Artificial intelligence rice heating and cooking auxiliary system

Abstract

The invention discloses an artificial intelligent rice heating and cooking auxiliary system. Food pictures are input through an external camera or a file system, picture features are extracted through a deep learning convolutional neural network, then the accurate heating time of food on a stove is predicted through two-stage regression, and manual estimation is replaced. The method has the beneficial effects that the method can be operated on equipment with limited computing power, such as mobile computing equipment and kitchen appliances, and can accurately predict rice heating and cooking time so as to assist in cooking, improve life efficiency, improve dining experience, protect environment cleanness and improve use safety.

Description

Technical Field

[0001] The invention relates to the field of artificial intelligence home technology, and in particular to an artificial intelligence rice heating and cooking auxiliary system. Background Art

[0002] With the development of artificial intelligence home technology, people's requirements for quality of life and safety are increasing.

[0003] The food heating and cooking temperature control equipment currently used on the market have the following problems: 1. It is not possible to quickly, accurately, and conveniently intelligently estimate the heating time of different types of food to assist in heating and cooking food; 2. Some rely on users to manually estimate and control time and temperature, which makes use inconvenient and the experience unsatisfactory; 3. Some rely on traditional detectors, such as infrared radiation detectors, and some rely on remote servers for auxiliary calculations, which are costly and not conducive to popularization; 4. Some AI estimation algorithms use overly simple technical solutions, are not accurate enough, have low efficiency, or have redundant algorithms, and need to be improved; 5. There is no similar artificial intelligence device on the market that can estimate time and assist in heating and cooking.

[0004] Specifically, A rapeseed oil heating time prediction system and method, patent number: CN112766187A Methods: The VGG16 convolutional neural network was used to extract the image features of the rapeseed oil to be processed, and then the color difference was compared with the standard rapeseed oil image. The SVR support vector regression algorithm was used to predict the time to heat to the standard rapeseed oil color. Disadvantages: The VGG16 convolutional neural network is very deep. For devices with limited computing power such as mobile computing devices, home appliances or kitchen appliances, it may have high hardware requirements and increase costs. Moreover, the VGG16 convolutional neural network is a general-purpose pattern recognition model. It is not flexible enough for specific application scenarios such as food pictures. There is room for optimization, speed-up and energy reduction. In addition, this system relies on standard rapeseed oil pictures and only performs color comparison. However, the types of food heating are complicated and have many features. Generally, there are no finished product comparison pictures. In addition, the SVR model of regression prediction used in the system can also be considered to be replaced by polynomial regression. The SVR model will require more computing power, increase hardware costs and energy consumption, and this system is not designed for heating and cooking daily food.

[0005] A vehicle-mounted intelligent lunch box intelligent temperature control method and system, patent number: CN118349048A Method: The camera, temperature sensor, weight sensor and remote server in the on-board smart lunch box are used to classify meat and vegetarian dishes to estimate the heating time of the overall type of food in the smart lunch box, and intelligently control the heat preservation or heating; Disadvantages: Using multiple sensors other than cameras and remote servers to estimate food heating time is costly. In addition, the Fast R-CNN algorithm is not optimized for food image scenes and is not flexible enough. The algorithm only roughly classifies food types into meat and vegetarian dishes, and cannot directly and accurately estimate the heating time. It is only used for heating smart lunch boxes on trucks, so its application scope is limited.

[0006] Intelligent temperature control system for efficient electromagnetic cookers, patent number: CN115789717A Method: By monitoring the vibration of the boiling liquid food in the pot, the heating temperature of the stove can be controlled to prevent overflow; Disadvantages: It is only used to heat porridge, soup and other liquid foods that need to be heated to boiling. The applicable scenarios are limited, and the temperature adjustment will only be triggered after the boiling food produces vibrations for a period of time, which is not safe and clean enough.

[0007] Food heating temperature control methods on the market: Using thermal infrared sensor probes, thermosensitive elements, vibration frequency monitors, smart cameras, remote server-assisted computing, and overly simple graphic recognition algorithms to keep food warm or heat it; Disadvantages: It cannot intelligently and accurately estimate the heating time of food of different types, ingredients and initial temperatures to assist in heating and cooking, and its applicable scenarios are limited. In addition, some detection components and equipment are expensive and cannot be popularized in households. Some of the intelligent estimation algorithms used are not optimized for the application scenarios of heating and cooking daily food. Summary of the invention

[0008] The purpose of the present invention is to provide an artificial intelligence rice heating and cooking assistance system, which can run an optimized deep learning graphic feature extraction algorithm on a mobile computing device, a household appliance or a kitchen appliance with limited computing power, extract features in food pictures, and accurately estimate the heating time through a two-stage regression prediction algorithm, replacing manual estimation, so as to assist users in heating and cooking rice and provide convenience in life.

[0009] To achieve the above object, the present invention adopts the following technical solutions: An artificial intelligence rice heating and cooking auxiliary system, comprising: S1: External input, accepting food pictures, stove heating power values ​​and target dining temperature values; S2: Convolutional neural network module, used to preliminarily estimate the energy required to heat food, which is the first stage prediction; S3: Accurate heating time estimation module, used to accurately estimate the food heating time, which is the second stage prediction; The artificial intelligence rice heating and cooking auxiliary system receives food pictures input from an external camera or file system, uses a deep learning convolutional neural network to extract picture features, and regressively predicts the energy value required to heat the food to a predefined fixed temperature. This is the first stage prediction. Then, this value, the heating power of the stove, and the target dining temperature are used as inputs to perform the second stage prediction. The regression prediction finally feeds back the precise heating time to the user to assist in heating and cooking rice. Furthermore, in step S1, the external input includes: S101: A picture of food to be heated or cooked is inputted from an external camera or a file system. The picture should have good clarity and illumination, because in real life, the human eye can distinguish the surface composition of food and its initial temperature range, and can estimate the heating time of food. For example, the food may be at room temperature or frozen and have different combinations and proportions of meat, vegetables, soup, rice and noodles, etc. The input picture can provide information in this regard; S102: The heating power of the stove. For example, a microwave oven has power options such as high, medium and low, and these settings need to be referenced to accurately estimate the heating time; S103: Target dining temperature. When using a stove to defrost, heat rice, boil water or cook noodles, there will be different target temperatures. You also need to refer to this part of the settings to accurately estimate the heating time to achieve the best dining experience, ensure a clean environment and safe use; Furthermore, in step S2, the convolutional neural network module includes: S201: one or more convolutional layers, using the food image as input to extract features from the image. The convolutional layer can cooperate with the pooling layer to compress the data dimension and improve the operation effect and efficiency. It can also cooperate with the Dropout layer to prevent overfitting and enhance robustness. This type of deep learning algorithm runs fast, has high recognition accuracy, can achieve real-time detection, and can also run on frameworks such as Tensorflow Lite or PyTorch Mobile. It supports mobile, ultra-small devices, household appliances and kitchen appliances with limited computing power, which can reduce equipment costs and energy consumption; S202: one or more fully connected layers, and finally output a value. This step is used to accept the input of the convolution layer, regress and predict the energy value required to heat the food to a predefined fixed temperature. For example, heating to 40 degrees Celsius requires 0.033 kWh. At this time, it is only related to the initial temperature and composition of the food, and has nothing to do with the heating power of the stove and the user's target heating temperature. Therefore, information can be obtained only from the food picture; Furthermore, in step S3, the accurate heating time estimation module includes: S301: A regression prediction algorithm uses the output value of the convolutional neural network module and the values ​​of the stove heating power and the target dining temperature as inputs, and regressively predicts the precise heating time that meets the user's expectations and is suitable for the current stove, and can continue to output this value to the digital stove, or prompt the user in the form of a display screen, voice, etc.; Furthermore, the convolutional neural network deep learning model needs to prepare a data set for pre-training. The data set should include pictures of multiple categories of food with uniform specifications and annotate the energy value required to heat the food to a predefined fixed temperature. For example, kilowatt-hours can be used for measurement. This value is the overall energy value and has nothing to do with the performance of the specific stove, but is related to the predefined heating temperature and has nothing to do with the user's target heating temperature. Furthermore, the regression prediction algorithm may use models such as Polynomial Regression and Support Vector Machine. Such algorithms have fast running speed, high prediction accuracy, and mature algorithms. They can be run on frameworks such as Tensorflow Lite or PyTorch Mobile, and can be used on mobile, ultra-small devices, household appliances, and kitchen appliances with limited computing power, which can reduce equipment costs, reduce energy consumption, facilitate daily use by users, and use smaller training data sets. Furthermore, the model of the regression prediction algorithm also needs to prepare a data set for pre-training. The data set should include the energy value output by the convolutional neural network module to predict the energy required to heat food to a certain fixed temperature, as well as different stove heating power values, target dining temperature values, and the actual heating time obtained from manual experiments in this scenario.

[0010] Beneficial effects of the present invention: 1. The deep learning algorithm used does not put much pressure on modern software and hardware, can run on devices with limited computing power, has a fast speed, consumes little energy, can recognize in real time, and can be used in mobile devices, ultra-small devices, home appliances or kitchen appliances to achieve low cost and convenient daily use; 2. The recognition and estimation accuracy is high, which can avoid the errors caused by manual estimation and operation, help users heat and cook food successfully in one go, reduce the time wasted due to manual errors and the need for multiple heating, and improve life efficiency; 3. It can avoid the degradation of dining experience, environmental pollution, and safety and health risks caused by overheating; 4. If combined with remote control and time control systems, remote, timed automation and even unmanned operation can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a work flow chart of the present invention; Figure 2 It is a schematic diagram of an application scenario of the present invention. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0013] In the description of the embodiments of the present invention, it should be noted that if the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, or the orientation or position relationship in which the invented product is usually placed when used. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0014] In addition, the terms "horizontal", "vertical", "overhanging" and the like do not mean that the components must be absolutely horizontal or overhanging, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0015] In the description of the embodiments of the present invention, "plurality" means at least 2.

[0016] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. Example

[0017] An artificial intelligence rice heating and cooking auxiliary system.

[0018] System composition: 1. External input, accepting food pictures, stove heating power values ​​and target dining temperature values; 2. Convolutional neural network module, used to preliminarily estimate the energy required to heat food, which is the first stage of prediction; 3. Accurate heating time estimation module, which is used to accurately estimate the food heating time. This is the second stage prediction.

[0019] Working principle: The artificial intelligence rice heating and cooking assistance system accepts food pictures input by an external camera or file system, uses a deep learning convolutional neural network to extract picture features, and regressively predicts the energy value required to heat the food to a predefined fixed temperature. This is the first stage prediction. This value, the heating power of the stove, and the target dining temperature are then used as inputs for the second stage prediction. The regression prediction ultimately feeds back the precise heating time to the user to assist in heating and cooking rice.

[0020] Specifically: An artificial intelligence rice heating and cooking auxiliary system, comprising: S1: External input, accepting food pictures, stove heating power values ​​and target dining temperature values; S2: Convolutional neural network module, used to preliminarily estimate the energy required to heat food, which is the first stage prediction; S3: Accurate heating time estimation module, used to accurately estimate the food heating time, which is the second stage prediction; The artificial intelligence rice heating and cooking auxiliary system receives food pictures input from an external camera or file system, uses a deep learning convolutional neural network to extract picture features, and regressively predicts the energy value required to heat the food to a predefined fixed temperature. This is the first stage prediction. Then, this value, the heating power of the stove, and the target dining temperature are used as inputs to perform the second stage prediction. The regression prediction finally feeds back the precise heating time to the user to assist in heating and cooking rice. In this embodiment, the external input in step S1 includes: S101: A picture of food to be heated or cooked is inputted from an external camera or a file system. The picture should have good clarity and illumination, because in real life, the human eye can distinguish the surface composition of food and its initial temperature range, and can estimate the heating time of food. For example, the food may be at room temperature or frozen and have different combinations and proportions of meat, vegetables, soup, rice and noodles, etc. The input picture can provide information in this regard; S102: The heating power of the stove. For example, a microwave oven has power options such as high, medium and low, and these settings need to be referenced to accurately estimate the heating time; S103: Target dining temperature. When using a stove to defrost, heat rice, boil water or cook noodles, there will be different target temperatures. You also need to refer to this part of the settings to accurately estimate the heating time to achieve the best dining experience, ensure a clean environment and safe use; In this embodiment, the convolutional neural network module in step S2 includes: S201: one or more convolutional layers, using the food image as input to extract features from the image. The convolutional layer can cooperate with the pooling layer to compress the data dimension and improve the operation effect and efficiency. It can also cooperate with the Dropout layer to prevent overfitting and enhance robustness. This type of deep learning algorithm runs fast, has high recognition accuracy, can achieve real-time detection, and can also run on frameworks such as Tensorflow Lite or PyTorch Mobile. It supports mobile, ultra-small devices, household appliances and kitchen appliances with limited computing power, which can reduce equipment costs and energy consumption; S202: one or more fully connected layers, and finally output a value. This step is used to accept the input of the convolution layer, regress and predict the energy value required to heat the food to a predefined fixed temperature. For example, heating to 40 degrees Celsius requires 0.033 kWh. At this time, it is only related to the initial temperature and composition of the food, and has nothing to do with the heating power of the stove and the user's target heating temperature. Therefore, information can be obtained only from the food picture; In this embodiment, the accurate heating time estimation module in step S3 includes: S301: A regression prediction algorithm uses the output value of the convolutional neural network module and the values ​​of the stove heating power and the target dining temperature as inputs, and regressively predicts the precise heating time that meets the user's expectations and is suitable for the current stove, and can continue to output this value to the digital stove, or prompt the user in the form of a display screen, voice, etc.; In this embodiment, the convolutional neural network deep learning model needs to prepare a data set for pre-training. The data set should include pictures of multiple categories of food with uniform specifications and annotate the energy value required to heat the food to a predefined fixed temperature. For example, kilowatt-hours can be used for measurement. This value is the overall energy value and has nothing to do with the performance of the specific stove, but is related to the predefined heating temperature and has nothing to do with the user's target heating temperature. In this embodiment, the regression prediction algorithm may use models such as Polynomial Regression and Support Vector Machine. Such algorithms have fast running speed, high prediction accuracy, and mature algorithms. They can be run on frameworks such as Tensorflow Lite or PyTorch Mobile, and can be used on mobile, ultra-small devices, household appliances, and kitchen appliances with limited computing power, which can reduce device costs, reduce energy consumption, facilitate daily use by users, and use smaller training data sets. In this embodiment, the model of the regression prediction algorithm also needs to prepare a data set for pre-training. The data set should include the energy value output by the convolutional neural network module to predict the energy required to heat food to a certain fixed temperature, as well as different stove heating power values, target dining temperature values, and the actual heating time obtained by manual experiments in this scenario.

[0021] in, The calculation part of image feature extraction and heating time estimation can be completed with Prompt using the AI ​​big model; The advantages are: low development difficulty, only using natural language to write applicable prompts, and building and calling large model services, but it requires high computing power of the device, and has too high hardware requirements for mobile devices, ultra-small devices, home appliances and kitchen appliances, high cost, large computing delay, and high energy consumption; It is also possible to transmit food pictures to a cloud service provider through an integrated Internet access module, and call the cloud AI big model service to complete the image feature extraction and heating time estimation described in this system; The advantages are: it does not require high hardware for mobile devices, ultra-small devices, household appliances, and kitchen appliances, and the software development is not difficult. However, it is necessary to add hardware and software modules for Internet access to the devices, which will lead to high manufacturing, development, maintenance and operation costs. It also requires the user's location to have Internet access, and the user needs to manually perform additional configuration, which increases the cost and difficulty of use. There may also be large delays and unstable services. In addition, there will be problems with user data and privacy security. Another improvement is to omit the external input of the stove heating power and the target dining temperature in the precise heating time estimation module, because the common electronic stoves on the market, such as microwave ovens, have only a few power options such as high fire, medium fire and low fire, and the target heating temperature can also be pre-defined with a few options commonly used by users, such as 37 degrees Celsius, 40 degrees, 60 degrees and 100 degrees. Their combination can be calculated all at once, and the user can select it with one click or reuse the user's historical selection preference record; The advantages are: it can further reduce the complexity of user operations, but it will lead to an increase in the complexity of user interface design and software system design, and may have problems such as practicality and practicability not conforming to users' actual usage habits. It will also limit users' freedom of choice and there may be safety risks in use.

[0022] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. An artificial intelligence rice heating and cooking auxiliary system, characterized in that: include: S1: External input, accepting food pictures, stove heating power values ​​and target dining temperature values; S2: Convolutional neural network module, used to preliminarily estimate the energy required to heat food, which is the first stage prediction; S3: Accurate heating time estimation module, used to accurately estimate the food heating time, which is the second stage prediction; The artificial intelligence rice heating and cooking assistance system accepts food pictures input by an external camera or file system, uses a deep learning convolutional neural network to extract picture features, and regressively predicts the energy value required to heat the food to a predefined fixed temperature. This is the first stage prediction. This value, the heating power of the stove, and the target dining temperature are then used as inputs for the second stage prediction. The regression prediction ultimately feeds back the precise heating time to the user to assist in heating and cooking rice.

2. The artificial intelligence rice heating and cooking auxiliary system according to claim 1 is characterized in that: In step S1, the external input includes: S101: A picture of food to be heated or cooked is inputted from an external camera or a file system. The picture should have good clarity and illumination, because in real life, the human eye can distinguish the surface composition of food and its initial temperature range, and can estimate the heating time of food. For example, the food may be at room temperature or frozen and have different combinations and proportions of meat, vegetables, soup, rice and noodles, etc. The input picture can provide information in this regard; S102: The heating power of the stove. For example, a microwave oven has power options such as high, medium and low, and these settings need to be referenced to accurately estimate the heating time; S103: Target dining temperature. There will be different target temperatures when using the stove to defrost, heat rice, boil water or cook noodles. You also need to refer to this part of the settings to accurately estimate the heating time to achieve the best dining experience, ensure a clean environment and safe use.

3. The artificial intelligence rice heating and cooking auxiliary system according to claim 1 is characterized in that: In step S2, the convolutional neural network module includes: S201: one or more convolutional layers, using the food image as input to extract features from the image. The convolutional layer can cooperate with the pooling layer to compress the data dimension and improve the operation effect and efficiency. It can also cooperate with the Dropout layer to prevent overfitting and enhance robustness. This type of deep learning algorithm runs fast, has high recognition accuracy, can achieve real-time detection, and can also run on frameworks such as Tensorflow Lite or PyTorch Mobile. It supports mobile, ultra-small devices, household appliances and kitchen appliances with limited computing power, which can reduce equipment costs and energy consumption; S202: One or more fully connected layers, and finally output a value. This step is used to accept the input of the convolutional layer and regressively predict the energy value required to heat the food to a predefined fixed temperature. For example, heating to 40 degrees Celsius requires 0.033 kWh. At this time, it is only related to the initial temperature and composition of the food, and has nothing to do with the heating power of the stove and the user's target heating temperature, so information can be obtained only from the food picture.

4. The artificial intelligence rice heating and cooking auxiliary system according to claim 1, characterized in that: In step S3, the accurate heating time estimation module includes: S301: A regression prediction algorithm uses the output value of the convolutional neural network module and the values ​​of the stove heating power and target dining temperature as inputs. The regression prediction meets the user's expectations and is suitable for the precise heating time of the current stove. This value can be continuously output to the digital stove, or the user can be prompted in the form of a display screen, voice, etc.

5. The artificial intelligence rice heating and cooking auxiliary system according to claim 3 is characterized in that: The convolutional neural network deep learning model requires a data set for pre-training. The data set should include multi-category food images of uniform specifications and annotate the energy value required to heat the food to a predefined fixed temperature. For example, kilowatt-hours can be used for measurement. This value is the overall energy value and has nothing to do with the performance of the specific stove, but is related to the predefined heating temperature and has nothing to do with the user's target heating temperature.

6. The artificial intelligence rice heating and cooking auxiliary system according to claim 4, characterized in that: The regression prediction algorithm can use models such as Polynomial Regression and Support Vector Machine. Such algorithms have fast running speed, high prediction accuracy, and mature algorithms. They can be run on frameworks such as Tensorflow Lite or PyTorchMobile, and can be used on mobile, ultra-small devices, household appliances, and kitchen appliances with limited computing power. They can reduce equipment costs, reduce energy consumption, facilitate users' daily use, and use smaller training data sets.

7. The artificial intelligence rice heating and cooking auxiliary system according to claim 4, characterized in that: The model of the regression prediction algorithm also needs to prepare a data set for pre-training. The data set should include the energy value output by the convolutional neural network module to predict the energy required to heat food to a certain fixed temperature, as well as different stove heating power values, target dining temperature values, and the actual heating time obtained from manual experiments in this scenario.

Images