Chef machine intelligent remote control method and system based on artificial intelligence analysis

Abstract

The invention discloses a cook machine intelligent remote control method and system based on artificial intelligence analysis. The method comprises the following steps: receiving an operation instruction input by a user through remote terminal equipment; acquiring image and weight information of food materials in the chef machine by using a built-in camera and a sensor, and generating food material processing parameters based on a pre-trained neural network model; in combination with an operation instruction input by a user, the food material processing parameters and a preset recipe database, determining an adaptive stirring mode, a rotating speed and running time, and generating a control instruction; the control instruction is sent to the chef machine to be executed, the running state is monitored through a sensor, and the operation process and abnormal information are fed back in real time; and when overload, food material mixing abnormity or operation abnormity is detected, analyzing an abnormity reason and executing a corresponding adjustment strategy. According to the invention, the precision and intelligent level of food material processing can be improved, intelligent remote control and automatic optimization of the chef machine are realized, and the user experience and the stability of food material stirring are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cooking machines, and particularly to an intelligent remote control method and system for a cooking machine based on artificial intelligence analysis. Background Art

[0002] With the development of smart home technology, cooking machines, as a common kitchen appliance, are gradually evolving towards automation and intelligence. Existing cooking machines usually support multiple stirring modes and speed adjustments, capable of meeting the mixing requirements of different ingredients. At the same time, some high-end cooking machines have introduced electronic control systems, enabling users to adjust operating parameters through physical buttons or touch panels to enhance the convenience of cooking. In addition, some intelligent cooking machines already have remote control functions, allowing users to send basic instructions through mobile terminals to achieve a certain degree of automated operation.

[0003] However, existing intelligent cooking machines still have many problems in practical applications. For example, most devices rely on manual settings by users and lack the ability to automatically identify and adjust the state of ingredients, resulting in inaccurate stirring parameter settings and affecting the final mixing effect. In addition, the remote control function of existing devices is usually limited to basic operation instructions, unable to optimize operating parameters according to the real-time state of ingredients, and it is also difficult to timely feedback abnormal situations during the stirring process, restricting the level of intelligence and user experience.

[0004] Therefore, it is necessary to develop a cooking machine that can analyze the state of ingredients based on artificial intelligence and achieve intelligent remote control. Summary of the Invention

[0005] The present application provides an intelligent remote control method and system for a cooking machine based on artificial intelligence analysis to improve the accuracy and intelligence level of ingredient processing.

[0006] The present application provides an intelligent remote control method for a cooking machine based on artificial intelligence analysis, including:

[0007] Receiving an operation instruction input by a user through a remote terminal device, where the operation instruction includes start, stop, speed adjustment, stirring time, and mode selection;

[0008] Utilizing a built-in camera and sensors to obtain the image and weight information of the ingredients in the cooking machine, and analyzing the type, quantity, and mixing state of the ingredients based on a pre-trained neural network model to generate ingredient processing parameters;

[0009] Combining the operation instruction input by the user, the ingredient processing parameters, and a preset recipe database to determine the stirring mode, speed, and running time of the cooking machine, and generating a control instruction;

[0010] Send the generated control instructions to the cooking machine for execution, and monitor the operating status through sensors, and feedback the operation process and abnormal information to the remote terminal device in real time;

[0011] When overload, abnormal ingredient mixing or abnormal operation is detected, analyze the cause of the abnormality and execute corresponding adjustment strategies, including adjusting the rotation speed, modifying the operation mode or prompting the user to intervene. At the same time, push the operating status of the cooking machine, the progress of ingredient mixing and the recommended adjustment plan to the remote terminal device.

[0012] The beneficial effects of this application mainly include: (1) Collect ingredient information through built-in cameras and sensors, and analyze it based on a pre-trained neural network model to achieve accurate identification of ingredient types, quantities and mixing states. Combine the recipe database to dynamically adjust the mixing mode, rotation speed and running time, improve the accuracy of ingredient processing, and avoid problems such as overmixing or undermixing. (2) Receive user instructions through the remote terminal device, and generate control instructions in combination with the ingredient status to achieve remote control of the intelligent cooking machine. At the same time, the device operating status, ingredient mixing progress and abnormal information can be fed back to the remote terminal in real time, enabling users to accurately control the operation of the cooking machine even when not on-site, improving the convenience and intelligence level of use. (3) Monitor the operating status of the cooking machine through sensors. When overload, abnormal ingredient mixing or other abnormal operations are detected, automatically analyze the cause of the abnormality and execute corresponding adjustment strategies, such as adjusting the rotation speed, modifying the operation mode or reminding the user to intervene, improve the operating stability of the device, and reduce operation failures caused by improper parameter settings. (4) Combining user instructions, ingredient processing parameters and the recipe database, the system can automatically match a suitable mixing mode and recommend an optimized adjustment plan when necessary. Compared with traditional cooking machines that rely on users to manually set parameters, this method effectively reduces the user's operation burden, ensures the consistency of the mixing effect, and improves the automation level and cooking quality of the intelligent cooking machine. Description of the Drawings

[0013] Figure 1 It is a flowchart of a method for intelligent remote control of a cooking machine based on artificial intelligence analysis provided by the first embodiment of this application.

[0014] Figure 2 It is a schematic diagram of a system for intelligent remote control of a cooking machine based on artificial intelligence analysis provided by the second embodiment of this application. Detailed Embodiments

[0015] Many specific details are set forth in the following description in order to provide a thorough understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of this application. Therefore, this application is not limited by the specific implementations disclosed below.

[0016] The first embodiment of this application provides an intelligent remote control method for a cooking machine based on artificial intelligence analysis. Please refer to Figure 1 , which is the flowchart of the first embodiment of this application. The following will be combined with Figure 1 to elaborate in detail on an intelligent remote control method for a cooking machine based on artificial intelligence analysis provided by the first embodiment of this application.

[0017] Step S101: Receive an operation instruction input by a user through a remote terminal device, where the operation instruction includes start, stop, speed adjustment, stirring time, and mode selection.

[0018] In step S101, an operation instruction input by a user is received through a remote terminal device to control the operating state and working mode of the cooking machine. The remote terminal device can be a smart phone, a tablet computer, a computer, or other electronic devices with wireless communication functions. The communication between the remote terminal device and the cooking machine can adopt Wi-Fi, Bluetooth, cellular network (4G / 5G), or other wireless communication protocols to ensure real-time data transmission and stable connection.

[0019] The user can input an operation instruction through the application program, web interface, or voice assistant of the remote terminal device. The operation instruction includes, but is not limited to, start, stop, speed adjustment, stirring time, and mode selection. Specifically, the start instruction is used to activate the cooking machine and make it enter the working state; the stop instruction is used to terminate the current running task to ensure that the user can interrupt the operation at any time when necessary. The speed adjustment instruction allows the user to set the stirring speed according to the requirements of different ingredients. For example, a lower speed is suitable for gentle mixing, while a higher speed is suitable for stirring high-viscosity ingredients. The stirring time instruction is used to set the running duration of the cooking machine so that it automatically stops after reaching the preset time to prevent over-stirring from affecting the quality of the ingredients. In addition, the mode selection instruction allows the user to select a suitable stirring mode according to different recipes and ingredient types, such as dough stirring mode, egg liquid stirring mode, cream whipping mode, etc.

[0020] After receiving the operation instruction input by the user, the remote terminal device needs to parse the instruction to ensure that the data format meets the requirements of the cooking machine control system. After parsing, the operation instruction is converted into a standardized control signal and transmitted to the main control unit of the cooking machine through the communication module. After receiving the control signal, the main control unit of the cooking machine triggers the corresponding execution mechanism, such as activating the motor, adjusting the speed, setting the timer, etc., to complete the user's instruction.

[0021] To enhance the user experience and operational convenience, the remote terminal device can provide user interface feedback, such as displaying the currently input instruction, the estimated running duration, and the optimized options recommended by the system on the screen. In addition, if the cooking machine fails to successfully receive or execute an instruction, such as due to a network failure or abnormal device status, the remote terminal device can prompt the user with relevant error messages and suggest that the user re-enter the instruction or check the device connection status. To improve the stability of the system, the remote terminal device can adopt an ACK (Acknowledgment) confirmation mechanism, that is, after the cooking machine successfully receives an instruction, it returns a confirmation signal to the remote terminal device to ensure that the instruction is correctly transmitted and executed.

[0022] In summary, step S101 ensures that users can operate the cooking machine efficiently and accurately through the remote terminal device, enabling it to meet the processing requirements of different ingredients, while enhancing the stability and reliability of remote control.

[0023] Step S102: Use the built-in camera and sensors to obtain images and weight information of the ingredients in the cooking machine, and analyze the type, quantity, and mixing state of the ingredients based on a pre-trained neural network model to generate ingredient processing parameters.

[0024] In step S102, the cooking machine needs to use the built-in camera and sensors to collect relevant information about the ingredients to ensure that the system can accurately analyze the type, quantity, and current mixing state of the ingredients, thereby providing data support for the subsequent optimization of the stirring mode. The implementation of this step mainly relies on the collaborative work of the hardware acquisition module, the data processing unit, and the artificial intelligence analysis model.

[0025] First, the built-in camera is installed above or on the side of the stirring cavity of the cooking machine to clearly capture the image information of the ingredients. The resolution of the camera should meet the requirements for ingredient type and state recognition. Usually, it is recommended to use a high-definition CMOS or CCD sensor to provide sufficient visual details. To ensure the stability and consistency of shooting, the camera can also be equipped with a fill light or use infrared imaging technology to reduce the impact of changes in the light environment on the image quality. After the system is started, the camera will capture images periodically or at key operation nodes (such as after the user inputs an instruction or before stirring starts), and transmit the image data to the processing unit for analysis.

[0026] At the same time, the weight sensor is usually installed on the base of the cooking machine or under the stirring container to measure the total weight of the ingredients. The sensor should have high precision to ensure accurate identification of different ingredient proportions. For example, strain gauge sensors or MEMS pressure sensors should be used to achieve a measurement accuracy at the gram level. The system can reduce instantaneous errors by taking multiple measurements and averaging, and combine the data obtained by the camera to improve the reliability of ingredient identification.

[0027] After obtaining the ingredient image and weight information, the data is transmitted to the artificial intelligence analysis module. This module contains a pre-trained neural network model responsible for parsing the image data and identifying features such as ingredient types, colors, and shapes. The training process of the neural network is usually based on a large amount of ingredient sample data and uses deep learning frameworks (such as CNN convolutional neural networks) to improve the recognition accuracy. The model can distinguish different types of ingredients, such as flour, eggs, butter, etc., and can detect their quantities and mixing states. For example, the system can judge the humidity of the dough, the uniformity of the egg liquid, and even identify the mixing degree of different particle sizes to assist in optimizing the subsequent stirring process.

[0028] During the data processing, the system also needs to combine the data from the weight sensor to further correct the errors in image analysis. For example, if the camera identifies a certain ingredient, but the measured value of the weight sensor does not match the typical mass range of this ingredient, the system can readjust the recognition result or prompt the user to check the placement of the ingredient. In addition, the artificial intelligence model can use multi-frame image analysis technology to identify the mixing uniformity of the ingredients by comparing the images before and after stirring, and dynamically adjust the model weights to improve the adaptability to different ingredients.

[0029] Finally, based on the image analysis and weight data, the system generates ingredient processing parameters. These parameters serve as an important basis for optimizing the subsequent stirring mode and will be combined with the operation instructions input by the user and the preset recipe database in the next step to determine the optimal stirring strategy.

[0030] In summary, step S102 realizes the comprehensive acquisition of ingredient information through the collaborative work of the camera and the sensor, and uses the artificial intelligence model for high-precision analysis to ensure that the system can accurately identify the ingredient state and provide accurate data support for the subsequent intelligent stirring control.

[0031] Furthermore, the neural network model includes an ingredient recognition module, a mixing state evaluation module, and an ingredient processing parameter generation module;

[0032] Among them, the ingredient recognition module is used to identify and estimate the type, quantity, and preliminary mixing ratio of the ingredients. The input of the ingredient recognition module is the ingredient image data collected by the camera and the weight data collected by the weight sensor, and the output is the ingredient type, weight parameter, preliminary mixing ratio, and estimated value of the solid-liquid content. The ingredient recognition module adopts a dual-channel convolutional neural network architecture. The first channel is used to process the image data, and extracts the color, shape, and edge information of the ingredients through multiple convolutional, pooling, and fully connected layers. The second channel is used to process the weight data and match the known ingredient density characteristics based on a statistical model. Through the feature fusion layer, the image features and weight information are combined to output the classification and preliminary ratio estimation value of the ingredients.

[0033] The mixing state evaluation module is used to analyze the mixing state of the dough or ingredients during the operation of the dough mixer. The input of the mixing state evaluation module is the continuous frame image data collected by the camera and the real-time torque data collected by the torque sensor, and the output is the mixing uniformity score, the gluten network formation state, and the real-time state parameters during the mixing process. Among them, the mixing state evaluation module uses a temporal convolutional network combined with a long short-term memory network for analysis. The temporal convolutional network is used to extract the characteristics of the distribution change of the ingredients in the continuous frame images and calculate the change trend of the dough structure. The long short-term memory network is used to analyze the change pattern of the torque data to judge the degree of gluten network formation during the stirring process, and calculate the mixing uniformity score and other parameters characterizing the dough state based on the set uniformity threshold.

[0034] The ingredient processing parameter generation module is used to generate the final ingredient processing parameters based on the output data of the ingredient recognition module and the mixing state evaluation module. The input of the ingredient processing parameter generation module is the ingredient type, weight parameter, preliminary mixing ratio, solid-liquid content estimation value, mixing uniformity score, and gluten network formation state, and the output is the ingredient processing parameters. Among them, the ingredient processing parameter generation module adopts a multi-layer perceptron structure. After the input data is normalized, the final ingredient processing parameters are generated through multi-layer non-linear mapping. The ingredient processing parameters include the recommended mixing time, stirring speed, required additional liquid or solid ingredient amount, and ingredient mixing adjustment suggestions.

[0035] In this embodiment, in order to achieve accurate identification of the ingredients in the dough mixer, analysis of the mixing state, and optimization of the stirring control, the system uses a neural network model, which is composed of an ingredient recognition module, a mixing state evaluation module, and an ingredient processing parameter generation module. Each module works together to ensure that the processing quality of the dough or other ingredients is stable, controllable, and meets different formula requirements.

[0036] The ingredient recognition module is responsible for classifying, weighing the ingredients put into the cooking machine, and estimating the preliminary mixing ratio. The inputs of this module include the ingredient image data collected by the camera and the weight information measured by the weight sensor. The images captured by the camera can be used to analyze the color, shape, and edge features of the ingredients, while the weight data provides the actual mass information of the ingredients. This module adopts a dual-channel convolutional neural network architecture. The first channel is specifically used to process the image data. It extracts low-level and high-level features through multiple layers of convolution, reduces the data dimension using pooling operations, and calculates the key visual features of the ingredients, such as color distribution, texture details, and shape contours, through the fully connected layer. The second channel is used to process the weight data and matches the density characteristics of known ingredients based on a statistical model to assist in judging the ingredient type and improving the recognition accuracy. Through the feature fusion layer, this module can combine the image features and weight information to generate the final ingredient recognition result, and output the classification of the ingredients, weight parameters, preliminary mixing ratio, and estimated values of solid-liquid content. These data are then transmitted to the mixing state evaluation module for further analysis of the ingredient state during the mixing process.

[0037] During the operation of the cooking machine, the mixing state evaluation module is responsible for analyzing the state of the dough or other mixtures to ensure that the mixing uniformity meets the expected requirements. The inputs of this module include the image data continuously collected by the camera and the resistance change data measured by the torque sensor in real time. The evaluation of the mixing state adopts an analysis method combining a temporal convolutional network and a long short-term memory network. The temporal convolutional network is used to extract the features of the dough structure change from consecutive frame images, such as observing the evolution trend of the ingredient distribution at different time steps and detecting local areas with uneven mixing. The long short-term memory network is mainly used to process the change patterns of the torque data and identify the elasticity, resistance, and internal structure formation of the dough at different stages. By analyzing the change curve of the torque data, this module can judge the formation degree of the gluten network during the mixing process, calculate the mixing uniformity score based on the set uniformity threshold, and other parameters characterizing the dough state. This score can be used to dynamically adjust the mixing plan to ensure that different types of ingredients can reach an ideal mixing state.

[0038] The function of the ingredient processing parameter generation module is to generate the final ingredient processing parameters based on the output data of the ingredient recognition module and the mixing state evaluation module, so as to provide optimized control instructions for the stirring process. The inputs of this module include the type of ingredients, weight parameters, preliminary mixing ratio, estimated solid-liquid content, mixing uniformity score, and gluten network formation state. This module adopts a multi-layer perceptron structure. After normalizing the input data, it calculates the optimal stirring parameters through multi-layer non-linear mapping. Specifically, this module can calculate and recommend the mixing time, stirring speed, the amount of additional liquid or solid ingredients required based on the neural network, as well as suggestions for adjusting the ingredient mixing based on the dough state. For example, if the system detects that the gluten network has not been fully formed, the stirring time can be appropriately extended or the speed can be adjusted to improve the taste and structure of the final product. In addition, when it is recognized that the ratio of specific ingredients does not match, this module can suggest to the user to increase or decrease certain ingredients to optimize the mixing effect.

[0039] Through the collaborative effect of the above three modules in this embodiment, the chef machine can intelligently adjust the stirring parameters according to the type of ingredients and the mixing state, thereby improving the processing accuracy, reducing human intervention, and enhancing the stability and consistency of ingredient mixing. The application of this method can not only adapt to various ingredient combinations, but also dynamically adjust the mixing strategy to ensure that the final product meets the expected quality standards.

[0040] The following is the schematic reference implementation code of the neural network model:

[0041]

[0042]

[0043]

[0044]

[0045]

[0046] The process of training this neural network model includes data collection, data preprocessing, model training, optimization, and evaluation. First, a large number of ingredient images, weight data, real-time torque data during the stirring process, and consecutive frame images are collected, and the type of ingredients, preliminary mixing ratio, gluten network state, and final mixing effect are labeled. Data preprocessing includes image normalization, data augmentation, weight normalization, and sliding window processing of time series data to improve the generalization ability of the model.

[0047] The food ingredient recognition module is trained using a dual-channel convolutional neural network. Among them, the image data undergoes multiple layers of convolution, pooling, and feature extraction, and the weight data is processed through a fully connected network. After the two are merged in the feature fusion layer, a classification task is carried out, and the cross-entropy loss function is used for optimization. The mixed state evaluation module processes consecutive frame images using a temporal convolutional network, processes torque data using LSTM, calculates the mixing uniformity score, and optimizes the prediction accuracy using the mean squared error loss. The food ingredient processing parameter generation module uses a multi-layer perceptron, inputs the output data of the aforementioned two modules, and adjusts the weights through the gradient descent method to minimize the prediction error. Finally, the performance of the model is evaluated using validation data, the hyperparameters are adjusted to improve the training effect, and the adaptability and robustness on new data are ensured.

[0048] Furthermore, the mixed state evaluation module includes a dynamic torque uniformity optimization calculation unit. This calculation unit calculates the mixing uniformity score according to the following formula 1 based on real-time torque data, the dough surface change parameters collected by the camera, and the gluten network formation state:

[0049]

[0050] Among them, U is the mixing uniformity score, and the range is [0, 1]. When U is closer to 1, it indicates that the mixing uniformity of the dough is lower and there is still a large room for optimization; when U is closer to 0, it indicates that the dough mixing is approaching a uniform state. This score comprehensively considers the smoothness of torque change, the uniformity of the dough surface, and the formation of the internal gluten network to provide a more reliable evaluation of the mixing state.

[0051] N is the number of time steps sampled by the torque sensor; T i represents the torque value at the i-th time step; T i-1 represents the torque value at the (i - 1)-th time step; M is the number of image frames captured by the camera; V j represents the surface feature distribution uniformity score of the j-th frame image. The surface feature distribution uniformity score is calculated by the image analysis module based on the food ingredient distribution histogram, reflecting the smoothness of the dough surface and the material distribution; V j-1 represents the surface feature distribution uniformity score of the (j - 1)-th frame image; R is the degree of gluten network formation, calculated by the long short-term memory network, reflecting the formation state of the internal elastic structure of the dough; α, β, γ, λ are empirical optimization parameters;

[0052] Based on the calculated mixing uniformity score, when the uniformity score is lower than the set threshold, the dynamic torque uniformity optimization calculation unit automatically adjusts the stirring mode, rotation speed, and stirring time, and provides optimization suggestions.

[0053] The first term is used to measure the smoothness of torque change. T iRepresents the torque value at the i-th time step, in units of N·m (Newton·meter), measured by a torque sensor. T i-1 Represents the torque value at the previous time step. The change in torque |T i -T i-1 | reflects the changing trend of the force on the dough. If the torque value varies significantly between adjacent time steps, it indicates that the resistance of the dough during the stirring process is unstable, which may mean that the dough has not reached a homogeneous mixing state. When the torque change is small, it means that the force on the dough tends to be stable, indicating relatively homogeneous mixing. This item calculates the average value of the torque changes within N time steps, normalizes it to the range [0,1], and multiplies it by the weight coefficient α to adjust its influence in the overall score. The recommended value of α is 0.4 to 0.6, used to balance the contribution of the torque change term. The unit of α is (N·m) -1 , so that the first item is dimensionless.

[0054] The second item Evaluates the uniformity of the surface distribution of the dough. V j Represents the surface feature distribution uniformity score calculated from the j-th frame of the image. This score is calculated by the image analysis module based on the histogram of the ingredient distribution on the dough surface, and its value range is [0,1]. The higher the value, the smoother the dough surface and the more uniform the material distribution. The difference between adjacent frames |V j -V j-1 | represents the degree of fluctuation of the surface uniformity. If this value is large, it indicates that there are still obvious inhomogeneous regions on the dough surface. This item calculates the average value of M frames of images and normalizes it to [0,1], and multiplies it by the weight coefficient β to reflect its influence in the overall score. The recommended value of β is 0.3 to 0.5, used to adjust the contribution of this item to the final score. β is dimensionless.

[0055] The third item γ·e -λR Evaluates the formation state of the gluten network. R represents the degree of gluten network formation, which is calculated by a long short-term memory network (LSTM) based on torque data, time series features, and ingredient types. The higher the value, the higher the degree of gluten network formation, and the lower the value, the less well-established the gluten network. The exponential decay factor e -λR makes this item gradually approach 0 as R increases, indicating that the internal structure of the dough tends to be stable. When R is at a low level, the value of this item is close to γ and contributes more to the mixing uniformity score. The weight coefficient γ sets the influence of this item in the overall score. The recommended value of γ is 0.2 to 0.4 to ensure its appropriate contribution to the uniformity score. γ is dimensionless. The exponential decay factor λ controls the influence degree of R on this item. The recommended value of λ is 0.8 to 1.2 to provide moderate smoothing control.

[0056] Overall, this formula comprehensively considers the force characteristics of the dough, surface smoothness, and the formation state of the internal structure to provide a comprehensive mixing uniformity score. After the calculation, this score is used to determine whether the current mixing state meets the preset standard, and when the score is lower than the set threshold U threshold , the system will automatically adjust the mixing mode, rotation speed, and mixing time. For example, if U is lower than 0.6, the system may reduce the rotation speed and extend the mixing time to promote uniform mixing inside the dough; if U is lower than 0.4, the system may suggest the user to add additional liquid or readjust the recipe to improve the plasticity of the dough. The generation logic of the optimization suggestions is based on reinforcement learning or historical data matching, enabling the kitchen machine to dynamically adapt to different dough recipes and ensuring that the final product meets the set quality requirements.

[0057] This method can not only accurately evaluate the mixing uniformity of the dough, but also provide real-time optimization and adjustment, enabling the kitchen machine to have higher adaptability in the intelligent food processing process, reducing human intervention, and improving the consistency and stability of pastry making.

[0058] Step S103: Combine the operation instructions, food material processing parameters input by the user, and the preset recipe database to determine the mixing mode, rotation speed, and operation time of the kitchen machine, and generate a control instruction.

[0059] In step S103, the system needs to combine the operation instructions input by the user, food material processing parameters, and the preset recipe database to determine the mixing mode, rotation speed, and operation time of the kitchen machine, and generate the corresponding control instruction. The core of this step lies in the fusion and calculation of data to ensure that the kitchen machine can execute the optimal mixing plan under different food material conditions and user requirements.

[0060] When the system receives the operation instructions input by the user, it will first analyze the instruction content to determine the specific needs of the user. For example, if the user only selects to start or a certain specific mode without setting the detailed mixing time or rotation speed, the system will need to further combine the food material state and the recipe database to automatically match the appropriate mixing parameters. On the contrary, if the user has clearly specified the rotation speed and operation time, the system will give priority to the parameters set by the user and only provide optimization suggestions when necessary, without forcibly modifying the user's settings.

[0061] Meanwhile, the ingredient processing parameters generated in step S102 will be input into the decision-making system. These parameters include, but are not limited to, the recommended mixing time, stirring speed, required amounts of additional liquid or solid ingredients, and ingredient mixing adjustment suggestions, etc. The system will judge the characteristics of the current ingredients based on these parameters and compare them with the preset stirring standards. For example, if the identified ingredients are a mixture of flour and eggs and the current humidity is low, the system may tend to recommend slow and long-term stirring to ensure thorough mixing without excessive formation of gluten structure. For the scenario of whipping cream, the system may recommend gradually increasing the speed to achieve an ideal swelling effect.

[0062] After obtaining the user input and ingredient processing parameters, the system will further query the preset recipe database. This database stores the optimal stirring schemes for different ingredient combinations and can be adaptively adjusted according to the actual situation. The content of the recipe database can include standard recipe parameters, such as the recommended stirring time and speed range for a certain cake recipe, and may also contain parameters optimized based on historical data. For example, the system may record the user's previous operation habits and adjust with reference to the parameters used by the user under the same ingredient combination to improve the degree of personalized matching of the operation. The recipe database can be statically stored data or continuously optimized through online updates or machine learning to adapt to different user usage habits and the introduction of new recipes.

[0063] After comprehensively considering the user instructions, ingredient processing parameters, and recipe database, the system will perform parameter optimization calculations to finally determine the stirring mode, speed, and running time. The stirring mode determines the operation mode of the motor, such as constant speed operation, gradual speed increase, intermittent stirring, etc., which are suitable for different ingredient processing requirements. The speed determines the rotation speed of the stirring paddle and directly affects the mixing effect of the ingredients, while the running time controls the duration of the entire stirring process to ensure that the ingredients reach an appropriate mixing state.

[0064] Finally, the system generates specific control instructions based on the calculated optimal parameters and is ready to send them to the execution module of the cooking machine. The control instructions usually adopt a standardized data format to ensure compatibility with the control system of the cooking machine and support real-time adjustment. For example, the instructions may include the initial speed, stirring time, mode type, and whether dynamic adjustment is allowed during operation to adapt to changes in the actual situation. These instructions can be transmitted to the main control unit of the cooking machine through wireless communication or wired connection and are executed in step S104.

[0065] Through the optimization calculation and instruction generation in this step, the cooking machine can automatically adjust the operation parameters under different ingredient states and user requirements to ensure the stability and accuracy of the stirring effect, while reducing the user's operation burden and improving the degree of intelligence.

[0066] Furthermore, determining the stirring mode, rotation speed and running time of the cooking machine by combining the operation instructions input by the user, the ingredient processing parameters and the preset recipe database includes:

[0067] Based on the recommended mixing time and stirring speed in the ingredient processing parameters, match the closest standard recipe parameters in the preset recipe database, and combine the operation instructions input by the user to compare the difference between the currently set stirring mode and the recommended mode. If the user does not set custom parameters, directly adopt the recommended parameters; if the user sets different stirring times or rotation speeds, calculate the impact of this parameter adjustment on the ingredient mixing effect, and provide optional optimization suggestions on the remote terminal device.

[0068] Before executing the stirring mode, dynamically evaluate the viscosity, fluidity and structure of the dough or ingredient mixture in combination with the required additional liquid or solid ingredient amounts in the ingredient processing parameters, and adjust the liquid or solid addition timing according to the real-time sensor data during the stirring process, so that high-viscosity dough is supplemented with liquid at an appropriate stage, and low-viscosity dough is supplemented with solid powder at an appropriate stage to ensure the best plasticity and mixing uniformity of the dough.

[0069] In this embodiment, the stirring mode, rotation speed and running time of the cooking machine are intelligently determined by combining the operation instructions input by the user, the ingredient processing parameters and the preset recipe database to ensure that different types of ingredients can be processed according to the best process, improving the mixing uniformity and the quality of the final product. This process relies on intelligent data matching and real-time adjustment mechanisms to ensure the accuracy and flexibility of the operation.

[0070] When the user inputs a start instruction, the system first obtains the recommended mixing time and stirring speed in the ingredient processing parameters, and retrieves the standard recipe parameters that best match the ingredient in the preset recipe database. This database contains a large number of experimentally verified best stirring schemes, including the best stirring modes, rotation speed ranges and running time intervals for different ingredient combinations. The system ensures that the selected parameters can match the mixing characteristics of the ingredient by comparing the current recommended parameters with the standard recipe parameters in the database.

[0071] After the parameter comparison is completed, the system further combines the custom instructions input by the user to determine whether to adopt the recommended parameters or make adjustments. If the user does not make custom modifications to the stirring mode, speed, or running time, the system automatically adopts the best parameters recommended by the database to ensure that the stirring process meets the requirements of the standardized process. If the user manually sets different stirring times or speeds, the system will analyze the impact of these adjustments on the ingredient mixing effect and calculate the possible changes in uniformity, dough elasticity differences, or mixing stability fluctuations. If the system detects that the user's adjustments may lead to over-stirring of the dough, damage to the gluten structure, or uneven mixing of the ingredients, it will provide optimization suggestions on the remote terminal device, and the user can choose to accept the recommended adjustments or continue to use the custom parameters. This method not only ensures the intelligent optimization ability of the system but also retains the user's personalized control.

[0072] After determining the stirring mode, before performing the stirring, the system further dynamically evaluates the physical properties of the ingredients in combination with the required additional liquid or solid ingredient amounts in the ingredient processing parameters. For high-viscosity doughs, such as bread dough with a high protein content or pizza dough that requires long-term stirring, the system analyzes the internal moisture distribution and supplements the liquid at an appropriate stage to optimize the dough's extensibility and fermentation effect. If it is detected that a too-thick dry layer begins to form on the surface of the dough, the system precisely controls the liquid dosage and gradually adds water or oil at specific time points during the stirring process to avoid structural damage caused by over-stirring. For low-viscosity doughs, such as cake batter or rice milk, the system monitors the liquid content during the stirring process and supplements the solid powder at appropriate time points to ensure that the overall viscosity reaches the expected standard and prevent layering or precipitation phenomena caused by excessive fluidity during the mixing process.

[0073] The entire process is closed-loop controlled through the real-time data feedback of the sensors. The system not only selects the stirring mode based on the initial set parameters but can also make dynamic adjustments according to the actual state of the dough or ingredients during the stirring process. During the stirring process, the viscosity sensor, pressure sensor, and image analysis module work together to evaluate the state changes of the dough in real time. When it is detected that the dough is approaching the optimal mixing uniformity but has not yet reached the final stable state of the gluten network, the system can appropriately extend the low-speed stirring stage to ensure the full formation of the internal structure; if it is detected that the ingredient distribution is uneven during the stirring process or there are compositional deviations in certain areas, the system can adjust the speed mode or add additional stirring cycles to improve the overall uniformity.

[0074] Through the above methods, the chef machine can ensure standardized operation while adapting to the personalized needs of different ingredients, ensuring that each mixing process can achieve the best effect, improving the accuracy of automatic stirring, and providing intelligent optimization suggestions when the user adjusts the parameters to optimize the operation experience and the final food quality.

[0075] Step S104: Send the generated control instructions to the cooking machine for execution, and monitor the operating status through sensors, and feedback the operation process and abnormal information to the remote terminal device in real time.

[0076] In step S104, the system needs to send the generated control instructions to the cooking machine for execution, and monitor its operating status through sensors to ensure the accuracy of the mixing process. At the same time, it feedbacks the operation process and abnormal information to the remote terminal device in real time. This step involves multiple links such as instruction transmission, device control, status monitoring and data backhaul to ensure the stability and intelligence level of the whole operation.

[0077] When the control instructions are calculated and optimized in step S103, the system needs to transmit the instructions to the main control unit of the cooking machine through an appropriate communication method. The communication methods can include Wi-Fi, Bluetooth, Zigbee, wired serial communication (such as UART or I2C), etc. The specific method to be adopted can be determined according to the device design requirements. During the data transmission process, the system usually adopts the data packet formatting method to ensure that the instructions will not be in error due to network fluctuations or interference during transmission. For example, a check code (such as CRC check) can be used to verify the integrity of the data packet to ensure that the received instructions are not damaged or tampered with. After receiving the instructions, the main control unit of the cooking machine will parse the control parameters and activate the corresponding execution units according to the instruction requirements, such as motors, mixing paddles, timers, etc., to make the device enter the set mixing mode.

[0078] During the execution of the control instructions, the system needs to monitor the operating status of the cooking machine in real time to detect whether the device is operating as expected and make adjustments or alarm prompts when necessary. The status monitoring mainly relies on multiple sensors, including but not limited to current sensors, temperature sensors, torque sensors, weight sensors, vibration sensors and cameras. These sensors are used to detect motor load, mixing temperature, resistance of ingredients during mixing, change in ingredient weight, abnormal vibration of the device and visual feedback of the mixing state, etc. For example, a current sensor can be used to determine whether the motor is overloaded, and a temperature sensor can monitor the temperature of the motor or the mixing chamber to prevent damage caused by overheating, while a camera can be used to identify the mixing uniformity of the ingredients to ensure that the mixing effect meets the expectations.

[0079] After obtaining the sensor data, the system will compare it with the preset operating parameters to determine whether there are any abnormal situations. For example, if the motor current exceeds the normal range, it may mean that the viscosity of the ingredients is too high or the ingredients are stuck. The system needs to execute corresponding adjustment strategies to avoid equipment damage or mixing failure. If the system detects an abnormal situation, such as a sudden current fluctuation, temperature increase, abnormal weight change during the mixing process, or the ingredient state feedback by the camera not meeting the expectation, the system can take various measures, including reducing the rotation speed, adjusting the mixing time, pausing the operation, or sending an abnormal prompt to the user, to ensure the safe operation of the equipment.

[0080] Meanwhile, all operating status data needs to be transmitted to the remote terminal device in real time, enabling the user to monitor the mixing process in a remote environment. The remote terminal device can be a smartphone, tablet, or computer, and the data transmission method can adopt Wi-Fi, Bluetooth, or cloud server synchronization to ensure that the user can view the status of the cooking machine at any time. For example, the user can view information such as the current mixing mode, remaining time, real-time mixing rotation speed, and motor load on the mobile application. If an abnormality occurs, the remote terminal device can remind the user to take necessary intervention measures, such as confirming the adjustment parameters, stopping the operation, or manually checking the equipment, through push notifications or pop-up windows.

[0081] During the entire execution process, the system not only needs to feedback the mixing progress but also provide detailed abnormal information to help the user understand the problem. For example, if the system detects that the ingredients are not evenly mixed, the remote terminal may display "Low ingredient mixing degree, it is recommended to extend the mixing time" or "Detected that the viscosity of the ingredients is too high, it is recommended to reduce the rotation speed". These messages can effectively guide the user to adjust the operation, thereby improving the mixing effect and the intelligent experience of the equipment.

[0082] Through the implementation of this step, the cooking machine can accurately execute remote control instructions, and in the process of operation, it can monitor the status in real time, detect abnormalities, and feedback key information to the user, thereby ensuring the mixing quality and equipment safety, improving the user experience, and enhancing the intelligent level of the system.

[0083] Step S105: When detecting overload, abnormal ingredient mixing, or abnormal operation, analyze the cause of the abnormality and execute corresponding adjustment strategies, including adjusting the rotation speed, modifying the operation mode, or prompting the user to intervene. At the same time, push the operating status of the cooking machine, the progress of ingredient mixing, and the recommended adjustment plan to the remote terminal device.

[0084] In step S105, when the system detects overload, abnormal ingredient mixing, or other operating abnormalities during the operation of the cooking machine, it is necessary to analyze the abnormal situation and execute corresponding adjustment strategies to ensure the stability and safety of the stirring process. At the same time, it pushes the operating status of the cooking machine, the progress of ingredient mixing, and recommended adjustment plans to the remote terminal device so that users can obtain information in a timely manner and take necessary measures.

[0085] First of all, the system needs to monitor various operating parameters of the cooking machine in real time, including but not limited to the current and torque of the motor, the ingredient mixing state in the mixing chamber, the vibration of the equipment, and the temperature change. When an abnormality is detected, the system needs to analyze the specific type of the abnormality. For example, if the motor current suddenly increases and the torque exceeds the normal range, it may mean that the ingredient viscosity is too high or the ingredients are stuck to the mixing paddle. At this time, the system needs to judge whether the load can be relieved by reducing the rotation speed, or whether it is necessary to pause the operation and prompt the user for manual intervention. In addition, if the sensor detects that the ingredient mixing degree is low and fails to reach the expected uniform state for a period of time, the system can judge whether the current stirring strategy is applicable and make adjustments according to the optimization plan in the recipe database.

[0086] During the process of analyzing the abnormality, the system can use a variety of strategies for adjustment. For example, if the system detects overload, it can gradually reduce the stirring speed and monitor the change of the motor current to judge whether it is necessary to continue reducing the rotation speed, or switch to the intermittent stirring mode to reduce the continuous load on the motor. When detecting abnormal ingredient mixing, such as some ingredients not being evenly distributed or the viscosity exceeding the expectation, the system can appropriately extend the stirring time, or adjust the movement mode of the mixing paddle, such as switching from high-speed continuous stirring to low-speed reverse stirring, to improve the mixing effect. If the system detects abnormal temperature, such as too high motor temperature, it may trigger a short-term stop of operation to prevent equipment damage, and at the same time notify the user to take appropriate heat dissipation measures, such as reducing the stirring time or avoiding long-term continuous operation.

[0087] After the adjustment strategy is executed, the system will continuously monitor the device status to confirm whether the abnormal problem has been successfully solved. If the normal operation has not been restored after the adjustment, or the ingredient state still does not meet the expectation, the system will push detailed operating status information to the user and provide further adjustment suggestions. For example, if the system detects that the dough is too hard and the stirring difficulty increases, it may recommend that the user add an appropriate amount of liquid ingredient; if it detects that the egg liquid is not fully whipped, it may recommend that the user extend the stirring time or adjust the stirring mode. The user can confirm these suggestions through the remote terminal device and manually adjust the control parameters to optimize the final stirring effect.

[0088] During the process of pushing information, the system can interact with users in various ways, including message notifications of mobile applications, screen pop-up warnings, or voice prompts of intelligent voice assistants, to ensure that users can timely know the status of the device. When the user receives the adjustment plan, they can choose to accept the system's optimization plan to enable the device to automatically execute the adjustment strategy, or manually modify the parameters to meet personalized needs. If the user chooses to make manual adjustments, the system will re-execute the control instructions under the new parameter settings and continue to monitor the device operation to ensure that the adjusted operation meets the user's goals.

[0089] The implementation of this step not only improves the operation stability of the device, avoiding operation failures caused by overload or uneven mixing, but also enhances the operation flexibility of the user, enabling them to precisely control and intervene in the operation of the device in a remote environment. In addition, through intelligent analysis and adaptive adjustment, the system can continuously optimize the mixing parameters, improve the intelligent level of the device, and significantly improve the final effect of ingredient processing.

[0090] Furthermore, when overload, abnormal ingredient mixing, or abnormal operation is detected, analyze the cause of the abnormality and execute the corresponding adjustment strategy, including:

[0091] Based on the data of the torque sensor, camera, and pressure sensor, identify the type of abnormality and determine whether it belongs to torque overload, uneven mixing, or abnormal ingredient adhesion; among them, for torque overload, reduce the mixing speed and adjust the mixing mode to reduce resistance; for uneven mixing, extend the mixing time or increase the low-speed mixing stage; for abnormal ingredient adhesion, adjust the mixing trajectory or increase the vibration of the container to improve the mixing state;

[0092] Push the adjustment plan to the remote terminal device, allowing the user to manually intervene or confirm the automatic optimization.

[0093] In this embodiment, when the cooking machine detects overload, abnormal ingredient mixing, or abnormal operation during operation, the system performs abnormality identification based on the data collected by the sensors and executes the corresponding adjustment strategy to ensure the stability of the mixing process and the quality of the final ingredients. The core of abnormality detection relies on the real-time data analysis of the torque sensor, camera, and pressure sensor. By comparing with the reference values in the normal operation state, the system can accurately identify the type of abnormality and take appropriate adjustment measures.

[0094] When the system detects torque overload, it usually manifests as a sharp increase in torque data within a short period or exceeding the set threshold, which may be caused by overly dry dough or excessive stirring resistance. To avoid damage to the motor due to overload or failure of dough stirring, the system will automatically reduce the stirring speed and adjust the stirring mode, causing the movement trajectory of the stirring paddle to change to reduce local pressure concentration. If the torque overload situation remains unrelieved, the system will recommend that the user appropriately increase the liquid ingredients to reduce the overall viscosity of the dough and optimize the mixing effect.

[0095] Regarding the problem of uneven stirring, the system analyzes the change trend of the ingredient distribution based on the continuous image frames captured by the camera and calculates the mixing uniformity score. If the system detects that the uniformity score of the ingredients does not reach the standard value within the preset time, it indicates insufficient stirring or some ingredients have not been fully integrated. To improve this situation, the system can appropriately extend the stirring time, allowing the dough to continue running in the low-speed mode to enhance the interaction between the ingredients. At the same time, the system may adjust the stirring rhythm, such as increasing intermittent stirring, so that the ingredients that are not fully mixed can have more opportunities for uniform distribution, improving the final mixing effect.

[0096] In the case of abnormal ingredient adhesion, the system mainly relies on the feedback data from the pressure sensor and the stirring motor for analysis. When the system detects that the ingredients adhere to the stirring paddle or the container wall, resulting in a decrease in stirring efficiency, it will adjust the stirring trajectory so that the stirring paddle makes additional movements in different directions to improve the ingredient distribution. In addition, the system can also increase the container vibration function to make the ingredients adhering to the container wall fall off, thus restoring the normal stirring state. If the adhesion phenomenon persists, the system may push a prompt message to the remote terminal device, recommending that the user check the ingredient status and, according to the adjustment suggestions provided by the system, appropriately add lubricating ingredients (such as oil or water) to optimize the stirring effect.

[0097] During the execution of the abnormal adjustment strategy, all adjustment plans will be pushed to the remote terminal device in real time. The user can choose to manually intervene, adjust the mixing parameters, or directly confirm the adjustment plan automatically optimized by the system. The user can view the detailed analysis of the abnormal situation on the terminal and fine-tune the adjustment plan according to actual needs to ensure that the final mixing state meets the expected standard. After the optimization plan is executed, the system will record the adjustment data of this time and store it in the historical database to optimize the intelligent adjustment strategy in subsequent similar situations, improving the overall operation stability and intelligence level.

[0098] Furthermore, the intelligent remote control method for the chef machine based on artificial intelligence analysis further includes:

[0099] Construct a user personalized pasta making model based on the user's historical operation data, seasonal preferences, and regional characteristics;

[0100] When the user inputs the type of pasta, adjust the production parameters according to the personalized pasta production model, including the ratio of flour to liquid, proofing time, kneading strength, and stirring speed;

[0101] Based on the physiological status of the user recorded by the remote terminal device, perform health optimization adjustment on the production parameters, where the physiological status includes blood glucose level, blood pressure value, and blood lipid index;

[0102] According to the physiological status, automatically adjust the sugar addition amount, flour type selection, and oil usage amount in pasta production, and provide production suggestions for low-sugar, low-salt, or low-fat alternative options on the remote terminal device.

[0103] In this embodiment, a user personalized pasta production model is constructed through multiple data sources to adapt to different users' taste preferences, health needs, and environmental variables, so as to realize intelligent and healthy pasta production. This method relies on historical data analysis, artificial intelligence algorithms, and real-time health monitoring to provide the most optimized production parameters for users.

[0104] During the operation of the system, first, it will collect the past pasta production operation data of the user, including the recipes selected each time when using the dough mixer, the adjusted parameters, and the feedback information of the final product. For example, the system will record the ratio of flour to liquid, kneading strength, stirring speed, and proofing time selected by the user when making steamed buns, and at the same time, combined with the user feedback, such as "the dough is too hard", "insufficient fermentation", etc., gradually optimize the model so that it can learn the actual preferences of the user. As the number of uses increases, the system can more accurately match the user's habits and improve the success rate of each pasta production.

[0105] In addition to historical operation data, the system will also consider seasonal preferences and regional characteristics. The temperature and humidity changes in different seasons will affect the final forming effect of pasta. For example, in winter, the environmental temperature is relatively low, and the fermentation process may take longer. The system can automatically adjust the proofing time or suggest that the user increase the fermentation temperature; in summer, the air humidity is relatively high, and the water absorption of the dough may be different. The system can appropriately reduce the water addition to prevent excessive viscosity. In addition, regional characteristics will also affect the pasta production habits of users. For example, in the northern region, users may prefer a harder dough, while southern users may prefer a softer texture. The system can dynamically adjust the basic recipe based on the user's geographical location to better match the regional taste.

[0106] When the user inputs the type of pastry to be made, the system will call the personalized pastry-making model to optimize and adjust the production parameters based on the existing user data and external variables. These adjusted parameters include the ratio of flour to liquid, kneading strength, stirring speed, and proofing time. For example, for users who prefer a chewier texture, the system may increase the kneading strength to more fully form the gluten network, while for users who prefer a softer texture, the system may reduce the kneading time to lower the gluten strength. In addition, the choice of stirring speed can also be optimized according to the type of flour and the viscosity of the dough to ensure that the ingredients are fully mixed without over-stirring.

[0107] The system not only considers the user's taste requirements but also combines the user's health status to optimize the ingredients in the pastry-making process. Users can input or synchronize health data through remote terminal devices, such as physiological state parameters like blood sugar levels, blood pressure values, and blood lipid indices recorded by smart bracelets, health management apps, or medical devices. This data will be used by the system to adjust the key ingredients in pastry-making, such as the amount of sugar added, the choice of flour type, and the amount of oil used. For example, for users with higher blood sugar levels, the system may reduce the sugar addition or recommend using low-GI (glycemic index) flour to reduce the blood sugar burden; for users with higher blood lipids, the system may suggest reducing the amount of oil used or recommend using vegetable oil with a higher unsaturated fatty acid content to replace traditional animal fats to improve the dietary structure.

[0108] In addition, while adjusting the recipe, the system will also provide production suggestions for low-sugar, low-salt, or low-fat alternative options on the remote terminal device, and users can choose the appropriate optimization plan according to their own needs. For example, when the user tries to make a cake, the system may prompt "It is recommended to reduce the sugar by 20% and use a sugar substitute to replace part of the sucrose", or provide an option of "low-fat version, reduce the butter content and recommend using olive oil instead" when making bread. Users can choose the health optimization plan recommended by the system or adjust it according to their personal needs to make each pastry-making meet both taste preferences and health standards.

[0109] Throughout the pastry-making process, the system will continuously monitor the state of the dough and make dynamic adjustments if necessary. For example, during the dough stirring process, if the system detects that the dough is too sticky or too dry, it can automatically increase or decrease the liquid appropriately to ensure the stability of the final shaping. For pastries that require multi-step fermentation, such as European bread or Chinese steamed sponge cake, the system can dynamically adjust the temperature and humidity during the fermentation process to optimize the fermentation effect and obtain a more ideal fluffiness and texture.

[0110] Through this method, the dough mixer can not only optimize the production process according to the user's historical operation habits, but also provide personalized health optimization solutions by combining real-time health data, helping users maintain a reasonable diet structure while enjoying delicious food. This intelligent control method can effectively improve the accuracy and consistency of pasta making, while reducing the failure rate caused by improper parameter settings, making pasta making simpler, more intelligent and meeting individual health needs.

[0111] Furthermore, the intelligent remote control method of the dough mixer based on artificial intelligence analysis further includes:

[0112] A multi-band sound wave generating device is arranged in the dough mixer, and specific frequency sound waves are emitted during the stirring and kneading processes according to the physical characteristics of different pastas.

[0113] The sound wave reflection characteristics of the dough are monitored in real time through a sound wave sensor.

[0114] Based on the change curve of the sound wave reflection characteristics, the gluten formation stage of the dough is judged, and the stirring force, rotation speed and duration are adjusted accordingly.

[0115] When it is detected that the dough reaches the optimal gluten state, it enters the next processing stage, and a dough status report is sent to the remote terminal device.

[0116] In this embodiment, in order to further improve the intelligent level of the dough mixer during the dough stirring and kneading processes, a multi-band sound wave generating device is introduced inside the dough mixer, and the dough status is monitored and optimized in real time in combination with a sound wave sensor. This method accurately judges the gluten formation stage of the dough by analyzing the propagation and reflection characteristics of sound waves in the dough, and dynamically optimizes the stirring parameters, enabling different types of pastas to achieve an ideal taste and texture.

[0117] First of all, the multi-band sound wave generating device is installed inside the stirring cavity or around the body of the dough mixer, and can emit specific frequency sound waves according to the physical characteristics of the dough in different stirring modes. Different doughs have different sound wave absorption rates and reflection characteristics during the stirring process, and these characteristics are affected by the gluten network structure, water content, viscosity and stirring state inside the dough. Therefore, before starting to stir or knead, the system will preset a reference sound wave frequency band suitable for this type of dough according to the type of pasta selected by the user. For example, for high-gluten bread dough, the system may choose a lower frequency sound wave for monitoring, while for softer cake batter or Chinese steamed sponge cake, a higher frequency sound wave may be selected for analysis.

[0118] During the stirring and kneading process, the system uses a sonic sensor to collect real-time data on the propagation and reflection of sound waves within the dough, and converts this data into a sonic reflection characteristic curve. The sonic sensor can be installed near the mixing paddle of the mixer or on the container wall to ensure continuous monitoring of the entire dough state. When the gluten network within the dough begins to form, its ability to absorb and reflect sound waves changes significantly. Especially when the dough gradually transforms from a low-gluten state to a high-gluten state with elasticity and extensibility, the change curves of the sonic reflectivity and acoustic impedance will exhibit obvious characteristics.

[0119] To ensure accurate judgment of the gluten formation process in the dough, the system uses data analysis algorithms to process the sonic reflection curve and combines machine learning models to identify the dough state at different stages. For example, at the initial stage of stirring, the reflectivity of the sound wave is low, indicating that the dough is still in an unformed stage and the gluten network has not been established. As stirring progresses, the gluten structure within the dough gradually forms, and the reflectivity begins to increase, showing certain periodic fluctuations. When the gluten network reaches the optimal state, that is, a stable elastic structure is formed, the change amplitude of the reflection curve tends to be stable, and at this time, it can be determined that the dough has reached the ideal gluten level.

[0120] When judging the gluten formation stage of the dough, the system dynamically adjusts the stirring force, rotation speed, and duration to optimize the final quality of the dough. For example, if the system detects that the gluten growth rate of the dough is relatively fast, the rotation speed can be appropriately reduced to avoid over-stirring resulting in gluten breakage. If the gluten growth of the dough is slow, the stirring force can be increased or the stirring time can be extended to ensure the full formation of the gluten network. In addition, the system can also switch to an intermittent stirring mode when the dough is approaching the optimal state, allowing the gluten to have sufficient time for self-regulation, thereby improving the taste of the final product.

[0121] When it is detected that the dough has reached the optimal gluten state, the system automatically terminates the stirring process and enters the next processing stage, such as fermentation, shaping, or baking. At the same time, the system sends a detailed dough state report to the remote terminal device. The report content includes the current gluten state of the dough, the recommended subsequent processing methods, and the adjustment options available to the user. The user can decide whether to manually adjust the next processing parameters based on the information in the report or let the system automatically execute the preset next operation. This real-time feedback mechanism not only improves the accuracy of dough making but also enables the user to more intuitively understand the dough making process, enhancing the controllability and intelligence level of the entire pastry making process.

[0122] This method uses acoustic detection technology to non - contact monitor the internal structure of the dough, overcoming the limitation that traditional mixers can only stir based on fixed time and speed. Compared with the existing technology, this method can adapt to different types of dough in real - time, precisely control the gluten - forming process, ensure that the final dough reaches the ideal state, thus improving the quality and consistency of pastries. At the same time, combined with remote monitoring and dynamic adjustment functions, this method not only simplifies the user's operation process, but also enables the mixer to achieve intelligent stirring optimization without human intervention, improving the overall cooking experience.

[0123] Furthermore, the intelligent remote control method of the mixer based on artificial intelligence analysis further includes:

[0124] Obtain data on the dietary preferences and nutritional needs of the user's family members through a remote terminal device, and establish a demand model for multiple family members;

[0125] When the user inputs the pastry - making requirements, based on the multi - member demand model, generate a partitioned production plan for the pastry, so that the pastries made in a single batch can meet the personalized needs of different members;

[0126] Control the mixer to perform intelligent segmented processing on the dough during the production process, and add different auxiliary materials, seasonings or nutritional fortifiers in different segments;

[0127] After the basic production of the dough is completed, provide pastry - shaping suggestions to the remote terminal device, including the combination method of different - component doughs, partition identification methods, and the optimal baking temperature, to meet the personalized needs of each family member.

[0128] In this embodiment, data on the dietary preferences and nutritional needs of the user's family members are obtained through a remote terminal device, and a demand model for multiple family members is established based on these data, enabling the mixer to perform intelligent pastry - making according to the needs of different family members. This method can not only improve the personalization degree of pastry - making, but also meet the different requirements of different members for taste, nutrition and health needs.

[0129] In the initial stage of system operation, users can input the basic dietary information of family members on remote terminal devices, including preferences for different ingredients, allergen information, specific health needs, and taste preferences. For example, some family members may prefer low-sugar and low-salt pastries, while others may prefer high-gluten dough with a chewy texture, or due to health reasons, need to reduce fat intake. The system will store this information and establish a personalized database, and at the same time, combine nutritional parameters to build a complete family dietary needs model. In addition, the system can be data-connected with intelligent health devices or health management applications, such as synchronizing health data such as blood sugar, blood pressure, and weight changes, so as to optimize the diet plan at any time and improve the accuracy of health management.

[0130] When the user inputs the pastry-making requirements, the system will calculate the best pastry-making plan suitable for the current family members based on the multi-member needs model of the family. This plan not only includes the basic recipe, but also details the ingredients, auxiliary materials, and ratios suitable for different members. For example, when making a batch of bread, the system may automatically generate a partition-making plan, that is, in the same basic dough, different ingredients are added to different dough partitions for different members. For example, a high-protein fortified flour is added to a certain area to meet the needs of fitness people, and the sugar content is reduced in another area to meet the dietary requirements of diabetic patients. Through intelligent calculation, the pastries made in a single time can meet the personalized needs of different family members, without the need to make multiple batches of dough separately, thereby improving efficiency and reducing food waste.

[0131] In the specific production process, the system will control the chef machine to perform intelligent segmented processing on the dough according to the partition-making plan. This means that the chef machine not only has to complete the traditional mixing and kneading process, but also needs to add auxiliary materials precisely at specific time points and specific dough areas. For example, in the first stage, the chef machine can perform unified mixing according to the basic recipe to ensure that all doughs reach the same basic state; in the second stage, the system will add different nutritional fortifying ingredients, seasonings, or auxiliary materials to different dough areas according to the needs model. For example, oat fiber is added to a certain part of the dough to increase the dietary fiber content, while milk powder is added to another part of the dough to enhance the milk flavor and protein content. The whole process is precisely controlled by the system, including the mixing time, the order of adding auxiliary materials, and the mixing method of different ingredients, to ensure that the dough in each area can meet its set taste and nutritional requirements.

[0132] After the basic production of the dough is completed, the system will also provide detailed suggestions for shaping the pastry to the remote terminal device. These suggestions include the combination methods of different ingredient doughs, enabling users to make zone identifications according to the recommended methods. For example, the system can recommend using marks of different colors or shapes to distinguish different dough areas, ensuring that different members can clearly identify their exclusive pastries during subsequent baking or steaming processes. In addition, the system will also give the optimal baking or steaming temperature according to the characteristics of different dough ingredients to ensure the best retention of the taste and nutritional components of the final product. For example, dough rich in protein may require a lower baking temperature to avoid protein denaturation, while dough rich in whole wheat flour may require a longer fermentation time and a higher baking temperature to ensure sufficient expansion effect.

[0133] The implementation of this system enables the dough mixer to further achieve the personalized customization ability of pastries on the basis of the traditional single-recipe production method, enabling different members to obtain pastries that meet their dietary needs during the same production process.

[0134] In the above embodiment, an intelligent remote control method for a dough mixer based on artificial intelligence analysis is provided. Correspondingly, the present application also provides an intelligent remote control system for a dough mixer based on artificial intelligence analysis. Please refer to Figure 2 , which is a schematic diagram of an embodiment of an intelligent remote control system for a dough mixer based on artificial intelligence analysis of the present application. Since this embodiment, that is, the second embodiment, is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The device embodiments described below are only illustrative.

[0135] The intelligent remote control system for a dough mixer based on artificial intelligence analysis includes:

[0136] A remote terminal device 201, configured to receive an operation instruction input by a user, where the operation instruction includes start, stop, speed adjustment, stirring time, and mode selection;

[0137] A dough mixer body 202, including: a built-in camera for acquiring image information of the ingredients in the dough mixer; a weight sensor for acquiring the weight information of the ingredients; a group of operating state sensors for real-time monitoring of the operating state of the dough mixer; an actuator for performing stirring and kneading operations according to a control instruction;

[0138] An artificial intelligence processing unit 203, configured to analyze the types, quantities, and mixing states of ingredients based on a pre-trained neural network model, and generate ingredient processing parameters; combine the operation instructions input by the user, the ingredient processing parameters, and a preset recipe database to determine the mixing mode, rotation speed, and running time of the cooking machine, and generate control instructions; when detecting overload, abnormal ingredient mixing, or abnormal operation, analyze the cause of the abnormality and generate corresponding adjustment strategies.

[0139] A wireless communication module 204, configured to send the control instructions from the artificial intelligence processing unit to the actuator of the cooking machine; transmit the running state of the cooking machine, the progress of ingredient mixing, and the recommended adjustment plan to a remote terminal device in real time.

[0140] A cloud server 205, configured to store a preset recipe database, historical operation data, and user personal settings, and provide data backup and synchronization services.

[0141] The third embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps provided in the first embodiment of the present application are implemented.

[0142] Although the present application is disclosed above with preferred embodiments, it is not intended to limit the present application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application should be defined by the scope of the claims of the present application.

Claims

1. An intelligent remote control method for a chef machine based on artificial intelligence analysis, characterized in that: include: Receive operation instructions input by the user through the remote terminal device, wherein the operation instructions include starting, stopping, adjusting the speed, stirring time and mode selection; The built-in camera and sensor are used to obtain the image and weight information of the ingredients in the food processor, and the type, quantity and mixing status of the ingredients are analyzed based on the pre-trained neural network model to generate the ingredient processing parameters; Determine the mixing mode, speed and running time of the food processor in combination with the operation instructions input by the user, the food processing parameters and the preset recipe database, and generate control instructions; The generated control instructions are sent to the chef machine for execution, and the operating status is monitored through sensors, and the operation progress and abnormal information are fed back to the remote terminal device in real time; When overload, abnormal food mixing or abnormal operation is detected, the cause of the abnormality is analyzed and the corresponding adjustment strategy is executed, including adjusting the speed, modifying the operating mode or prompting the user to intervene. At the same time, the operating status of the food processor, the progress of food mixing and the recommended adjustment plan are pushed to the remote terminal device.

2. The intelligent remote control method for a chef machine based on artificial intelligence analysis according to claim 1, characterized in that: Also includes: Build a personalized pastry making model based on the user's historical operation data, seasonal preferences and regional characteristics; When the user inputs the type of pastry, the production parameters are adjusted according to the personalized pastry production model, including the ratio of flour to liquid, proofing time, kneading intensity and stirring speed; The production parameters are adjusted for health optimization based on the user's physiological state recorded by the remote terminal device, wherein the physiological state includes blood sugar level, blood pressure value and blood lipid index; According to the physiological state, the amount of sugar added, the type of flour selected, and the amount of oil used in pastry making are automatically adjusted, and production suggestions for low-sugar, low-salt, or low-fat alternative options are provided on the remote terminal device.

3. The intelligent remote control method for a chef machine based on artificial intelligence analysis according to claim 1, characterized in that: Also includes: A multi-band sound wave generator is installed in the kitchen machine to emit sound waves of specific frequencies during the mixing and kneading process according to the physical characteristics of different pastries; Real-time monitoring of the acoustic wave reflection characteristics of the dough through an acoustic wave sensor; Based on the changing curve of the sound wave reflection characteristics, the dough gluten formation stage is judged, and the stirring intensity, speed and duration are adjusted accordingly; When it is detected that the dough has reached the optimal gluten state, it enters the next processing stage and sends a dough status report to the remote terminal device.

4. The intelligent remote control method for a chef machine based on artificial intelligence analysis according to claim 1, characterized in that: Also includes: Obtain dietary preferences and nutritional needs data of user family members through remote terminal devices, and establish a demand model for multiple family members; When the user inputs the demand for making pastries, a partitioned making plan for pastries is generated based on the multi-member demand model, so that the pastries made at a time can meet the personalized needs of different members; Control the chef machine to process the dough in intelligent sections according to the zoning production plan during the production process, and add different auxiliary materials, seasonings or nutritional fortification ingredients in different sections; After completing the basic dough production, it provides pastry forming suggestions to the remote terminal device, including the combination of doughs with different ingredients, the partition identification method and the optimal baking temperature to meet the personalized needs of each family member.

5. The intelligent remote control method for a chef machine based on artificial intelligence analysis according to claim 1, characterized in that: The neural network model includes a food identification module, a mixed state evaluation module and a food processing parameter generation module; Among them, the food identification module is used to identify and estimate the type, quantity and preliminary mixing ratio of the food. The input of the food identification module is the food image data collected by the camera and the weight data collected by the weight sensor, and the output is the food type, weight parameter, preliminary mixing ratio and solid-liquid content estimation value; the food identification module adopts a dual-channel convolutional neural network architecture, in which the first channel is used to process image data, and the color, shape and edge information of the food are extracted through multi-layer convolution, pooling and fully connected layers. The second channel is used to process weight data and match the known food density features based on the statistical model; the image features and weight information are combined through the feature fusion layer to output the classification and preliminary ratio estimation of the food. The mixing state evaluation module is used to analyze the mixing state of dough or ingredients during the operation of the chef machine. The input of the mixing state evaluation module is the continuous frame image data collected by the camera and the real-time torque data collected by the torque sensor, and the output is the mixing uniformity score, the gluten network formation state and the real-time state parameters during the mixing process; wherein, the mixing state evaluation module adopts a temporal convolutional network combined with a long short-term memory network for analysis, the temporal convolutional network is used to extract the distribution change characteristics of ingredients in the continuous frame images and calculate the change trend of the dough structure, the long short-term memory network is used to analyze the change pattern of the torque data to determine the degree of gluten network formation during the mixing process, and calculate the mixing uniformity score and other parameters characterizing the dough state based on the set uniformity threshold; The food processing parameter generation module is used to generate final food processing parameters based on the output data of the food identification module and the mixing state evaluation module; the input of the food processing parameter generation module is the type of food, weight parameter, preliminary mixing ratio, estimated solid-liquid content, mixing uniformity score and gluten network formation state, and the output is the food processing parameters; wherein, the food processing parameter generation module adopts a multi-layer perceptron structure, and after the input data is normalized, the final food processing parameters are generated through multi-layer nonlinear mapping; the food processing parameters include recommended mixing time, stirring speed, required additional liquid or solid component amount and food mixing adjustment suggestions.

6. The intelligent remote control method for a chef machine based on artificial intelligence analysis according to claim 1, characterized in that: The mixing state evaluation module includes a dynamic torque uniformity optimization calculation unit, which calculates the mixing uniformity score according to the following formula 1 based on real-time torque data, dough surface change parameters collected by the camera, and gluten network formation state: Where U is the mixing uniformity score, ranging from [0,1]; N is the number of time steps for torque sensor sampling; T i represents the torque value at the i-th time step; T i-1 represents the torque value at the i-1th time step; M is the number of image frames captured by the camera; V j V represents the surface feature distribution uniformity score of the j-th frame image, which is calculated by the image analysis module based on the food distribution histogram and reflects the smoothness of the dough surface and the material distribution; j-1 represents the surface feature distribution uniformity score of the j-1th frame image; R is the degree of gluten network formation, which is calculated by the long short-term memory network and reflects the formation state of the elastic structure inside the dough; α, β, γ, and λ are empirical optimization parameters; The dynamic torque uniformity optimization calculation unit automatically adjusts the stirring mode, rotation speed and stirring time based on the calculated mixing uniformity score when the uniformity score is lower than a set threshold, and provides optimization suggestions.

7. The intelligent remote control method for a chef machine based on artificial intelligence analysis according to claim 1, characterized in that: The step of combining the operation instruction input by the user, the food processing parameters and the preset recipe database to determine the mixing mode, speed and running time of the food processor includes: Based on the recommended mixing time and stirring speed in the food processing parameters, the closest standard recipe parameters are matched in the preset recipe database, and combined with the operation instructions input by the user, the difference between the currently set stirring mode and the recommended mode is compared. If the user does not set custom parameters, the recommended parameters are directly used; if the user sets a different stirring time or speed, the impact of the parameter adjustment on the food mixing effect is calculated, and optional optimization suggestions are provided on the remote terminal device; Before executing the mixing mode, the viscosity, fluidity and structure of the dough or food mixture are dynamically evaluated in combination with the required amount of additional liquid or solid components in the food processing parameters, and the timing of adding liquid or solid is adjusted according to real-time sensor data during the mixing process, so that high-viscosity dough is supplemented with liquid at the appropriate stage and low-viscosity dough is supplemented with solid powder at the designated stage, so as to ensure the optimal plasticity and mixing uniformity of the dough.

8. The intelligent remote control method for a chef machine based on artificial intelligence analysis according to claim 1, characterized in that: When an overload, abnormal food mixing or abnormal operation is detected, the cause of the abnormality is analyzed and a corresponding adjustment strategy is executed, including: Based on the data from the torque sensor, camera and pressure sensor, the abnormality type is identified and it is determined whether it is torque overload, uneven stirring or abnormal food adhesion. In case of torque overload, the stirring speed is reduced and the stirring mode is adjusted to reduce resistance; in case of uneven stirring, the stirring time is extended or a low-speed mixing stage is added; in case of abnormal food adhesion, the stirring trajectory is adjusted or the container vibration is increased to improve the mixing state; Push adjustment plans to remote terminal devices, allowing users to manually intervene or confirm automatic optimization.

9. An intelligent remote control system for a chef machine based on artificial intelligence analysis, characterized in that: include: A remote terminal device, used to receive operation instructions input by a user, wherein the operation instructions include starting, stopping, adjusting the rotation speed, stirring time and mode selection; The main body of the food processor includes: a built-in camera for obtaining image information of the food in the food processor; a weight sensor for obtaining weight information of the food; an operation status sensor group for real-time monitoring of the operation status of the food processor; and an actuator for performing mixing and kneading operations according to control instructions; The artificial intelligence processing unit is used to analyze the type, quantity and mixing state of ingredients based on a pre-trained neural network model and generate ingredient processing parameters; determine the mixing mode, speed and running time of the food processor in combination with the operation instructions input by the user, the ingredient processing parameters and the preset recipe database, and generate control instructions; when an overload, abnormal ingredient mixing or abnormal operation is detected, analyze the cause of the abnormality and generate a corresponding adjustment strategy; A wireless communication module is used to send control instructions from the artificial intelligence processing unit to the chef machine actuator; and transmit the chef machine operating status, ingredient mixing progress and recommended adjustment plans to the remote terminal device in real time; The cloud server is used to store the preset recipe database, historical operation data and user personalized settings, and provide data backup and synchronization services.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the content of any one of claims 1 to 8 is implemented.

Images