Control method and system of intelligent electric cooker based on Internet of Things

Abstract

The invention relates to the technical field of intelligent control, in particular to an intelligent electric cooker control method and system based on the Internet of Things, and the method comprises the steps: obtaining instruction information remotely sent by a user, and converting the instruction information into coded information; the method comprises the following steps: acquiring type information and weight information of food in an intelligent electric cooker, fusing the type information and the weight information of the food to obtain a plurality of gene sequences, and taking a plurality of genes in the sequences as preferable genes; randomly modifying the value of a preferred gene in a preset range, and performing fitness evaluation on the modified gene sequence in combination with the coding information until an optimal gene sequence is obtained; and converting the optimal gene sequence into a cooking control instruction, and controlling the intelligent electric cooker to perform cooking operation according to the cooking control instruction. According to the method and the device, the optimal cooking scheme is automatically generated and selected by analyzing the user instruction, identifying the type and the weight of the food materials and adopting gene sequence optimization and fitness evaluation, so that personalized and intelligent cooking experience is realized, and the use experience of the user is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a control method and system for an intelligent rice cooker based on the Internet of Things. Background Art

[0002] With the rapid development of Internet of Things technology, smart home appliances have gradually entered thousands of households, especially smart rice cookers have been widely used in modern kitchens. Existing smart rice cookers mostly rely on simple automation programs such as timing and temperature control. Users select the corresponding cooking method through the touch screen or preset mode, and the system controls the cooking according to simple parameters.

[0003] However, these existing control methods cannot be fine-tuned according to the real-time needs of users, especially under complex ingredients or diverse cooking requirements, and existing technologies often cannot provide personalized and optimized cooking solutions. Although modern smart rice cookers can perform a certain degree of automatic adjustment, the existing control logic is mostly based on preset cooking programs, lacking flexibility and adaptability. Especially when the user issues a remote command, the response of the rice cooker is limited to starting, stopping or switching to a preset mode, and fails to optimize the control strategy according to the type and weight of the ingredients, as well as the real-time changes in the cooking environment. This control method is too simplified and difficult to meet the user's growing expectations for cooking accuracy and personalized needs.

[0004] For example, when a user uses a smart rice cooker to cook, even if the "porridge cooking" mode is selected, if the type and weight of the ingredients are different, the rice cooker cannot automatically adjust the appropriate temperature and time, and the porridge is often too thin or too dry; or when the user wants to cook a special portion of rice, the traditional smart rice cooker cannot automatically adjust the parameters according to factors such as the type, weight, and humidity of the rice, resulting in the cooking effect being difficult to achieve the best state. This mode limitation makes the user experience poor and unable to enjoy the personalized services brought by smart home appliances. Summary of the invention

[0005] The main purpose of the present invention is to provide a control method and system for an intelligent rice cooker based on the Internet of Things, aiming to overcome the defect that the prior art cannot perform fine adjustment according to the real-time needs of users.

[0006] In order to achieve the above-mentioned invention problem, the present invention proposes a control method of an intelligent rice cooker based on the Internet of Things, the method comprising: Acquire instruction information sent remotely by a user, identify a mode flag contained in the instruction information, and convert the mode flag into coded information; Acquire image information of food in the smart rice cooker based on a collection sensor in the smart rice cooker, identify the image information to obtain type information of the food, and acquire weight information of the food based on a pressure sensor; The food type information and the weight information are merged to obtain a plurality of gene sequences, wherein each gene sequence is a cooking scheme, and each gene in the gene sequence is a parameter in the cooking scheme; Mapping the target values ​​of the multiple genes included in the gene sequence to a preset interval, obtaining the fitness value of each of the genes based on the encoding information, sorting the multiple genes according to the fitness values, and selecting the genes with fitness higher than the preset value as preferred genes; Randomly modify the value of one of the preferred genes within a preset range, and perform fitness evaluation on the modified gene sequence in combination with the coding information until the optimal gene sequence is obtained; The optimal gene sequence is converted into a cooking control instruction, and the intelligent rice cooker is controlled to perform a cooking operation according to the cooking control instruction.

[0007] Furthermore, the step of acquiring the instruction information sent remotely by the user, identifying the mode flag contained in the instruction information, and converting the mode flag into coded information includes: Parse and process the command information sent remotely by the user to obtain the original data of the command information; Performing pattern recognition processing on the original data according to the format of the instruction information, extracting the pattern flag contained in the original data, and obtaining pattern flag data; Classifying the flag type according to the mode flag data, and determining the cooking mode corresponding to the mode flag according to a preset rule table, wherein the preset rule table includes a correspondence between a plurality of preset cooking modes and mode flags; Converting the cooking mode into unique coding information according to a preset coding table, wherein each cooking mode in the preset coding table corresponds to a specific identifier; The unique coding information is subjected to data compression processing, and the unique coding information is compressed according to a compression algorithm to obtain optimized and stored coding information.

[0008] Furthermore, the step of acquiring image information of food in the smart rice cooker based on an acquisition sensor in the smart rice cooker, identifying the image information to obtain type information of the food, and acquiring weight information of the food based on a pressure sensor includes: Acquire an image of food in the smart rice cooker according to an acquisition sensor in the smart rice cooker, and denoise the image using a Gaussian filter algorithm to obtain a denoised image; Performing target detection on the denoised image based on a regional convolutional neural network, outputting regional coordinates and confidence of the food, and generating a food regional image based on the regional coordinates and confidence of the food; Extracting features from the food region image to obtain surface feature information of the food, matching and clustering the feature information to obtain a unique surface feature descriptor for each food; Comparing the unique surface feature descriptor with food features stored in a database to obtain type information of the food; The weight data of the food is obtained according to the pressure sensor in the smart rice cooker, and the weight data is A / D converted to obtain the weight information of the food.

[0009] Furthermore, the step of fusing the food type information with the weight information to obtain a plurality of gene sequences, wherein each gene sequence is a cooking scheme, and each gene in the gene sequence is a parameter in the cooking scheme, comprises: Extracting features of the food type information and the food weight information respectively to obtain a type parameter feature set and a weight parameter feature set; Extracting each of the food type parameter feature set and weight parameter feature set for weighted synthesis to obtain a fusion weight value, and performing dimensionality reduction processing on the fusion weight value through a principal component analysis algorithm to obtain a low-dimensional feature vector; Normalizing the type information and weight information of the food based on the feature vector to obtain a standardized feature representation; The standardized feature representation is genetically encoded, wherein each genetic code corresponds to a cooking parameter, and multiple genetic sequences are constructed according to multiple cooking parameters, and each genetic sequence represents a cooking plan.

[0010] Furthermore, the step of mapping the target values ​​of the multiple genes included in the gene sequence to a preset interval, obtaining the fitness value of each of the genes based on the encoding information, sorting the multiple genes according to the fitness values, and selecting the genes with fitness higher than the preset value as the preferred genes includes: Mapping the target value of each gene to a preset interval to obtain a standardized target value, wherein the preset interval is [0, 1]; According to the encoding information, a fitness value of each gene is calculated using a fitness evaluation function to obtain a fitness value set; Based on the quick sorting algorithm, the fitness values ​​corresponding to the genes in the fitness value set are arranged in ascending or descending order to obtain a gene list arranged from high to low in terms of fitness value; A fitness threshold is set, the sorted gene list is traversed, and genes with fitness values ​​of the fitness threshold are selected as preferred genes.

[0011] Furthermore, the step of randomly modifying the value of one of the preferred genes within a preset range, and performing fitness evaluation on the modified gene sequence in combination with the coding information until the optimal gene sequence is obtained includes: Performing random perturbation processing on each gene value in the preferred genes to obtain a perturbed gene value, wherein the perturbation processing includes randomly generating within a value range of each gene; Based on the fitness function in the genetic algorithm, the modified gene sequence is evaluated for fitness according to the perturbed gene value to obtain an evaluated fitness value; The gene sequences with fitness values ​​higher than the preset threshold are retained to obtain the selected preferred gene sequences; Performing a crossover operation on the preferred gene sequence to obtain a new gene sequence set, performing fitness evaluation on the gene sequence set after the crossover to obtain an evaluated fitness value, and comparing the fitness value with the fitness value of the original preferred gene sequence; The above steps are repeated until an optimal gene sequence is obtained whose fitness value exceeds the preset standard and whose variation is less than the threshold.

[0012] Furthermore, the step of converting the optimal gene sequence into a cooking control instruction and controlling the smart rice cooker to perform a cooking operation according to the cooking control instruction comprises: Performing parameter extraction processing on each gene in the optimal gene sequence to obtain corresponding cooking parameters, wherein the cooking parameters at least include temperature, time, humidity and stirring frequency; According to the cooking parameters, preprocessing is performed in combination with actual environmental data in the intelligent rice cooker to obtain environmental correction parameters; Performing scheduling optimization processing on the environmental correction parameters to obtain optimized cooking instructions, generating control commands according to the optimized cooking instructions to control the working state of the hardware components inside the rice cooker, wherein the control commands at least include temperature control instructions, stirring instructions and heating time; The real-time feedback data during the execution process is monitored, the feedback data is obtained and the cooking state is adjusted, the cooking instructions adjusted in real time are fed back to the smart rice cooker, and the cooking process is continuously updated until the cooking is completed.

[0013] The present invention also proposes a control system for an intelligent rice cooker based on the Internet of Things, comprising: An acquisition module, used for acquiring instruction information sent remotely by a user, identifying a mode flag contained in the instruction information, and converting the mode flag into coded information; an identification module, used to obtain image information of food in the smart rice cooker based on an acquisition sensor in the smart rice cooker, identify the image information to obtain type information of the food, and obtain weight information of the food based on a pressure sensor; a fusion module, used for fusing the food type information with the weight information to obtain a plurality of gene sequences, wherein each of the gene sequences is a cooking scheme, and each gene in the gene sequence is a parameter in the cooking scheme; A mapping module, used to map the target values ​​of the multiple genes included in the gene sequence to a preset interval, obtain the fitness value of each of the genes based on the encoding information, sort the multiple genes according to the fitness values, and select the genes with fitness higher than the preset value as preferred genes; An evaluation module, used to randomly modify the value of one of the preferred genes within a preset range, and perform fitness evaluation on the modified gene sequence in combination with the coding information until the optimal gene sequence is obtained; The control module is used to convert the optimal gene sequence into a cooking control instruction, and control the intelligent rice cooker to perform cooking operations according to the cooking control instruction.

[0014] The present invention further provides a computer device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above method is implemented.

[0016] Beneficial effects: The control method of the smart rice cooker based on the Internet of Things proposed in this application can adapt to the needs of different users by analyzing the user's command information and converting the mode flag into coding information, providing a highly personalized cooking experience, integrating image recognition and weight sensors, and being able to intelligently obtain and analyze the type and weight of ingredients. By collecting the image information of food through the camera and combining the data of the weight sensor, the type of food can be accurately identified and its weight information can be obtained. By optimizing the gene sequence, the cooking plan for each ingredient is intelligently generated and continuously optimized, and the type information and weight information of the ingredient are converted into multiple gene sequences, each gene representing a parameter in the cooking process. Then, these plans are evaluated by the fitness value of the gene, and the optimal cooking plan is selected. The most suitable parameters for the current ingredients can be automatically selected from multiple possible cooking plans, thereby improving the cooking effect, greatly enhancing the interactivity and intelligence level of the rice cooker, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the steps of a control method of an intelligent rice cooker based on the Internet of Things in one embodiment of the present invention; Figure 2 It is a structural schematic block diagram of a control system of an intelligent rice cooker based on the Internet of Things according to an embodiment of the present invention; Figure 3 is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention; The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0019] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "above", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of features, integers, steps, operations, elements, modules, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, modules, components, and / or groups thereof. It should be understood that when an element is said to be "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any module and all combinations of one or more associated listed items.

[0020] Those skilled in the art will understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the field to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0021] Reference Figure 1 The embodiment of the present invention provides a control method of an intelligent rice cooker based on the Internet of Things, comprising the following steps: S1: Acquire instruction information sent remotely by a user, identify a mode flag contained in the instruction information, and convert the mode flag into coded information; In step S1, the user can send instructions to the rice cooker remotely through a smart device such as a mobile phone. The instruction information includes the user's operating requirements, such as starting, stopping, setting the cooking mode or adjusting other parameters. In this embodiment, the cooking mode can include low-fat health, fast cooking, soup, steaming and other modes. The mode flag in the instruction is extracted. The mode flag represents the user's operating intention or the preset cooking mode (for example, cooking, steaming, slow cooking, etc.). For example, the user selects the low-fat mode, indicating that the user hopes to achieve a healthier cooking method by reducing fat and controlling temperature. This mode flag is converted into coding information, which can be converted into a specific code, such as 001.

[0022] S2: acquiring image information of food in the smart rice cooker based on a collection sensor in the smart rice cooker, identifying the image information to obtain type information of the food, and acquiring weight information of the food based on a pressure sensor; In step S2, the image of the currently cooking food can be obtained by a camera or other image acquisition device installed inside or on the lid of the rice cooker, and the collected image information is analyzed and processed by image recognition technology to identify the type of food. For example, when a user has already put rice, porridge, soup or other ingredients into the smart rice cooker in advance, the type of food can be identified based on the appearance characteristics of the food, and the weight information of the food can be obtained based on the pressure sensor. The smart rice cooker is equipped with a pressure sensor that can monitor the pressure changes in the rice cooker in real time.

[0023] S3: fusing the food type information with the weight information to obtain a plurality of gene sequences, wherein each gene sequence is a cooking scheme, and each gene in the gene sequence is a parameter in the cooking scheme; In step S3, the type information and weight information of the food are obtained through the sensor of the smart rice cooker. Through image recognition technology, the smart rice cooker can identify the type of food put into the rice cooker, such as rice, porridge, soup, etc., and the pressure sensor measures the weight of the food. The type information and weight information of the food essentially represent two independent dimensions, each of which has a different impact on the cooking plan. There are two methods to fuse these two information. The first is a rule-based fusion method, which retrieves a set of basic cooking parameters from a preset database or model according to the type of food. These parameters may include temperature, time, water volume, etc. For example, if the food is identified as rice, the standard cooking parameters of rice are queried, such as the amount of water required to add 1.2 times the amount of rice, the cooking time is 20 minutes, etc. Then, these parameters are adjusted according to the weight of the food through weighted rules. For example, for 200 grams of rice, the recommended amount of water is 240 milliliters and the cooking time is 25 minutes; for 400 grams of rice, the amount of water is adjusted to 480 milliliters and the cooking time is adjusted to 30 minutes. This method maps the type and weight information to a set of cooking parameters through a rule base to generate a preliminary cooking plan. The second is a data-driven fusion method, which is based on machine learning or deep learning models and uses a large amount of historical data to learn the relationship between type and weight and cooking parameters. In this method, a large amount of cooking data of different food types and weights is collected, including different types of ingredients, corresponding weights, and parameters such as temperature, time, and water used in the actual cooking process. By analyzing these data, a multivariate regression model or a neural network model can be trained to generate the most appropriate cooking plan in real time based on the type and weight of the food. The fused cooking parameters are converted into gene sequences, each cooking plan corresponds to a gene sequence, and each gene in the sequence represents a specific cooking parameter, such as temperature, time, water, etc. After the fusion process is completed, multiple gene sequences are generated, each of which represents a possible cooking plan. Specifically, each gene sequence is generated by mapping a combination of food type and weight into the parameter space. Each gene sequence contains multiple genes, and the gene values ​​are adjusted by the fusion results of species and weight.

[0024] S4: mapping the target values ​​of the multiple genes included in the gene sequence to a preset interval, obtaining a fitness value of each of the genes based on the encoding information, sorting the multiple genes according to the fitness values, and selecting the gene with a fitness higher than the preset value as a preferred gene; In step S4, the gene sequence refers to a set of coded information containing cooking process control parameters. For example, each gene in the gene sequence represents a cooking parameter (such as time, temperature, water volume, etc.). The target value of these genes is a continuous range of values, indicating the ideal state or expected value of these parameters. These target values ​​are mapped to a preset interval, which is a set reasonable numerical interval that can be defined by historical data, experimental results, user preferences and other factors. For example, the target value of temperature may be between "50°C and 100°C", and the target value of cooking time may be between "20 minutes and 40 minutes". The mapping process ensures that the parameter values ​​in the gene sequence do not exceed the practical operating range, thereby avoiding possible cooking failures or inappropriate operations. The coded information refers to the coded information converted from the instruction information sent by the above-mentioned user, and the fitness of the genes in each gene sequence is evaluated based on this information. The fitness value is determined based on the degree of matching between the parameters in the gene sequence and the user's needs. For example, if the user selects the low-fat health mode, the system will give priority to those gene sequences that can meet the low-fat cooking requirements. In the specific implementation, the calculation of the fitness value depends on an objective function, which evaluates the difference between the actual value of each gene (such as cooking time, temperature, etc.) and the ideal value. For example, if a gene represents cooking time, the objective function may calculate the difference between the actual cooking time and the ideal cooking time, and then quantify this difference in some way. If the value of the gene is close to the ideal value, then its fitness value will be higher; if the deviation is large, the fitness value will be lower. After obtaining the fitness value of each gene, multiple genes are sorted and their priority is determined according to the fitness value of each gene. A gene with a high fitness value means that it can better meet the expected needs in the current cooking task, and a gene with a low fitness value needs to be adjusted or replaced.

[0025] Genes with fitness higher than the preset value are selected as preferred genes. The preset value refers to the set minimum fitness threshold, which means that only when the fitness of the gene exceeds a certain standard can it be considered as a suitable parameter. In practical applications, this preset value can be set based on factors such as cooking experiment data, user feedback, and historical experience.

[0026] S5: randomly modifying the value of one of the preferred genes within a preset range, and performing fitness evaluation on the modified gene sequence in combination with the coding information, until the optimal gene sequence is obtained; In step S5, a preferred gene is randomly selected within a preset range for modification, and the value of the gene can be adjusted according to certain rules or probability distribution. For example, if the gene represents the cooking time, a certain proportion of time is increased or decreased based on the time set by the user to explore a better cooking solution. The purpose of random modification is to introduce diversity and avoid the algorithm from falling into a local optimal solution, thereby increasing the possibility of finding a global optimal solution. The modified gene sequence is evaluated for fitness in combination with the encoding information. This evaluation process is similar to step S4, and it is necessary to calculate the difference between the actual value and the ideal value of each gene, and quantify this difference through the objective function. The result of the fitness evaluation will determine whether the modified gene sequence is better than the previous sequence. If the new gene sequence has a higher fitness, it will replace the previous sequence as the current optimal gene sequence. This process will be repeated until the preset number of iterations is reached or the stop condition is met. The stop condition can be to find a gene sequence with a fitness exceeding a certain threshold, or to find no better gene sequence after a certain number of iterations. Finally, the algorithm outputs the optimal gene sequence, which represents the best cooking solution calculated based on user needs and the current food state.

[0027] S6: Convert the optimal gene sequence into a cooking control instruction, and control the smart rice cooker to perform cooking operations according to the cooking control instruction.

[0028] In step S6, the optimal gene sequence obtained in the previous step is used to convert it into a specific cooking control instruction to directly guide the cooking process of the intelligent rice cooker and ensure that the food can be cooked according to the optimal parameters. The conversion process involves mapping each gene value in the gene sequence to the control parameters of the rice cooker, such as converting the temperature gene value to the power output of the rice cooker heating element, converting the time gene value to the duration of cooking, etc. The converted cooking control instructions will be executed by the control system of the rice cooker to achieve accurate cooking process control. The control system of the intelligent rice cooker will automatically adjust various parameters in the cooking process, such as temperature, pressure, time, etc., according to these instructions to achieve the best cooking effect. For example, if the optimal gene sequence indicates that cooking needs to be done at a specific temperature for a period of time, the control system will ensure that the temperature monitored by the temperature sensor inside the rice cooker matches the temperature set in the instruction, and automatically switches to the next cooking stage after reaching the preset time.

[0029] In one embodiment, the steps of obtaining instruction information sent remotely by a user, identifying a mode flag contained in the instruction information, and converting the mode flag into coded information include: Parse and process the command information sent remotely by the user to obtain the original data of the command information; Performing pattern recognition processing on the original data according to the format of the instruction information, extracting the pattern flag contained in the original data, and obtaining pattern flag data; Classifying the flag type according to the mode flag data, and determining the cooking mode corresponding to the mode flag according to a preset rule table, wherein the preset rule table includes a correspondence between a plurality of preset cooking modes and mode flags; Converting the cooking mode into unique coding information according to a preset coding table, wherein each cooking mode in the preset coding table corresponds to a specific identifier; The unique coding information is subjected to data compression processing, and the unique coding information is compressed according to a compression algorithm to obtain optimized and stored coding information.

[0030] In the above embodiment, the command information sent remotely by the user is received through the Internet of Things. These command information can be sent through various devices (such as smart phones, tablet computers, etc.) and may contain multiple operation contents. Parsing is to convert the received original command data into a format that the system can understand. The parsed original data is subjected to pattern recognition processing, and the mode flags are extracted from the command information. These flags are used to indicate specific cooking modes, and the flag data is classified, and the specific cooking mode corresponding to each mode flag is determined according to the preset rule table. The preset rule table is a mapping relationship table, which contains the correspondence between multiple cooking modes and corresponding mode flags. For example, the rule table may stipulate that flag A corresponds to the rice cooking mode, flag B corresponds to the steaming mode, etc. By searching the rule table, the mode flag can be mapped to the specific cooking mode, thereby obtaining the cooking operation that the user actually wants to perform. After identifying the specific cooking mode, these modes are converted into unique coding information. Each cooking mode has a unique identifier in the system, which may be a number, letter or other symbol. In this step, the cooking mode is converted into the corresponding code by searching the preset coding table. For example, the rice cooking mode corresponds to the code 01, and the steaming mode corresponds to the code 02. This encoding mechanism can simplify data processing and transmission, reduce storage space usage, and ensure that each mode has a unique identifier to avoid ambiguity. After the cooking mode is converted into coded information, the coded information is compressed. The purpose of compression is to reduce the size of the data through an algorithm, making the information more efficient during transmission and easier to store.

[0031] In one embodiment, the steps of acquiring image information of food in the smart rice cooker based on an acquisition sensor in the smart rice cooker, identifying the image information to obtain type information of the food, and acquiring weight information of the food based on a pressure sensor include: Acquire an image of food in the smart rice cooker according to an acquisition sensor in the smart rice cooker, and denoise the image using a Gaussian filter algorithm to obtain a denoised image; Performing target detection on the denoised image based on a regional convolutional neural network, outputting regional coordinates and confidence of the food, and generating a food regional image based on the regional coordinates and confidence of the food; Extracting features from the food region image to obtain surface feature information of the food, matching and clustering the feature information to obtain a unique surface feature descriptor for each food; Comparing the unique surface feature descriptor with food features stored in a database to obtain type information of the food; The weight data of the food is obtained according to the pressure sensor in the smart rice cooker, and the weight data is A / D converted to obtain the weight information of the food.

[0032] In the above embodiment, the acquisition sensor in the smart rice cooker is used to obtain the image information of the food, and the collected image is denoised by the Gaussian filtering algorithm to reduce the noise interference in the image and obtain a clear denoised image. Then, the denoised image is detected by the region-based convolutional neural network (R-CNN), and the regional coordinates and confidence of the food are identified, so as to extract the food region image. The region convolutional neural network is a deep learning model that can effectively identify multiple targets in the image and give the precise position and confidence of each target. The food region image is feature extracted to extract the surface feature information of the food, which includes color, texture, shape, etc., and can reflect the unique attributes of the food. Through matching and clustering algorithms, the extracted feature information is compared with the food features stored in the database to identify the type information of the food. The database stores a large number of feature descriptors of food, which are pre-trained by machine learning algorithms and can accurately describe the characteristics of different foods. At the same time, the pressure sensor in the smart rice cooker is used to monitor the weight of the food in real time. By converting the analog signal of the pressure sensor into a digital signal (A / D conversion), the weight information of the food is obtained.

[0033] In one embodiment, the step of fusing the food type information with the weight information to obtain a plurality of gene sequences, wherein each gene sequence is a cooking scheme, and each gene in the gene sequence is a parameter in the cooking scheme, comprises: Extracting features of the food type information and the food weight information respectively to obtain a type parameter feature set and a weight parameter feature set; Extracting each of the food type parameter feature set and weight parameter feature set for weighted synthesis to obtain a fusion weight value, and performing dimensionality reduction processing on the fusion weight value through a principal component analysis algorithm to obtain a low-dimensional feature vector; Normalizing the type information and weight information of the food based on the feature vector to obtain a standardized feature representation; The standardized feature representation is genetically encoded, wherein each genetic code corresponds to a cooking parameter, and multiple genetic sequences are constructed according to multiple cooking parameters, and each genetic sequence represents a cooking plan.

[0034] In the above embodiment, feature extraction is performed on the type information and weight information of the food to obtain a type parameter feature set and a weight parameter feature set, respectively. The feature sets contain key information that can represent the type and weight of the food, such as visual features such as the shape, size, and color of the food, as well as numerical information of the weight. Weighted synthesis is performed on each food type parameter feature set and weight parameter feature set to obtain a fusion weight value. The purpose of weighted synthesis is to balance the importance of different features to ensure that the final gene sequence can comprehensively consider the type and weight information of the food, and the fusion weight value is reduced in dimension through the principal component analysis algorithm (PCA) to obtain a low-dimensional feature vector. Dimensionality reduction processing helps to remove redundant information while retaining the features that have the greatest impact on the cooking plan, making the gene sequence more refined and efficient. Based on the obtained feature vector, the type and weight information of the food are normalized to obtain a standardized feature representation. The normalization is to ensure that different features are comparable in numerical values, making the genetic encoding process more fair and accurate. The standardized feature representation is genetically encoded, where each gene code corresponds to a cooking parameter, each gene sequence represents a possible cooking plan, and each gene represents a specific parameter in the plan, such as temperature, time, water volume, etc.

[0035] In one embodiment, the step of mapping the target values ​​of the multiple genes included in the gene sequence to a preset interval, obtaining the fitness value of each of the genes based on the encoding information, sorting the multiple genes according to the fitness values, and selecting the genes with fitness higher than the preset value as the preferred genes includes: Mapping the target value of each gene to a preset interval to obtain a standardized target value, wherein the preset interval is [0, 1]; According to the encoding information, a fitness value of each gene is calculated using a fitness evaluation function to obtain a fitness value set; Based on the quick sorting algorithm, the fitness values ​​corresponding to the genes in the fitness value set are arranged in ascending or descending order to obtain a gene list arranged from high to low in terms of fitness value; A fitness threshold is set, the sorted gene list is traversed, and genes with fitness values ​​of the fitness threshold are selected as preferred genes.

[0036] In the above embodiment, the target value of each gene is mapped to a preset interval [0,1] for standardization, so that the target values ​​of all genes are compared and evaluated within a unified range, simplifying the fitness evaluation process and converting these values ​​into a common scale. According to the coded information, the fitness value of each gene is calculated using the fitness evaluation function. The fitness evaluation function is designed based on the objective function and can evaluate the gap between the actual performance and the ideal performance of each gene in the gene sequence. The output of the evaluation function is a fitness value set, which reflects the degree of adaptability of each gene to the current cooking task. The fitness value set is sorted using a quick sorting algorithm to obtain a gene list arranged from high to low by fitness value. Finally, a fitness threshold is set, the sorted gene list is traversed, and genes with fitness values ​​higher than the threshold are selected as preferred genes. The fitness threshold is a preset value that represents the minimum fitness standard that a gene must meet. In this way, the system can screen out genes that perform well in the current cooking task and provide a basis for the next step of gene sequence optimization.

[0037] In a specific embodiment, the establishment of the objective function first clarifies the optimization goal, that is, it is necessary to find the optimal control parameters. These parameters may include temperature, cooking time, and power, for example, setting the temperature to a specific value. An error metric is defined for each control parameter. The error metric reflects the deviation between the actual value and the expected value, and is usually quantified by calculating the difference between the target value and the actual value. Through these error metrics, we can quantify the deviation between each control parameter and the target value. Since different parameters may have different importance to the cooking effect, different weights can be assigned to the error of each parameter when designing the objective function. For example, temperature may have a greater impact on the quality of food, and time may have a smaller impact on the final effect. Therefore, assigning different weights to different errors can make the objective function more in line with actual needs.

[0038] In one embodiment, the step of randomly modifying the value of one of the preferred genes within a preset range, and performing fitness evaluation on the modified gene sequence in combination with the coding information until the optimal gene sequence is obtained includes: Performing random perturbation processing on each gene value in the preferred genes to obtain a perturbed gene value, wherein the perturbation processing includes randomly generating within a value range of each gene; Based on the fitness function in the genetic algorithm, the modified gene sequence is evaluated for fitness according to the perturbed gene value to obtain an evaluated fitness value; The gene sequences with fitness values ​​higher than a preset threshold are retained to obtain the selected preferred gene sequences; Performing a crossover operation on the preferred gene sequence to obtain a new gene sequence set, performing fitness evaluation on the gene sequence set after the crossover to obtain an evaluated fitness value, and comparing the fitness value with the fitness value of the original preferred gene sequence; The above steps are repeated until an optimal gene sequence is obtained whose fitness value exceeds the preset standard and whose variation is less than the threshold.

[0039] In the above embodiment, each gene value in the preferred gene is randomly perturbed to generate a new gene value. The perturbation is performed within a preset range of the gene value, ensuring that the modification of the gene value will not exceed a reasonable range. At the same time, randomness is introduced to provide diversity for the algorithm to explore the solution space. By randomly generating within the value range of each gene, a series of perturbed gene values ​​can be obtained, and these values ​​constitute a new gene sequence. Based on the fitness function in the genetic algorithm, the modified gene sequence is evaluated for fitness. The fitness function is designed according to the objective function and is used to measure the adaptability of the gene sequence to a specific cooking task. The fitness value calculated by the fitness function can be used to judge the quality of the gene sequence, thereby providing a basis for selecting and retaining excellent gene sequences. By comparing the fitness values ​​of different gene sequences and selecting the sequences with better performance to be retained, the gene sequences with lower fitness are gradually eliminated. A crossover operation is performed on the preferred gene sequence to generate a new set of gene sequences. The crossover operation generates new gene sequences by exchanging some genes of two or more preferred gene sequences. These new sequences inherit certain characteristics of the parent sequence and introduce new combinations, thereby increasing the diversity of the population. The fitness of the gene sequence set after the crossover is evaluated, and the evaluated fitness value is obtained, which is compared with the fitness value of the original preferred gene sequence. By comparison, it can be determined which newly generated gene sequences have higher fitness, so that they are retained and further optimized in subsequent iterations. Repeat the above steps until the optimal gene sequence with a fitness value exceeding the preset standard and a change less than the threshold is obtained. This process is an iterative optimization process. By repeatedly repeating the steps of perturbation, evaluation, screening and crossover, the algorithm gradually approaches the optimal solution. When a gene sequence is found whose fitness value exceeds the preset standard and changes very little after multiple consecutive iterations, it can be considered that the algorithm has converged. At this time, the output gene sequence is the optimal gene sequence, which represents the best cooking plan calculated based on user needs and the current food state.

[0040] In one embodiment, the step of converting the optimal gene sequence into a cooking control instruction and controlling the smart rice cooker to perform a cooking operation according to the cooking control instruction comprises: Performing parameter extraction processing on each gene in the optimal gene sequence to obtain corresponding cooking parameters, wherein the cooking parameters at least include temperature, time, humidity and stirring frequency; According to the cooking parameters, preprocessing is performed in combination with actual environmental data in the intelligent rice cooker to obtain environmental correction parameters; Performing scheduling optimization processing on the environmental correction parameters to obtain optimized cooking instructions, generating control commands according to the optimized cooking instructions to control the working state of the hardware components inside the rice cooker, wherein the control commands at least include temperature control instructions, stirring instructions and heating time; The real-time feedback data during the execution process is monitored, the feedback data is obtained and the cooking state is adjusted, the cooking instructions adjusted in real time are fed back to the smart rice cooker, and the cooking process is continuously updated until the cooking is completed.

[0041] In the above embodiment, each gene in the optimal gene sequence is subjected to parameter extraction processing to obtain corresponding cooking parameters, which include key factors such as temperature, time, humidity and stirring frequency. These parameters are the core control variables in the cooking process and determine the final taste and quality of the food. According to the extracted cooking parameters, the actual environmental data in the intelligent rice cooker is preprocessed to obtain environmental correction parameters, which take into account environmental factors such as temperature and humidity inside the rice cooker to ensure that the cooking parameters can adapt to the current environmental conditions, thereby ensuring the accuracy and stability of the cooking process. The environmental correction parameters are dispatched and optimized to obtain optimized cooking instructions. The optimization process may involve fuzzy logic control or neural network prediction models to ensure that the cooking instructions can be dynamically adjusted according to real-time feedback data to achieve the best cooking effect. Control commands are generated according to the optimized cooking instructions to control the working state of the hardware components inside the rice cooker. The control commands include temperature control instructions, stirring instructions and heating time, etc. These instructions directly act on the heating elements, stirring devices and other hardware of the rice cooker to ensure that the rice cooker can perform cooking tasks according to the optimized cooking plan. Finally, the real-time feedback data during the execution process is monitored, feedback data is obtained and the cooking status is adjusted. Real-time monitoring can be data provided by temperature sensors, pressure sensors, etc., which reflect the real-time status of the cooking process. By analyzing these data, the system can adjust the cooking instructions in time, such as adjusting the heating power, extending or shortening the cooking time, etc., to cope with possible deviations in the actual cooking process and ensure the cooking quality of the food. The real-time adjusted cooking instructions are fed back to the smart rice cooker, and the cooking process is continuously updated until the cooking is completed. This process is a closed-loop control system. Through continuous feedback and adjustment, the smart rice cooker can automatically adapt to various cooking conditions to ensure that the taste and quality of the final food meet the user's expectations.

[0042] Reference Figure 2 , a control system of an intelligent rice cooker based on the Internet of Things, comprising: The acquisition module 100 is used to acquire the instruction information sent remotely by the user, identify the mode flag contained in the instruction information, and convert the mode flag into coded information; The recognition module 200 is used to obtain image information of food in the smart rice cooker based on a collection sensor in the smart rice cooker, recognize the image information to obtain type information of the food, and obtain weight information of the food based on a pressure sensor; A fusion module 300 is used to fuse the food type information with the weight information to obtain a plurality of gene sequences, wherein each gene sequence is a cooking scheme, and each gene in the gene sequence is a parameter in the cooking scheme; A mapping module 400, for mapping the target values ​​of the multiple genes included in the gene sequence to a preset interval, obtaining a fitness value of each of the genes based on the encoding information, sorting the multiple genes according to the fitness values, and selecting the genes with a fitness higher than the preset value as preferred genes; An evaluation module 500, for randomly modifying the value of one of the preferred genes within a preset range, and performing fitness evaluation on the modified gene sequence in combination with the coding information, until the optimal gene sequence is obtained; The control module 600 is used to convert the optimal gene sequence into a cooking control instruction, and control the smart rice cooker to perform cooking operations according to the cooking control instruction.

[0043] In this embodiment, starting from the instruction information sent remotely by the user, by identifying the mode flag in the instruction and converting the mode flag into coded information, the mode flag in the instruction usually represents the user's desired cooking method or preference, and obtaining the image information of the food through the built-in acquisition sensor. This image information helps the system identify the type of food through image recognition technology, thereby determining the type of food. At the same time, the pressure sensor will provide data related to the weight of the food, and the type information and weight information of the food are merged to obtain multiple gene sequences. Each gene sequence actually represents a cooking scheme, and each gene is a parameter in the scheme, such as temperature, time, power, etc. Therefore, multiple gene parameters in the gene sequence constitute a complete cooking scheme, covering all necessary cooking control information. To ensure the accuracy and consistency of cooking, the target values ​​of these gene sequences (i.e., the ideal values ​​of each gene) will be mapped to a preset interval. At this time, the coded information will be used to obtain the fitness value of each gene, which is an evaluation result of the current gene sequence in achieving the best cooking effect. Based on these fitness values, multiple genes are sorted, and genes with fitness higher than the preset value are selected as preferred genes. These genes represent the optimal cooking parameters. After selecting the preferred gene, the value of one of the preferred genes is randomly modified within the preset range, and the modified gene sequence is evaluated for fitness by combining the coding information. New possibilities are explored by randomly modifying the gene value, hoping to find a better cooking solution. The modified gene sequence will continue to be evaluated for fitness until an optimal gene sequence is found, representing a parameter combination that can achieve the best cooking effect. Finally, this optimal gene sequence will be converted into actual cooking control instructions, which will be transmitted to the smart rice cooker to guide the rice cooker to perform cooking operations according to these control instructions. Through such an intelligent control method based on the Internet of Things, cooking parameters can be automatically analyzed and optimized, and cooking plans can be adjusted in real time according to food types and weights, thereby achieving a personalized, accurate and efficient cooking experience, while also improving the user's convenience and satisfaction with the operation of the smart rice cooker.

[0044] Reference Figure 3 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as a control method for an intelligent rice cooker based on the Internet of Things. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a control method for an intelligent rice cooker based on the Internet of Things is implemented.

[0045] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a control method for a smart rice cooker based on the Internet of Things is implemented, comprising the steps of: obtaining instruction information sent remotely by a user, identifying a mode flag contained in the instruction information, and converting the mode flag into coding information; obtaining image information of food in the smart rice cooker based on a collection sensor in the smart rice cooker, identifying the image information to obtain type information of the food, and obtaining weight information of the food based on a pressure sensor; fusing the type information of the food with the weight information to obtain multiple gene sequences, wherein each of the gene sequences The sequence is a cooking scheme, and each gene in the gene sequence is a parameter in the cooking scheme; the target values ​​of multiple genes contained in the gene sequence are mapped to a preset interval, the fitness value of each gene is obtained based on the coding information, the multiple genes are sorted according to the fitness value, and the gene with a fitness higher than the preset value is selected as the preferred gene; the value of one of the preferred genes is randomly modified within a preset range, and the fitness of the modified gene sequence is evaluated in combination with the coding information until the optimal gene sequence is obtained; the optimal gene sequence is converted into a cooking control instruction, and the smart rice cooker is controlled to perform a cooking operation according to the cooking control instruction.

[0046] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0047] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A control method for an intelligent rice cooker based on the Internet of Things, characterized in that: include: Acquire instruction information sent remotely by a user, identify a mode flag contained in the instruction information, and convert the mode flag into coded information; Acquire image information of food in the smart rice cooker based on a collection sensor in the smart rice cooker, identify the image information to obtain type information of the food, and acquire weight information of the food based on a pressure sensor; The food type information and the weight information are merged to obtain a plurality of gene sequences, wherein each gene sequence is a cooking scheme, and each gene in the gene sequence is a parameter in the cooking scheme; Mapping the target values ​​of the multiple genes included in the gene sequence to a preset interval, obtaining the fitness value of each of the genes based on the encoding information, sorting the multiple genes according to the fitness values, and selecting the genes with fitness higher than the preset value as preferred genes; Randomly modify the value of one of the preferred genes within a preset range, and perform fitness evaluation on the modified gene sequence in combination with the coding information until the optimal gene sequence is obtained; The optimal gene sequence is converted into a cooking control instruction, and the intelligent rice cooker is controlled to perform a cooking operation according to the cooking control instruction.

2. The control method of the intelligent rice cooker based on the Internet of Things according to claim 1, characterized in that: The step of acquiring the instruction information sent remotely by the user, identifying the mode flag contained in the instruction information, and converting the mode flag into coded information includes: Parse and process the command information sent remotely by the user to obtain the original data of the command information; Performing pattern recognition processing on the original data according to the format of the instruction information, extracting the pattern flag contained in the original data, and obtaining pattern flag data; Classifying the flag type according to the mode flag data, and determining the cooking mode corresponding to the mode flag according to a preset rule table, wherein the preset rule table includes a correspondence between a plurality of preset cooking modes and mode flags; Converting the cooking mode into unique coding information according to a preset coding table, wherein each cooking mode in the preset coding table corresponds to a specific identifier; The unique coding information is subjected to data compression processing, and the unique coding information is compressed according to a compression algorithm to obtain optimized and stored coding information.

3. The control method of the intelligent rice cooker based on the Internet of Things according to claim 1, characterized in that: The steps of acquiring image information of food in the smart rice cooker based on a collection sensor in the smart rice cooker, identifying the image information to obtain type information of the food, and acquiring weight information of the food based on a pressure sensor include: Acquire an image of food in the smart rice cooker according to an acquisition sensor in the smart rice cooker, and denoise the image using a Gaussian filter algorithm to obtain a denoised image; Performing target detection on the denoised image based on a regional convolutional neural network, outputting regional coordinates and confidence of the food, and generating a food regional image based on the regional coordinates and confidence of the food; Extracting features from the food region image to obtain surface feature information of the food, matching and clustering the feature information to obtain a unique surface feature descriptor for each food; Comparing the unique surface feature descriptor with food features stored in a database to obtain type information of the food; The weight data of the food is obtained according to the pressure sensor in the smart rice cooker, and the weight data is A / D converted to obtain the weight information of the food.

4. The control method of the intelligent rice cooker based on the Internet of Things according to claim 1, characterized in that: The step of fusing the food type information with the weight information to obtain a plurality of gene sequences, wherein each gene sequence is a cooking scheme, and each gene in the gene sequence is a parameter in the cooking scheme, comprises: Extracting features of the food type information and the food weight information respectively to obtain a type parameter feature set and a weight parameter feature set; Extracting each of the food type parameter feature set and weight parameter feature set for weighted synthesis to obtain a fusion weight value, and performing dimensionality reduction processing on the fusion weight value through a principal component analysis algorithm to obtain a low-dimensional feature vector; Normalizing the type information and weight information of the food based on the feature vector to obtain a standardized feature representation; The standardized feature representation is genetically encoded, wherein each genetic code corresponds to a cooking parameter, and multiple genetic sequences are constructed according to multiple cooking parameters, and each genetic sequence represents a cooking plan.

5. The control method of the intelligent rice cooker based on the Internet of Things according to claim 1, characterized in that: The step of mapping the target values ​​of the multiple genes included in the gene sequence to a preset interval, obtaining the fitness value of each of the genes based on the encoding information, sorting the multiple genes according to the fitness values, and selecting the gene with a fitness higher than the preset value as the preferred gene includes: Mapping the target value of each gene to a preset interval to obtain a standardized target value, wherein the preset interval is [0, 1]; According to the encoding information, a fitness value of each gene is calculated using a fitness evaluation function to obtain a fitness value set; Based on the quick sorting algorithm, the fitness values ​​corresponding to the genes in the fitness value set are arranged in ascending or descending order to obtain a gene list arranged from high to low in terms of fitness value; A fitness threshold is set, the sorted gene list is traversed, and genes with fitness values ​​of the fitness threshold are selected as preferred genes.

6. The control method of the intelligent rice cooker based on the Internet of Things according to claim 1, characterized in that: The step of randomly modifying the value of one of the preferred genes within a preset range, and performing fitness evaluation on the modified gene sequence in combination with the coding information until the optimal gene sequence is obtained includes: Performing random perturbation processing on each gene value in the preferred genes to obtain a perturbed gene value, wherein the perturbation processing includes randomly generating within a value range of each gene; Based on the fitness function in the genetic algorithm, the modified gene sequence is evaluated for fitness according to the disturbed gene value to obtain an evaluated fitness value; The gene sequences with fitness values ​​higher than the preset threshold are retained to obtain the selected preferred gene sequences; Performing a crossover operation on the preferred gene sequence to obtain a new gene sequence set, performing fitness evaluation on the gene sequence set after the crossover to obtain an evaluated fitness value, and comparing the fitness value with the fitness value of the original preferred gene sequence; The above steps are repeated until an optimal gene sequence is obtained whose fitness value exceeds the preset standard and whose variation is less than the threshold.

7. The control method of the intelligent rice cooker based on the Internet of Things according to claim 1, characterized in that: The step of converting the optimal gene sequence into a cooking control instruction and controlling the intelligent rice cooker to perform a cooking operation according to the cooking control instruction comprises: Performing parameter extraction processing on each gene in the optimal gene sequence to obtain corresponding cooking parameters, wherein the cooking parameters at least include temperature, time, humidity and stirring frequency; According to the cooking parameters, preprocessing is performed in combination with actual environmental data in the intelligent rice cooker to obtain environmental correction parameters; Performing scheduling optimization processing on the environmental correction parameters to obtain optimized cooking instructions, generating control commands according to the optimized cooking instructions to control the working state of the hardware components inside the rice cooker, wherein the control commands at least include temperature control instructions, stirring instructions and heating time; The real-time feedback data during the execution process is monitored, the feedback data is obtained and the cooking state is adjusted, the cooking instructions adjusted in real time are fed back to the smart rice cooker, and the cooking process is continuously updated until the cooking is completed.

8. A control system for an intelligent rice cooker based on the Internet of Things, characterized in that: include: An acquisition module, used for acquiring instruction information sent remotely by a user, identifying a mode flag contained in the instruction information, and converting the mode flag into coded information; an identification module, used to obtain image information of food in the smart rice cooker based on an acquisition sensor in the smart rice cooker, identify the image information to obtain type information of the food, and obtain weight information of the food based on a pressure sensor; a fusion module, used for fusing the food type information with the weight information to obtain a plurality of gene sequences, wherein each of the gene sequences is a cooking scheme, and each gene in the gene sequence is a parameter in the cooking scheme; A mapping module, used to map the target values ​​of the multiple genes included in the gene sequence to a preset interval, obtain the fitness value of each of the genes based on the encoding information, sort the multiple genes according to the fitness values, and select the genes with fitness higher than the preset value as preferred genes; An evaluation module, used to randomly modify the value of one of the preferred genes within a preset range, and perform fitness evaluation on the modified gene sequence in combination with the coding information until the optimal gene sequence is obtained; The control module is used to convert the optimal gene sequence into a cooking control instruction, and control the intelligent rice cooker to perform cooking operations according to the cooking control instruction.

9. A computer device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images