrence matrix is ​​constructed to describe the spatial relationship between pixels, and the multi-dimensional features are fused into features. , defined as A two-dimensional matrix, The number of rows in the image, is the number of columns in the image, where each pixel value Belongs to a grayscale extreme set, in is the number of gray levels of the input grayscale image, and the co-occurrence frequency of different gray levels in the input grayscale image at the specified direction and distance is calculated, which is expressed as: ; in, is the gray-level co-occurrence matrix, representing the gray level and Between in the direction and Co-occurrence frequency at distance, is the Kronecker delta function, The input grayscale image Middle position The pixel value of is the distance between pixels, To calculate the direction; The calculated gray level co-occurrence matrix After normalization, it is expressed as: ; in, is the normalized gray-level co-occurrence matrix, the sum of the matrix is ​​1; Capture the texture features of the image and introduce the local gradient information of the image. The gradient amplitude of the image is calculated by the following formula: ; in, is an image In Location The gradient of , which indicates the intensity of image change; The normalized gray-level co-occurrence matrix Perform time integration to accumulate the texture changes of the image at different time steps, expressed as: ; in, is the cumulative gray-level co-occurrence matrix, which represents the The accumulated gray level co-occurrence frequency within is the grayscale image at time The pixel value at the moment, is the time variable, representing different time steps in the cooking process; in, The value range of is [0, ∞), which indicates the co-occurrence frequency between gray level pairs. The range of is [0, 1], which means the normalized co-occurrence matrix. The value of each element reflects the relative frequency of the gray level pair. The range of is [0, ∞), which represents the cumulative co-occurrence matrix.

[0011] As a preferred solution of the temperature control method for Chinese food cooking based on multimodal characterization and recognition of the present invention, the introduction of feedback variables to adjust the temperature control specifically includes: Introduce the feedback function required for temperature control strategy adjustment and build the feedback function Indicates at time The cooking status feedback is expressed as: ; in, Representative Feedback dimension, Z ; Introducing the time decay factor , γ is the attenuation factor, assuming that the distance from the current time The farther the feedback is, the less impact it has on the current temperature control strategy. The impact at any time is expressed as: ; in, It is the feedback function adjusted by time decay, which indicates the influence of historical feedback after the time decay factor; Introduce the spatial feedback attenuation factor to control the feedback effect at different spatial positions, using the Gaussian attenuation function represents the spatial effect, where is the spatial attenuation factor, x and y represent the spatial coordinates; Considering the impact of feedback information in multiple time and space dimensions on the temperature control strategy, a high-order integral function is used to integrate the feedback information, integrate the feedback information of all historical time and space regions, and calculate the adjustment amount of the temperature control strategy: ; in, Indicates at time When, spatial position The local feedback strength is calculated as follows: Get in time and spatial location The actual temperature value at ; Get in time and spatial location The actual humidity value at ; Obtain color and texture feature data of food surface and calculate texture features using image analysis algorithm; Set cooking target temperature , set the target humidity , setting target state of cookedness and desired food doneness; Calculate the temperature feedback, expressed as: ; Calculate the humidity feedback, expressed as: ; Introducing the time decay factor , controls the degree of weakening of historical feedback over time, expressed as: ; in, is the attenuation factor, which determines the impact of historical feedback on the current moment; A Gaussian attenuation function is introduced to control the feedback effect at different spatial positions: ; in, is the sum of the squares of the distances from the center, used to calculate the distance of each pixel relative to the center. It is a factor used to control the decay speed of spatial feedback effect and adjust the value of α; Combining time attenuation and space attenuation, the final humidity feedback value is obtained, which is expressed as: ; in This feedback function is used to represent the error and deviation from the target value. Exponential decay factor, indicating that the impact of historical feedback on the current temperature control strategy gradually weakens, the integral interval , indicating the time from the start of cooking to the current moment All time feedback For the time The system status value at the moment is obtained by Historical feedback is accumulated; Adjust the impact of feedback on the temperature control strategy and increase its nonlinearity. Use the Sigmoid function to compress the feedback information into : ; Where x is the feedback value The Sigmoid function maps the input value to In the range of Input, It is an exponential function of the natural logarithm base, which represents the nonlinear characteristics of the Sigmoid function; Introduce Sigmoid function to feedback value Perform nonlinear scaling to control the effect of feedback on the temperature control strategy, and finally obtain the temperature control strategy adjustment model, which is calculated as follows: ; in For the current moment The target temperature you want to achieve; based on The temperature difference with the current time t is used to adjust the temperature control.

[0012] As a preferred solution of the temperature control method for Chinese food cooking based on multimodal characterization and recognition of the present invention, the monitoring of environmental variables and setting of preferences specifically include: Set the target temperature range through the UI, monitor data in real time, and continuously track the surface and internal temperature of food; Set the humidity range and target humidity, and automatically adjust the humidity according to the needs of food types; The user sets the heating power, which is adjusted according to different cooking stages. The heating power is determined by dynamically calculating the difference between the surface and internal temperature of the food, humidity, and cooking status; Dynamically adjust heating power based on the model and combined with user setting preferences; Calculate the rate of change of temperature and humidity and the color change signal to determine whether the food is nearly done and adjust the remaining cooking time and power output; Adjust food settings through the UI. The system adjusts temperature control parameters according to user requirements and monitors the kitchen environment to adjust temperature control parameters. Based on historical cooking feedback data and user-set preferences, the feedback data is stored and analyzed.

[0013] As a preferred solution of the temperature control method for Chinese food cooking based on multimodal characterization and recognition according to the present invention, the analysis of big data and user history data specifically includes: Preprocessing of real-time and historical data, including data cleaning, removal of outliers and noise, filling in missing data, and detection of outliers; Group users, record similar preferences of grouped users and build models; Compare user characteristics online, explore correlations, and optimize cooking strategies; Extract data features, including temperature change curve, food surface color change, and heating power, and use the above features as input parameters for predictive modeling; Use cooking data as training data for reinforcement learning, adjust the temperature control strategy, and keep it updated.

[0014] A temperature control system for Chinese food cooking based on multimodal representation and recognition, the system comprises: Temperature sensor module, used to monitor the temperature of food surface and inside in real time; Humidity sensor module, used to monitor humidity changes on the food surface; Gas concentration sensor module, used to monitor the concentration of steam, oil smoke and water vapor; In a second aspect, the present invention provides a temperature control system for Chinese food cooking based on multimodal characterization and recognition, including an image acquisition module, including an RGB camera and an infrared thermal imaging camera, to capture image changes on the surface and inside of food and identify the cooked state of food; Environmental monitoring sensor module, used to monitor the temperature, humidity and airflow environment data in the kitchen in real time; The data acquisition module is used to collect temperature, humidity, gas concentration, image data and other information from each sensor in real time, and to time-calibrate the data according to time steps; Data cleaning and preprocessing module, used to clean the collected data, including denoising, outlier detection, missing data filling, etc.; Data fusion and analysis module, used for fusion analysis of sensor data, including image feature extraction using image processing technology, convolutional neural network, multi-dimensional data fusion, gray-level co-occurrence matrix analysis and texture feature extraction; The dynamic temperature control adjustment is achieved through the following steps: The cooking state at each moment is calculated through the feedback function, and the influence of historical feedback is adjusted by using the time decay factor and the space decay factor; Adjust temperature control parameters according to real-time data and the target temperature and humidity set by the user.

[0015] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the temperature control method for Chinese food cooking based on multimodal representation recognition as described in the first aspect of the present invention is implemented.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the temperature control method for Chinese food cooking based on multimodal representation and recognition as described in the first aspect of the present invention.

[0017] The beneficial effects of the present invention are: Through the fusion processing of multi-modal sensors, comprehensive monitoring of multi-dimensional data such as temperature, humidity, and color is achieved to ensure the accuracy and real-time nature of cooking data; By combining multimodal sensor data fusion, big data analysis, time and space attenuation modeling, user preference settings and other technologies, the food state is dynamically analyzed, the cooking stage is accurately determined, the temperature control strategy is optimized, and the extensive control problems of traditional methods are avoided; Through user preference settings and real-time feedback adjustments, seamless matching of intelligent temperature control and user needs is achieved, which significantly improves cooking quality and user satisfaction, thereby increasing the demand for intelligent operation of this method. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use 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 ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0019] Figure 1 This is a flow chart of the temperature control method for Chinese food cooking based on multimodal characterization and recognition in Example 1.

[0020] Figure 2 This is a flowchart of the enhanced processing of the gray-level co-occurrence matrix in Example 1. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0023] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0024] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a temperature control method for Chinese food cooking based on multimodal characterization recognition, comprising the following steps: S1, uses sensors to collect data and perform fusion processing; Preferably, the sensor data is collected and preprocessed, including: The use of sensor data for collection and fusion processing includes:

[0025] To collect temperature data, infrared temperature sensors are deployed on the heating surface of the cooking equipment and the surface of the food. The temperature distribution on the surface of the food is monitored in real time in a non-contact manner to complete the surface temperature measurement. The invasive temperature sensor is inserted into the food to monitor the internal temperature of the food and complete the internal temperature measurement. By monitoring the surface and internal temperature of ingredients in real time, the system can adjust the heating power and change the heating method in time to ensure that the food is cooked at the optimal temperature. This is crucial for cooking methods that require precise temperature control. Real-time temperature data provides continuous feedback to the system, allowing it to dynamically adjust the firepower to avoid excessive or insufficient temperature fluctuations, ensure that the food is evenly heated, prevent overheating and undercooking, and thus achieve precise temperature control. In addition, by inserting invasive temperature sensors into the interior of the ingredients, the internal temperature of the food can also be effectively monitored. Especially for thicker ingredients, the system can ensure that the food is evenly heated by collecting the temperatures of different parts of the food, avoiding the situation where the outside is burnt and the inside is raw, thereby effectively improving the uniformity of food heating. Collect gas concentration data, set up steam concentration sensors and oil fume sensors above the cooking equipment to monitor water vapor evaporation and oil fume generation during cooking. Changes in steam concentration can reflect whether the food has reached the boiling point or whether the water evaporates too quickly, while an increase in oil fume concentration may mean that the oil temperature is too high and the food is burnt, so the fire needs to be adjusted in time. In the cooking process, especially in frying, cooking and other operations, the generation of oil smoke and steam is inevitable. By real-time monitoring of steam concentration and oil smoke concentration, the system can automatically adjust the cooking firepower and enable the exhaust system to avoid the accumulation of oil smoke that easily destroys the flavor of food and affects the normal use of the device. Not only that, in the actual use process, especially in low-temperature cooking processes such as steaming and stewing, the change in steam concentration affects the moisture content of food. By monitoring the steam concentration, the system can adjust the heating power and adjust the steam release method according to the steam concentration data to ensure the ideal moisture content of food and the use effect of the device. Image data is collected, and an RGB camera is installed above the cooking equipment to capture the surface color and shape changes of the ingredients to determine whether the ingredients are in the ideal cooking state; an infrared thermal imaging camera is also installed to capture the temperature distribution in different areas to help identify whether the food is heated evenly. It is suitable for frying, baking, and other occasions where the surface temperature changes of food need to be observed; The monitoring and transmission of image data can directly reflect the cooking status of food. By identifying the color change of the food surface, it can infer whether the food has reached the ideal degree of doneness. The system can intelligently analyze the image data, determine the cooking stage, and automatically adjust the temperature control strategy accordingly to avoid overcooking or undercooking. Collect environmental data, install air pressure sensors, air velocity sensors, and temperature and humidity sensors around cooking equipment to monitor the temperature, humidity, and airflow in the kitchen. These data have an important impact on the evaporation and heat conduction of food ingredients, especially in different seasons and indoor environmental conditions, and can provide a basis for dynamic temperature compensation for cooking equipment. When the weather changes and the ventilation conditions in the kitchen are unstable, the ambient temperature and humidity may cause unstable cooking temperature. Specifically, when the humidity is high, the moisture on the surface of the food is more likely to evaporate, affecting the heating effect. When the temperature is too high, the ingredients may burn too quickly and the outer layer may become too dry. By collecting environmental data such as the temperature and humidity in the kitchen in real time, the system can compensate for external factors in the cooking process and dynamically adjust the temperature control parameters to ensure that the food is cooked under optimal environmental conditions. In another extreme case, specifically in a more humid kitchen, the system can also adjust the firepower according to the ambient humidity to avoid excessive evaporation of moisture. Conversely, in a drier environment, the system may need to increase the heating power and extend the cooking time to keep the food moist, so as to ensure that the food is not too dry and affect its taste.

[0026] During the cooking process, users may have different preferences for temperature, humidity, heat, etc. By real-time collection of the multi-dimensional data mentioned above, the system can not only accurately adjust the temperature, but also customize it based on user preferences and types of ingredients. Through real-time monitoring and analysis of temperature, humidity, gas concentration, and images, the system can automatically make adjustments during the cooking process without the need for manual intervention by the user. The data collected in real time is not only used for current cooking control, but can also be stored and used for subsequent system learning and optimization. Through the analysis of multiple cooking data, the system can gradually learn the temperature control solutions that are most suitable for different ingredients, different environments, and different users, thereby improving cooking efficiency and accuracy.

[0027] S2, analyze food state changes, monitor food state changes in real time, and perform multi-dimensional feature fusion; Preferably, analyzing food state changes and real-time monitoring of food state changes specifically include: The analyzing of food state changes and real-time monitoring of food state changes specifically include: Clean the collected image data and normalize the image data; Based on the convolutional neural network structure, a convolution layer is set to perform convolution operation with the input image through a mean filter; The convolution operation is to perform convolution calculation on the input image to generate convolution features: ; in, Represents the feature map output after the convolution operation, is the pixel value of the offset position m, n of the input image pixel value i, j, where i+m, j+n represent the row and column positions of the convolution kernel on the input image, respectively. is a fixed filter matrix; A nonlinear activation function is applied to the output pixels after convolution, nonlinear features are introduced, and the activation function output of each time step is integrated. ReLU is used to truncate the negative value to zero to ensure that the model can learn more complex features. Since convolutional neural networks are usually used to process dynamic data, in order to comprehensively consider the changes in time, it is expressed as: ; ; in, Represents the output value after applying the ReLU activation function, The positive value will be retained and the negative value will be converted to zero. Indicates the cumulative value of the food state change from time 0 to time t, which is used to determine the cooking stage of the food and adjust the temperature control strategy. It is used to dynamically adjust the temperature control strategy and is the pixel value of the input image or multi-dimensional data; By introducing time and space attenuation factors, the model can effectively control the feedback influence of different time points and spatial regions. The time attenuation factor gradually reduces the influence of historical feedback and only focuses on the feedback in the current time period, thereby improving the model's response speed to real-time changes; the space attenuation factor makes the area farther away from the central area in the image contribute less to the final decision, ensuring that the model focuses more on the key areas of food cooking. By using high-order integrals to integrate the feedback information of multi-dimensional time and space dimensions, the model can consider the changes at each time point in the cooking process from multiple dimensions and provide a more accurate temperature control strategy. The nonlinear activation function further enhances the complexity of the model, enabling the model to handle the complex relationship between temperature, humidity and food state, ensuring that the feedback value is suitable for subsequent temperature control adjustments. The model dynamically adjusts the feedback of various sensor data collected in real time, such as temperature, humidity, color changes, etc., thereby achieving precise control of parameters such as heating power, cooking temperature, and time. This dynamic feedback mechanism can optimize the temperature control strategy in real time, improve the cooking effect of food, and avoid food charring or undercooking due to overheating or temperature fluctuations.

[0028] Furthermore, the multi-dimensional feature fusion includes: Set up a pooling layer to perform pooling on the cumulative value of food state changes after integral calculation to reduce the amount of calculation and enhance the abstractness of the features. The output value range after pooling is [0, ∞), where Indicates that the features in this area are not effectively extracted and ignored, and the pooling operation does not find effective features in this area. It means that the pooling operation extracts the significant features of the area. Generally, the larger the output value, the more prominent the features of the area. The range of the image is divided during the pooling operation by the sliding window division method, in which the gradient amplitude within the pooling window is calculated and the adjustment factor is set based on the gradient amplitude and , expressed as: ; ; in is a small constant, and α is used to adjust the feedback strength of the area according to the changes of the image in the local area. represents the gradient value of the local area, Used to adjust spatial feedback; Perform regional weighted processing on the feature map output after the convolution operation to form a regionalized feature map; Specifically, the formula Represents the pixel value of the local area in the input feature map. The feature map is a feature representation extracted from the input image and is expressed as: ; in, and Represents the relative coordinates within the window, and the pooling window size is , introducing an exponential decay factor , Represents the input feature map Each pixel value within the pooling window is and is the regulating factor, Output feature map Middle position The final value of the feature map is calculated by selecting a local area in the feature map and calculating the pixel value of the area. Indicates that the input feature map is The local area centered on is the size of the local area; Perform multi-dimensional feature fusion on the image color channels, perform pooling on each channel separately, and fuse the results, expressed as: ; in, Represents the total number of channels of input data, Indicates the number of a specific channel, specifically an index from 1 to C. The above summation operation is performed on the index from 1 to This is done on all channels. Represents the current processing channel. The specific calculation is performed separately for each channel. For multi-channel input data No. The pixel value of each channel is the number of channels of the input data, indicating the color channel and other multidimensional data. is the pixel value in the input feature map, , It is the multi-dimensional feature fusion after pooling. Specifically, after the input data of different channels are processed specifically, the data features of multiple channels are integrated into an output with higher expressive ability. The specific processing includes weighted summation, activation function, and exponential scaling. It retains the important features of the input data while reducing the dimension of the data, thereby improving computational efficiency and reducing noise, so as to represent the features extracted from each local area. It is the fusion of multi-dimensional features after pooling; In image processing and convolutional neural networks, a local region refers to a small area in an image that is used to extract local features. This area can be obtained by sliding a window. For example, in a convolution operation, the image is divided into small matrix blocks, each of which is processed separately, and image features are extracted through the convolution kernel. Local region processing can effectively reduce the amount of computation and improve the efficiency of feature extraction. By performing local region processing on the image and combining it with the spatial attenuation factor, the model can effectively focus on the local details of the image while reducing the interference of irrelevant information far from the center. This step effectively improves the computational efficiency and accuracy of the system, especially when processing large-scale data, which can significantly reduce the amount of computation. During the cooking process, the state changes of food are usually multidimensional and nonlinear. The introduction of a feedback function can be based on real-time collected sensor data, such as temperature error, Humidity changes, etc., dynamically adjust the temperature control strategy. This feedback mechanism ensures that each cooking can adjust the heating power and cooking time in time according to the current food status to optimize the final result. By introducing nonlinear mapping functions such as Sigmoid function, the influence range of feedback data can be effectively compressed or expanded, avoiding the overfitting problem in simple linear models. This not only increases the flexibility of the model, but also improves the performance of the temperature control system in complex cooking tasks and ensures the rational application of feedback signals. In traditional cooking feedback adjustment models, only a single sensor data is usually considered, while multi-dimensional feature fusion can simultaneously consider information in multiple dimensions such as temperature, humidity, and color changes, so that the temperature control system can make decisions based on comprehensive data. This fusion method enables the system to efficiently and accurately adjust cooking parameters in complex environments.

[0029] S3, captures texture dynamic features, monitors cooking images, introduces feedback variables, and adjusts temperature control; Preferably, the capturing of texture dynamic features and monitoring of cooking images: Fusion features based on extracted multi-dimensional features , the extracted features are classified and regressed through the fully connected layer; The extracted multi-dimensional features are fused into features The image data in is converted into a single-channel grayscale image. According to the spatial distribution characteristics of pixel gray levels, a grayscale co-occurrence matrix is ​​constructed to describe the spatial relationship between pixels. Represents the gray value in the image and In a given direction and The co-occurrence frequency under distance combines multi-dimensional features , defined as A two-dimensional matrix, The number of rows in the image, is the number of columns in the image, where each pixel value Belongs to a grayscale extreme set, in is the number of gray levels of the input grayscale image, and the co-occurrence frequency of different gray levels in the input grayscale image at the specified direction and distance is calculated, which is expressed as: ; in, is the gray-level co-occurrence matrix, representing the gray level and Between in the direction and Co-occurrence frequency at distance, is the Kronecker delta function, used to determine and Are they equal? ​​If they are equal, then it is 1, otherwise it is 0. The input grayscale image Middle position The pixel value of is the distance between pixels, usually set to 1, To calculate the directions, including 0°, 45°, 90°, and 135°, the spatial relationship of pixels is calculated by high-order integrals, which enhances the ability to capture spatial structures. The calculated gray level co-occurrence matrix Normalization is performed to ensure that the sum of the matrix is ​​1 and meets the requirements of probability distribution, expressed as: ; in, is the normalized gray-level co-occurrence matrix, the sum of the matrix is ​​1, and the normalization process replaces the simple summation with integration, ensuring the correct measurement of gray-level pairs; Capture the texture features of the image and introduce the local gradient information of the image. The gradient amplitude of the image is calculated by the following formula: ; in, is an image In Location The gradient of , which indicates the intensity of image change; The image changes during the cooking process,introduced the time dimension to capture the dynamic characteristics of texture changes,and introduced the calculation of gray-level co-occurrence matrix into the time series to capture the texture characteristics of the image changing over time,due to the temporal evolution of the image during the cooking process; Gray Level Co-occurrence Matrix Perform time integration to accumulate the texture changes of the image at different time steps, expressed as: ; in, is the cumulative gray-level co-occurrence matrix, which represents the The accumulated gray level co-occurrence frequency within is the grayscale image at time The pixel value at the moment, is the time variable, representing different time steps in the cooking process; In the above, The value range of is [0, ∞, which indicates the co-occurrence frequency between grayscale pairs. A larger value indicates that the grayscale pair appears more frequently in the image. The range of is [0, 1], which means the normalized co-occurrence matrix. The value of each element reflects the relative frequency of the gray level pair. The range of is [0, ∞), which represents the cumulative co-occurrence matrix, which changes over time and captures the changes in image texture; Based on the accumulated co-occurrence matrix, the dynamic characteristics of texture changes are captured to monitor cooking images in real time.

[0030] By adopting the integral feedback mechanism and nonlinear adjustment, the temperature control strategy can not only rely on the feedback at the current moment, but also consider the feedback information at the past moment. This consideration of historical data greatly improves the dynamic adjustment ability of the model, especially in complex cooking tasks. It can maintain the balance of temperature and humidity to ensure the best effect every time cooking. The temperature control strategy adjustment model based on image processing and multi-dimensional feature fusion can achieve precise temperature and humidity control during the cooking process through precise feedback mechanism, spatial attenuation and nonlinear mapping.

[0031] Preferably, the introducing of feedback variables to adjust the temperature control specifically includes: Introduce the feedback function required for adjusting the temperature control strategy. Depends on the current time In the cooking process, the adjustment of the temperature control strategy is not only affected by the feedback at the current moment, but also by the feedback at the past moment. Therefore, the adjustment of the temperature control strategy needs to introduce the time accumulation effect, so that the feedback at the past moment has a certain influence on the current temperature control strategy. By historical moment Strategy And the feedback information at each moment in the cooking process is weighted to obtain: ; Indicates that the temperature control strategy is at time The adjustment amount is further derived expression; Introduce the feedback function required for adjusting the temperature control strategy, including temperature, humidity, and food ripening status, and use the feedback function To indicate at the time The cooking status feedback of Including the error between the temperature and the target temperature, humidity changes, and the degree of food maturity, it is expressed by the following formula: ; in, represents the zth feedback dimension, Z , introducing the time decay factor , because the influence of past feedback on the current temperature control strategy gradually decreases, the time decay factor is introduced to reflect the gradual weakening effect of historical feedback on the current decision. γ is the decay factor, which controls the speed of the influence of past feedback. , assuming that the time from the current time The farther the feedback is, the less impact it has on the current temperature control strategy. The impact at a certain moment is expressed as: ; in, It is the feedback function adjusted by time decay, which represents the influence of historical feedback after time decay factor, and is used to adjust the current temperature control strategy; Considering spatial changes in modeling, during the cooking process, food at different locations, such as the surface and the interior, has different effects on the temperature control strategy. The spatial feedback attenuation factor is introduced to control the feedback effect at different spatial locations, using a Gaussian attenuation function. To represent the spatial effect, where α is the spatial attenuation factor, x and represents the spatial coordinates, is the square of the distance relative to the center position. After introducing spatial attenuation, local feedback It will be adjusted according to the distance of the spatial location; Considering the impact of feedback information in multiple time and space dimensions on the temperature control strategy, a high-order integral function is used to integrate the feedback information, integrate the feedback information of all historical time and space regions, and calculate the adjustment amount of the temperature control strategy: ; in, Indicates at time When, spatial position The local feedback strength is calculated as follows: Get in time and spatial location The actual temperature value at ; Get in time and spatial location The actual humidity value at ; Obtaining characteristic data such as color and texture of food surface, usually using image analysis algorithms to calculate color changes or texture features; Set cooking target temperature , set the target humidity , setting a target state of doneness or desired degree of food doneness; Combine the collected data with the target state to calculate the feedback function , calculate the temperature feedback: ; Calculate the current time of food The difference between the temperature and the target temperature; Calculate humidity feedback: ; Calculate food maturity feedback based on image processing algorithms, extract food surface color changes or texture features, and generate maturity scores; Introducing the time decay factor , controls the degree of attenuation of historical feedback over time, ; in, is the attenuation factor, which determines the impact of historical feedback on the current moment; A Gaussian attenuation function is introduced to control the feedback effect at different spatial positions: ; in, It is the spatial location where feedback information is collected, specifically the horizontal and vertical coordinates, which are collected by sensors at different locations on the surface and inside of the food. is the sum of the squares of the distances from the center, used to calculate the distance of each pixel relative to the center. It is a factor used to control the attenuation rate of the spatial feedback effect. It is estimated through experiments. Specifically, by collecting feedback data at different spatial locations, observing the influence of different regions on the temperature control strategy, and adjusting the value of α; Combining time attenuation and space attenuation, the final humidity feedback value is obtained, which is expressed as: ; The local feedback strength does not affect the entire system. This feedback function is used to represent the error and deviation from the target value, indicating the spatial position In time Feedback information at all times, including temperature error and temperature deviation, Exponential decay factor, indicating that the impact of historical feedback on the current temperature control strategy gradually weakens, the integral interval , indicating the time from the start of cooking to the current moment All time feedback, The exponential decay coefficient describes the decay degree of feedback information over time. It is the time variable in the integral and represents the historical time point when the feedback effect occurs. Together, they are used to describe the cumulative impact of historical feedback on the current state. For time The initial state value at , represents the initial condition or initial output value of the system, For time The system status value at the moment is obtained by Historical feedback is accumulated to describe the dynamic changes of the system; Adjust the impact of feedback on the temperature control strategy so that it is not too large or too small, and increase its nonlinearity. Use the Sigmoid function to compress the feedback information into : ; in, is the feedback value The Sigmoid function maps the input value to In the range of Input, It is an exponential function of the natural logarithm base, which represents the nonlinear characteristics of the Sigmoid function; Introduce Sigmoid function to feedback value Nonlinear scaling is performed to control the effect of feedback on the temperature control strategy, and finally the temperature control strategy adjustment model is obtained. The calculation is expressed as: ; From the initial setting At the beginning, it gradually adjusts according to the feedback, and adjusts the temperature control strategy with multiple feedback dimensions, including temperature, humidity, and food status. It uses exponential decay function modeling to solve the problem that the impact of historical feedback will gradually decay over time and become difficult to balance. Through Gaussian decay function modeling, it actively absorbs feedback from spatial positions, and takes into account the different impacts of different positions on the temperature control strategy. Then, through the integral function, the information of historical feedback and spatial feedback is integrated to form an adjustment to the current temperature control strategy. Finally, the feedback is nonlinearly compressed through the Sigmoid function to ensure that the impact of feedback on the temperature control strategy is within a reasonable range. In this way, the model can effectively perform dynamic temperature control adjustments on each feedback in the cooking process, ensuring that the temperature, time and other parameters can be accurately controlled each time cooking to ensure the best cooking effect of food. For the current moment The target temperature that the system is expected to reach, combined with the initial temperature and historical feedback information The model describes the dynamic process of the temperature control strategy adjustment system, dynamically adjusts the temperature control strategy based on the feedback signals at each moment in the cooking process to optimize the cooking effect. The temperature difference with the current time t is used to adjust the temperature control.

[0032] S4, monitors environment variables and sets preferences; Preferably, the monitoring of environmental variables and setting of preferences specifically includes: Set the target temperature range through the UI, monitor data in real time, and continuously track the surface and internal temperature of food; Set the humidity range and target humidity, and automatically adjust the humidity according to the needs of food types; The user sets the heating power, which is adjusted according to different cooking stages. The heating power is determined by dynamically calculating the difference between the surface and internal temperature of the food, humidity, and cooking status; The system dynamically adjusts the heating power based on the model and in combination with user setting preferences; Calculate the rate of change of temperature and humidity and the color change signal to determine whether the food is nearly done and adjust the remaining cooking time and power output; Feedback is provided during the cooking process, and the system optimizes the temperature control strategy based on the feedback, including automatic adjustment of temperature, humidity, pressure, and time; In different cooking stages, the system dynamically adjusts various parameters based on current environmental conditions and sensor data to ensure that the temperature control strategy matches user preferences and real-time environmental needs; Adjust food settings through the UI. The system adjusts temperature control parameters according to user requirements and monitors the kitchen environment to adjust temperature control parameters. Based on historical cooking feedback data and user-set preferences, the feedback data is stored and analyzed.

[0033] S5, analyzes big data and user historical data, generates temperature control suggestions for visual display; Preferably, the analysis of big data and user historical data specifically includes: Preprocessing of real-time and historical data, including data cleaning, removal of outliers and noise, filling in missing data, and detection of outliers; Group users, record similar preferences of grouped users and build models; Compare user characteristics online, explore correlations, and optimize cooking strategies; Extract data features, including temperature change curve, food surface color change, and heating power, and use the above features as input parameters for predictive modeling; Use cooking data as training data for reinforcement learning, adjust the temperature control strategy, and keep it updated.

[0034] This embodiment also provides a temperature control system for Chinese food cooking based on multimodal characterization recognition, the system comprising: Temperature sensor module, used to monitor the temperature of food surface and inside in real time; Humidity sensor module, used to monitor humidity changes on the food surface; Gas concentration sensor module, used to monitor the concentration of steam, oil smoke and water vapor; Image acquisition module, including RGB camera and infrared thermal imaging camera, to capture image changes on the surface and inside of food and identify the cooked state of food; Environmental monitoring sensor module, used to monitor the temperature, humidity and airflow environment data in the kitchen in real time; The data acquisition module is used to collect temperature, humidity, gas concentration, image data and other information from each sensor in real time, and to time-calibrate the data according to time steps; Data cleaning and preprocessing module, used to clean the collected data, including denoising, outlier detection, missing data filling, etc.; Data fusion and analysis module, used for fusion analysis of sensor data, including image feature extraction using image processing technology, convolutional neural network, multi-dimensional data fusion, gray-level co-occurrence matrix analysis and texture feature extraction; The dynamic temperature control adjustment is achieved through the following steps: The cooking state at each moment is calculated through the feedback function, and the influence of historical feedback is adjusted by using the time decay factor and the space decay factor; Adjust temperature control parameters according to real-time data and the target temperature and humidity set by the user.

[0035] This embodiment also provides a computer device, which is suitable for the temperature control method of Chinese food cooking based on multimodal representation recognition, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the temperature control method of Chinese food cooking based on multimodal representation recognition as proposed in the above embodiment. The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0036] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the temperature control method for Chinese food cooking based on multimodal representation recognition as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, EPROM), programmable read-only memory (Programmable Red-Only Memory, PROM), read-only memory (Read-Only Memory, ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0037] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A temperature control method for Chinese food cooking based on multimodal characterization and recognition, characterized in that: include: Use sensors to collect data and perform preprocessing; Analyze food status changes, monitor food status changes in real time, and perform multi-dimensional feature fusion; Capture texture dynamic features, monitor cooking images, introduce feedback variables, and adjust temperature control; Monitor environment variables and set preferences; Analyze big data and user historical data to generate temperature control suggestions for visual display.

2. The temperature control method for Chinese food cooking based on multimodal characterization recognition according to claim 1, characterized in that: The method of collecting and preprocessing sensor data includes: Collect temperature data, deploy infrared temperature sensors, monitor and complete food surface temperature measurement, deploy invasive temperature sensors, monitor and complete food internal temperature measurement; Collect gas concentration data, deploy steam concentration sensors and oil fume sensors, and monitor water vapor evaporation and oil fume generation; Collect image data, deploy RGB cameras to capture changes in food ingredients, install infrared thermal imaging cameras to capture temperature distribution in different areas, and identify the uniform heating status; Collect environmental data, deploy air pressure sensors, air velocity sensors, and temperature and humidity sensors to monitor the temperature, humidity, and airflow in the kitchen, and provide a basis for dynamic temperature compensation; sensor Provide a set of measurement data ,time No. The temperature data collected at different times are matched with time, and the data points are matched with the collected timestamps.

3. The temperature control method for Chinese food cooking based on multimodal characterization recognition according to claim 2, characterized in that: The analyzing of food state changes and real-time monitoring of food state changes specifically include: Clean the collected image data and normalize the image data; Based on the convolutional neural network structure, a convolution layer is set to perform convolution operation with the input image through a mean filter; The convolution operation is to perform convolution calculation on the input image to generate convolution features: ； in, Represents the feature map output after the convolution operation, is the pixel value of the offset position (m, n) of the input image pixel (i, j), where (i+m, j+n) represent the row and column positions of the convolution kernel on the input image, respectively. is a fixed filter matrix; A nonlinear activation function is applied to the output pixel after convolution, nonlinear features are introduced, and the activation function output at each time step is integrated, which is expressed as: ； ； in, Represents the output value after applying the ReLU activation function, Represents the cumulative value of food status change from time 0 to time t.

4. The temperature control method for Chinese food cooking based on multimodal characterization recognition according to claim 3 is characterized in that: The multi-dimensional feature fusion comprises: Set up a pooling layer to perform pooling on the cumulative value of food state changes after integral calculation to reduce the amount of calculation and enhance the abstractness of the features. The output value range after pooling is [0, ∞); The image is divided into ranges during the pooling operation by the sliding window division method, the gradient amplitude within the pooling window is calculated, and the adjustment factor is set based on the gradient amplitude and , expressed as: ； ； in is a small constant, Represents the gradient value of the local area; Perform regional weighted processing on the feature map output after the convolution operation to form a regionalized feature map; Specifically, the formula Represents the pixel value of the local area in the input feature map. The feature map is a feature representation extracted from the input image and is expressed as: ； in, and Represents the relative coordinates within the window, and the pooling window size is , introducing an exponential decay factor , Represents the input feature map Each pixel value within the pooling window is and is the regulating factor, Represents the output feature map Middle position The final value of the feature map is calculated by selecting an area in the feature map and calculating the pixel value of the area. Indicates that the input feature map is The central area, is the size of the region; Perform multi-dimensional feature fusion on the image color channels, perform pooling on each channel separately, and fuse the results, expressed as: ； in, Represents the total number of channels of input data, Indicates the number of a specific channel, specifically an index from 1 to C. For multi-channel input data No. The pixel value of each channel, is the pixel value in the input feature map, Control the pixel value within the pooling window, It is the fusion of multi-dimensional features after pooling.

5. The temperature control method for Chinese food cooking based on multimodal characterization recognition according to claim 4, characterized in that: The method captures the dynamic characteristics of texture and monitors the cooking image: Fusion features based on extracted multi-dimensional features , the extracted features are classified and regressed through the fully connected layer; The extracted multi-dimensional features are fused into features The image data in the image is converted into a single-channel grayscale image, and a grayscale co-occurrence matrix is ​​constructed to describe the spatial relationship between pixels, and the multi-dimensional features are fused into features. , defined as A two-dimensional matrix, the number of rows in the image matrix, is the number of columns in the image matrix, where each pixel value belongs to a grayscale set, ,in is the number of gray levels of the input grayscale image, and the co-occurrence frequency of different gray levels in the input grayscale image at the specified direction and distance is calculated, which is expressed as: ； in, is the gray-level co-occurrence matrix, representing the gray level and Between in the direction and Co-occurrence frequency at distance, is the Kronecker delta function, The input grayscale image Middle position The pixel value of is the distance between pixels, To calculate the direction; The calculated gray level co-occurrence matrix After normalization, it is expressed as: ； in, is the normalized gray-level co-occurrence matrix, the sum of the matrix is ​​1; Capture the texture features of the image and introduce the local gradient information of the image. The gradient amplitude of the image is calculated by the following formula: ； in, is an image In Location The gradient of , which indicates the intensity of image change; The normalized gray-level co-occurrence matrix Perform time integration to accumulate the texture changes of the image at different time steps, expressed as: ； in, is the cumulative gray-level co-occurrence matrix, which represents the The accumulated gray level co-occurrence frequency within is the grayscale image at time The pixel value at the moment, is the time variable, representing different time steps in the cooking process; in, The value range of is [0, ∞), which indicates the co-occurrence frequency between gray level pairs. The range of is [0, 1], which means the normalized co-occurrence matrix. The value of each element reflects the relative frequency of the gray level pair. The range of is [0, ∞), which represents the cumulative co-occurrence matrix; Based on the accumulated co-occurrence matrix, the dynamic characteristics of texture changes are captured to form a comprehensive description of the evolution of image content. The cooking images are monitored in real time, and the texture changes are integrated over time to obtain feedback signals and provide a basis for the calculation of feedback functions.

6. The temperature control method for Chinese food cooking based on multimodal characterization recognition according to claim 5, characterized in that: The introduction of feedback variables to adjust the temperature control specifically includes: Introduce the feedback function required for temperature control strategy adjustment and build the feedback function Indicates at time The cooking status feedback is expressed as: ； in, Representative feedback variable, Z ; Introducing the time decay factor , γ is the attenuation factor, assuming that the distance from the current time The farther the feedback is, the less impact it has on the current temperature control strategy. The impact at any time is expressed as: ； in, It is the feedback function adjusted by time decay, which indicates the influence of historical feedback after the time decay factor; Introduce the spatial feedback attenuation factor to control the feedback effect at different spatial positions, using the Gaussian attenuation function represents the spatial effect, where is the spatial attenuation factor, and Represents spatial coordinates; Use a high-order integral function to synthesize the feedback information, integrate the feedback information of all historical time and space regions, and calculate the adjustment amount of the temperature control strategy: ； in, Indicates at time When, spatial position The local feedback strength, Adjust the impact of feedback on the temperature control strategy and increase its nonlinearity. Use the Sigmoid function to compress the feedback information into : ； in, is the feedback value The Sigmoid function maps the input value to the range of [0, 1] and represents the input of the feedback value F(t), e -x It is an exponential function of the natural logarithm base, which represents the nonlinear characteristics of the Sigmoid function; Introduce Sigmoid function to feedback value Perform nonlinear scaling to control the effect of feedback on the temperature control strategy, and finally obtain the temperature control strategy adjustment model, which is calculated as follows: ； The specific calculation process is: Get in time and spatial location The actual temperature value at ; Get in time and spatial location The actual humidity value at ; Obtain color and texture feature data of food surface and calculate texture features using image analysis algorithm; Set cooking target temperature , set the target humidity , setting target state of cookedness and desired food doneness; Calculate the temperature feedback, expressed as: ； Calculate the humidity feedback, expressed as: ； Introducing the time decay factor , controls the degree of weakening of historical feedback over time, expressed as: ； in, is the attenuation factor, which determines the impact of historical feedback on the current moment; A Gaussian attenuation function is introduced to control the feedback effect at different spatial positions: ； in, is the sum of the squares of the distances from the center, used to calculate the distance of each pixel relative to the center. It is a factor used to control the decay speed of spatial feedback effect and adjust the value of α; Combining time attenuation and space attenuation, the final humidity feedback value is obtained, which is expressed as: ； is the feedback function, which is used to represent the error and deviation from the target value Exponential decay factor, indicating that the impact of historical feedback on the current temperature control strategy gradually weakens, the integral interval , indicating the time from the start of cooking to the current moment All time feedback For the time The system state value at time t is obtained by accumulating historical feedback with T0; in For the current moment The target temperature you want to achieve; based on The temperature difference with the current time t is used to adjust the temperature control.

7. The temperature control method for Chinese food cooking based on multimodal characterization recognition according to claim 6, characterized in that: The monitoring of environment variables and setting of preferences specifically include: Set the target temperature range through the UI, monitor data in real time, and continuously track the surface and internal temperature of food; Set the humidity range and target humidity, and automatically adjust the humidity according to the needs of food types; The user sets the heating power, which is adjusted according to different cooking stages. The heating power is determined by dynamically calculating the difference between the surface and internal temperature of the food, humidity, and cooking status; Dynamically adjust heating power based on the model and combined with user setting preferences; Calculate the rate of change of temperature and humidity and the color change signal to determine whether the food is nearly done and adjust the remaining cooking time and power output; Adjust food settings through the UI. The system adjusts temperature control parameters according to user requirements and monitors the kitchen environment to adjust temperature control parameters. Based on the historical data of cooking feedback and the preferences set by the user, the feedback data is stored and analyzed; The analysis big data and user historical data specifically include: Preprocessing of real-time and historical data, including data cleaning, removal of outliers and noise, filling in missing data, and detection of outliers; Group users, record similar preferences of grouped users and build models; Compare user characteristics online, explore correlations, and optimize cooking strategies; Extract data features, including temperature change curve, food surface color change, and heating power, and use the above features as input parameters for predictive modeling; Use cooking data as training data for reinforcement learning, adjust the temperature control strategy, and keep it updated.

8. The temperature control system for Chinese food cooking based on multimodal characterization and recognition as described in any one of claims 1 to 7, characterized in that: The system includes: Temperature sensor module, used to monitor the temperature of food surface and inside in real time; Humidity sensor module, used to monitor humidity changes on the food surface; Gas concentration sensor module, used to monitor the concentration of steam, oil smoke and water vapor; Image acquisition module, including RGB camera and infrared thermal imaging camera, to capture image changes on the surface and inside of food and identify the cooked state of food; Environmental monitoring sensor module, used to monitor the temperature, humidity and airflow environment data in the kitchen in real time; The data acquisition module is used to collect temperature, humidity, gas concentration, image data and other information from each sensor in real time, and to time-calibrate the data according to time steps; Data cleaning and preprocessing module, used to clean the collected data, including denoising, outlier detection, missing data filling, etc.; Data fusion and analysis module, used for fusion analysis of sensor data, including image feature extraction using image processing technology, convolutional neural network, multi-dimensional data fusion, gray-level co-occurrence matrix analysis and texture feature extraction; The dynamic temperature control adjustment is achieved through the following steps: The cooking state at each moment is calculated through the feedback function, and the influence of historical feedback is adjusted by using the time decay factor and the space decay factor; Adjust temperature control parameters according to real-time data and the target temperature and humidity set by the user.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the temperature control method for Chinese food cooking based on multimodal representation and recognition as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the temperature control method for Chinese food cooking based on multimodal representation and recognition as described in any one of claims 1 to 7 are implemented.

Images