Load prediction method and system based on hybrid rice algorithm optimization

Abstract

The embodiment of the invention provides a load prediction method and system based on hybrid rice algorithm optimization. The method comprises the steps that air conditioner operation parameters and environment parameters of a hybrid rice cultivation environment are acquired; evaluating and determining important features through a preset algorithm, and constructing a BP neural network model for cultivating environment load prediction by taking the number of the important features as a dimension; obtaining and initializing a gene sequence of hybrid rice, adjusting an initial weight of a BP neural network model by using the gene sequence, and taking the important features as an input model for training; the cultivation environment load prediction accuracy in model weight training serves as a fitness value, line grouping is conducted on the hybrid rice, grouping updating optimization is conducted on the hybrid rice, and initial weight training is conducted on the BP neural network model through the updated and optimized hybrid rice; and when training stops, outputting optimal weight parameter configuration of the BP neural network, inputting the important features into a BP neural network model with the optimal weight parameter configuration, and determining an air conditioner operation scheme.

Description

Technical Field

[0001] The present invention relates to the field of automatic control technology, and in particular to a load prediction method and system based on hybrid rice algorithm optimization. Background Art

[0002] With the advancement of science and technology, the cooperation and participation of other scientific and technological equipment is also needed in the process of hybrid rice cultivation. For example, air conditioning is needed in various stages such as seed preservation, breeding, greenhouse cultivation, and seed production. This will enable the environmental load of the hybrid rice cultivation environment to be controlled, which will help improve the yield, quality, and reliability of scientific research results of hybrid rice.

[0003] However, in the traditional hybrid rice cultivation process, the artificially designed start and stop times of air conditioners result in serious energy waste. This is because the artificially designed start and stop times often cannot accurately match the actual environmental requirements, resulting in the air conditioner still running when it is not needed, or starting too early when it is needed, causing energy waste. Summary of the invention

[0004] In view of the problems existing in the prior art, an embodiment of the present invention provides a load forecasting method and system based on hybrid rice algorithm optimization.

[0005] The embodiment of the present invention provides a load forecasting method based on hybrid rice algorithm optimization, comprising:

[0006] Acquiring the associated parameters of the hybrid rice cultivation environment and preprocessing the associated parameters, wherein the associated parameters include air conditioning operation parameters and environmental parameters;

[0007] The importance of the associated parameters is evaluated by a preset algorithm, important features in the associated parameters are determined, and a BP neural network model for predicting the cultivation environment load is constructed based on the number of the important features as a dimension;

[0008] Obtaining and initializing a gene sequence of hybrid rice, adjusting the initial weight of the BP neural network model with the gene sequence, and taking the important features as input to perform model training on the BP neural network model;

[0009] The prediction accuracy of the cultivation environment load in the model weight training is used as the fitness value, the hybrid rice is grouped into different lines, and the hybrid rice is updated and optimized based on different line groups, and the BP neural network model is initially trained with the updated and optimized hybrid rice;

[0010] When the detection update optimization process triggers the termination condition, the update optimization is stopped, the optimal weight parameter configuration of the BP neural network is output, and the important features are input into the BP neural network model with the optimal weight parameter configuration to determine the air conditioning operation plan of the cultivation environment.

[0011] In one embodiment, the department grouping includes:

[0012] Maintainer lines, restorer lines and sterile lines;

[0013] The method of renewing and optimizing the hybrid rice based on different lineage groups comprises:

[0014] hybridizing the sterile line with the maintainer line, and judging whether to update and optimize the sterile line based on the fitness value of the hybridization result;

[0015] The restoration line is self-pollinated, and whether to update and optimize the restoration line is determined based on the maximum number of self-pollinations.

[0016] In one embodiment, the method further comprises:

[0017] The sterile line and the maintainer line are hybridized by a hybridization formula, and the fitness value of the offspring rice seeds in the hybridization result is detected based on the BP neural network model, and when the fitness value is greater than the fitness value of the maintainer line, the sterile line is replaced with the offspring rice seeds, otherwise the sterile line is retained;

[0018] The hybridization formula includes:

[0019]

[0020] Among them, the above formula is the process of hybridization in the tth generation, is the dth gene in the gene sequence of the i-th rice seed in the sterile line, is the dth gene in the k2th rice seed gene sequence selected from the maintainer line, is the dth gene in the k2th rice seed gene sequence selected from the sterile line, r 2 , r 3 is a random number in the range [-1,1], and r 2 +r 3 ≠0.

[0021] In one embodiment, the method further comprises:

[0022] When the restorer line completes selfing, determining whether the number of selfing of the restorer line reaches a preset maximum number of selfings, and if it does not reach the preset maximum number of selfings, the restorer line self-pollinates according to a selfing formula to produce progeny rice seeds;

[0023] The self-intersection formula includes:

[0024]

[0025] in, Represents the i-th recovery system New individuals produced by self-fertilization represents the kth individual randomly selected from the recovery line, r 4 is a uniform random number in the range [0,1], x best represents the current optimal individual;

[0026] The fitness value of the offspring rice seeds in the self-pollination results is detected based on the BP neural network model, and the fitness value of the offspring rice seeds is compared with that of the previous generation rice seeds. When the fitness value of the offspring rice seeds is high, the offspring rice seeds are used to update and optimize the previous generation rice seeds and the number of self-pollination is set to 0. Otherwise, the previous generation rice seeds are retained and the number of self-pollination is increased by 1.

[0027] In one embodiment, the method further comprises:

[0028] When it is detected that the number of self-pollination reaches the maximum number of self-pollination, the rice seeds are reset by the following formula:

[0029]

[0030] in, Restore system New rice seeds generated by the reset operation, x min 、x max are the upper and lower limits of gene quantification, r 5 is a uniform random number in the range [0,1].

[0031] In one embodiment, the method further comprises:

[0032] Inputting the important features into the BP neural network model configured with optimal weight parameters to obtain the output final load forecast result;

[0033] The load type and load value of the load forecast result are detected, and the air conditioning operation plan of the cultivation environment is determined in combination with the environmental parameters.

[0034] The embodiment of the present invention provides a load forecasting system based on hybrid rice algorithm optimization, comprising:

[0035] An acquisition module, used for acquiring the associated parameters of the hybrid rice cultivation environment and preprocessing the associated parameters, wherein the associated parameters include air conditioning operation parameters and environmental parameters;

[0036] An evaluation module, used to evaluate the importance of the associated parameters through a preset algorithm, determine the important features in the associated parameters, and construct a BP neural network model for predicting the cultivation environment load based on the number of the important features as a dimension;

[0037] A weight module, used for obtaining and initializing the gene sequence of hybrid rice, adjusting the initial weight of the BP neural network model with the gene sequence, and taking the important features as input to perform model training on the BP neural network model;

[0038] A training module, for grouping the hybrid rice by strain using the prediction accuracy of the cultivation environment load in the model weight training as the fitness value, updating and optimizing the hybrid rice based on different strain groups, and performing initial weight training on the BP neural network model through the updated and optimized hybrid rice;

[0039] The output module is used to stop the update optimization when the detection update optimization process triggers the termination condition, output the optimal weight parameter configuration of the BP neural network, and input the important features into the BP neural network model with the optimal weight parameter configuration to determine the air conditioning operation plan of the cultivation environment.

[0040] In one embodiment, the system further comprises:

[0041] A first optimization module is used to hybridize the sterile line with the maintainer line, and determine whether to update and optimize the sterile line based on the fitness value of the hybridization result;

[0042] The second optimization module is used to perform self-pollination on the restoration line and determine whether to update and optimize the restoration line based on the maximum number of self-pollination times.

[0043] An embodiment of the present invention provides an electronic device, including a processor and a memory;

[0044] The processor is connected to the memory;

[0045] The memory is used to store executable program code;

[0046] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method described in one or more embodiments.

[0047] An embodiment of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the load forecasting method based on hybrid rice algorithm optimization are implemented.

[0048] In view of the above, in one or more embodiments of the present specification, the associated parameters of the hybrid rice cultivation environment are obtained and preprocessed, and the associated parameters include air conditioning operation parameters and environmental parameters; the importance of the associated parameters is evaluated through a preset algorithm, the important features in the associated parameters are determined, and a BP neural network model for predicting the cultivation environment load is constructed based on the number of important features as a dimension; the gene sequence of hybrid rice is obtained and initialized, the initial weight of the BP neural network model is adjusted with the gene sequence, and the important features are used as input to train the BP neural network model; the prediction accuracy of the cultivation environment load in the model weight training is used as the fitness value, the hybrid rice is grouped into series, and the hybrid rice is updated and optimized based on different series groupings, and the initial weight training of the BP neural network model is performed through the updated and optimized hybrid rice; when the detection update optimization process triggers the termination condition, the update optimization is stopped, the optimal weight parameter configuration of the BP neural network is output, and the important features are input into the BP neural network model with the optimal weight parameter configuration to determine the air conditioning operation plan of the cultivation environment. This enables real-time data to predict the load of the corresponding room. The system can automatically adjust the start and stop time of the air conditioner based on the predicted load demand, ensuring that the air conditioner starts and stops at the appropriate time to avoid unnecessary energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 This is a flow chart of a load forecasting method based on hybrid rice algorithm optimization provided in one embodiment of this specification.

[0051] Figure 2 It is a flow chart of a hybrid rice algorithm for optimizing BP neural network weight parameter configuration provided by an embodiment of this specification.

[0052] Figure 3 It is a structural schematic diagram of a load forecasting system based on hybrid rice algorithm optimization provided in one embodiment of this specification.

[0053] Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0054] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and is not a limitation of the scope of protection, applicability or examples set forth in the claims. The functions and arrangements of the elements discussed can be changed without departing from the scope of protection of the contents of this specification. Various examples can omit, replace or add various processes or components as needed. For example, the described method can be performed in an order different from the described order, and various steps can be added, omitted or combined. In addition, the features described relative to some examples can also be combined in other examples.

[0055] As used herein, the term "including" and its variations represent open terms, meaning "including but not limited to". The term "based on" means "based at least in part on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other definitions may be included below, whether explicit or implicit. Unless the context clearly indicates otherwise, the definition of a term is consistent throughout the specification.

[0056] like Figure 1 As shown, the embodiment of the present invention provides a method for predicting the cultivation environment load based on hybrid rice algorithm optimization, comprising:

[0057] Step S101, obtaining the associated parameters of the hybrid rice cultivation environment and preprocessing the associated parameters, wherein the associated parameters include air conditioning operation parameters and environmental parameters.

[0058] Specifically, the associated parameters of the hybrid rice cultivation environment are obtained, wherein the collection step of the associated parameters can be to establish a data integration platform or use an Internet of Things (IoT) platform to collect, store and preliminarily process historical and real-time data collected from various sensors. For example, when using the Internet of Things (IoT), the Lora protocol can be used for communication. Reliable connection performance and security are provided for various Internet of Things applications. Wireless transmission of real-time data from the sensor to the edge gateway is realized. Among them, the associated parameters collected by the sensor may include relevant parameters of the air conditioner and other environmental parameters when the hybrid rice grows, and the associated parameters include at least: indoor temperature and outdoor temperature at several different locations, indoor humidity, time when the air conditioner starts working, air supply volume of the air conditioner, working time of the air conditioner, working state of the air conditioner under the corresponding working time, production power consumption and steam consumption and other data, wherein the record of the working state of the air conditioner includes but is not limited to operating mode (such as cooling, heating, dehumidification, etc.), power consumption, fault alarm, and the power consumption of the air conditioning system itself and possible auxiliary heating (such as steam) steam consumption. After determining the associated parameters, they need to be sorted and preprocessed. Sorting can include regularly checking the integrity and accuracy of each data and handling the anomalies therein. Preprocessing can include cleaning, missing value processing, standardization or normalization, etc.

[0059] Step S102, evaluating the importance of the associated parameters through a preset algorithm, determining the important features in the associated parameters, and constructing a BP neural network model for predicting the cultivation environment load based on the number of the important features as a dimension.

[0060] Specifically, with respect to each associated parameter obtained in the above steps, it is necessary to screen the associated parameters and determine the important features with higher importance in the associated parameters. The method for evaluating the feature importance of the associated parameters may include performing feature analysis and selection using random forest and XGBoost (Extreme Gradient Boosting) to obtain the optimal feature parameters. The specific steps include: constructing a data set of each associated parameter, and then each tree in the random forest will be trained using a feature subset in the data set. The "importance" of each feature can be evaluated by observing the frequency of the feature as a split point in all trees, and its contribution to reducing the impurity of the tree (such as the Gini index or entropy) during segmentation. XGBoost builds a tree model through a gradient boosting framework, and can calculate the frequency of each feature appearing in all trees, thereby judging the importance of the feature. Combining the above methods, a feature importance list can be generated, in which each feature is associated with an importance score, sorting these lists, and identifying features with scores higher than a preset threshold, which are the important features in the associated parameters required in the subsequent steps.

[0061] After determining the important features, a BP neural network model for predicting the cultivation environment load is constructed, wherein the room load refers to the total amount of heat that the room needs to remove or add by the air conditioning system in order to maintain the indoor environment within a set comfort range, i.e., the comfort range of hybrid rice in this embodiment, in the field of building environment control and heating, ventilation and air conditioning (HVAC). The room load can be divided into cold load and heat load. The composition of the BP neural network includes four parts: input layer, hidden layer, fully connected layer and output layer. The input layer is an n-dimensional feature vector of the input, and n depends on the number of important features to ensure that the neural network can receive information on all important features. The hidden layer is located after the input layer, and each of its neurons is connected to all neurons in the previous layer. The fully connected layer flattens the features extracted by the previous layer and connects them to the output layer, thereby mapping the features to the final prediction results; in the prediction of the cultivation environment load, the fully connected layer can realize the mapping between the input features and the output prediction by learning the complex relationship between the features. The output layer can use a linear activation function (such as the identity function) to directly output the predicted value of the room load, because the room load prediction is a regression problem. For example, in the load prediction formula F(wx+b), w is the connection weight, b is the bias term, and F is the activation function Relu. The activation function Relu is usually used in the hidden layer, and the output layer may use a linear function to directly output continuous values. In addition, after the BP neural network completes the preliminary prediction of the room load, the support vector machine (SVM) is introduced to further process the prediction results, specifically for "start and stop time judgment". SVM is used to analyze the predicted load curve and identify the key points of load changes, such as predicting when the load reaches the threshold that requires turning on or off the air conditioning system. SVM establishes classification boundaries by learning the features extracted from the neural network prediction results to determine whether the conditions for starting or stopping the air conditioning are met.

[0062] Step S103, obtaining and initializing the gene sequence of hybrid rice, adjusting the initial weight of the BP neural network model with the gene sequence, and taking the important features as input to perform model training on the BP neural network model.

[0063] Specifically, the hybrid rice seeds are obtained, and the gene sequence of the hybrid rice seeds is initialized as the initial configuration of the BP neural network parameters. The length of the gene sequence corresponds to the number of features in the input data set, that is, the hybrid rice gene sequence is decoded into feature weights, each gene in the gene sequence corresponds to a feature weight, and the BP neural network algorithm is used to train the input training set to obtain a cultivation environment load prediction model corresponding to each set of weights. The specific steps can be: encoding, each "gene" or feature weight can be initialized by random or heuristic methods to ensure that the entire possible weight space is covered; decoding: converting these gene sequences into actual weight values, and applying them to the connection from the input layer to the hidden layer and from the hidden layer to the output layer of the BP neural network; model training: using these initial weights, using the BP algorithm to train the network, inputting the data set of important features in the above steps, and obtaining the accuracy of load prediction. The training goal is to minimize the error between the predicted load and the actual load. The load prediction accuracy of each model is used as the fitness function value of the corresponding hybrid rice seeds.

[0064] Step S104, using the prediction accuracy of the cultivation environment load in the model weight training as the fitness value, the hybrid rice is grouped according to the strains, and the hybrid rice is updated and optimized based on the different strain groups, and the BP neural network model is initially trained with the updated and optimized hybrid rice.

[0065] Specifically, the fitness function values ​​of hybrid rice seeds obtained through training are used to arrange the hybrid rice seeds according to their fitness, and the hybrid rice seeds are divided into maintenance lines, restoration lines and sterile lines according to their fitness. Among them, the sterile line has the lowest fitness and is a plant variety that cannot produce fertile pollen and can only bear fruit through cross-pollination. It serves as the female parent in hybrid breeding and is responsible for receiving pollen from the restoration line or maintenance line for hybridization. The restoration line has an intermediate fitness and serves as the female parent in hybrid breeding and is responsible for receiving pollen from the restoration line or maintenance line for hybridization. Its function is to overcome the sterility of the sterile line so that the hybrid offspring can reproduce normally. The maintenance line has the highest fitness and its function is to reproduce and maintain the sterile line. Then, the hybrid rice is updated and optimized according to different line groups. The updating and optimization process can be described as follows. Figure 2 As shown, Figure 2 Flowchart for optimizing the BP neural network weight parameter configuration for the hybrid rice algorithm. First, set the relevant parameters of the update optimization process, including the maximum number of iterations I max , the maximum number of self-crossing times T max , current algebra k = 0, current number of self-intersections t i =0, and then the fitness value of rice seeds is calculated and divided into categories through the weighted integration algorithm, and rice seeds are updated according to different categories.

[0066] For sterile and maintainer lines:

[0067] The sterile line and the maintenance line are hybridized according to the following hybridization formula. If the fitness value of the generated new gene sequence is greater than the fitness value of the selected maintenance line, the current sterile line is replaced, otherwise the sterile line of the previous generation is retained:

[0068]

[0069] Among them, the above formula is the process of hybridization in the tth generation, is the dth gene in the gene sequence of the i-th rice seed in the sterile line, is the dth gene in the k2th rice seed gene sequence selected from the maintainer line. is the dth gene in the k2th rice seed gene sequence selected from the sterile line. 2 , r 3 is a random number in the range [-1,1], and r 2 +r 3 ≠0.

[0070] For recovery system:

[0071] The restorer line individuals complete self-pollination, and determine whether the restorer line individuals have reached the maximum number of self-pollination. If not, the restorer line self-pollinates to produce the next generation of rice seeds through the following self-pollination formula, where the maximum number of self-pollination can be set by oneself, and the specific value is related to the maintenance of genetic diversity and the avoidance of inbreeding. The specific self-pollination formula is:

[0072]

[0073] in, Represents the i-th recovery system New individuals produced by self-fertilization represents the kth individual randomly selected from the recovery line. 4 is a uniform random number in the range [0,1]. best represents the current best individual.

[0074] In the next generation of self-pollination, the fitness of the next generation of rice seeds is compared with the original fitness of the previous generation. If the seeds after self-pollination are better, the new seeds are retained and the number of self-pollinations is set to 0. Otherwise, the number of self-pollinations is increased by 1. If the maximum number of self-pollinations is reached, the rice seeds are reset according to the following formula:

[0075]

[0076] in, Restore system New rice generated by the reset operation. min 、xmax are the upper and lower limits of gene quantification, r 5 is a uniform random number in the range [0,1].

[0077] Step S105, when the detection update optimization process triggers the termination condition, the update optimization is stopped, the optimal weight parameter configuration of the BP neural network is output, and the air conditioning operation plan of the cultivation environment is determined in combination with the important features.

[0078] Specifically, when it is detected that the update optimization of hybrid rice seeds reaches the termination condition, such as the maximum number of iterations reaches I max , the maximum number of self-crossings reaches T max When the gene sequence of the hybrid rice seeds with the largest fitness value is obtained, it is the optimal weight parameter configuration of the corresponding BP neural network, and then the important features in the associated parameters are input into the BP neural network with the optimal weight parameter configuration to determine the load prediction result corresponding to the hybrid rice. The load prediction result includes the load type, such as cold load or heat load, and the load value, that is, the corresponding specific value of heat. Then, based on the load prediction result and the heat value determined in the environmental parameters, the air-conditioning operation plan of the cultivation environment is adjusted accordingly to meet the requirements of the load prediction result.

[0079] The embodiment of the present invention provides a load prediction method based on hybrid rice algorithm optimization, which obtains the associated parameters of the hybrid rice cultivation environment and preprocesses the associated parameters, wherein the associated parameters include air conditioning operation parameters and environmental parameters; the importance of the associated parameters is evaluated by a preset algorithm, the important features in the associated parameters are determined, and a BP neural network model for predicting the cultivation environment load is constructed based on the number of important features as a dimension; the gene sequence of the hybrid rice is obtained and initialized, the initial weight of the BP neural network model is adjusted by the gene sequence, and the important features are used as input to perform model training on the BP neural network model; the prediction accuracy of the cultivation environment load in the model weight training is used as the fitness value, the hybrid rice is grouped into series, and the hybrid rice is updated and optimized based on different series groupings, and the BP neural network model is initially trained with the updated and optimized hybrid rice; when the detection update optimization process triggers a termination condition, the update optimization is stopped, the optimal weight parameter configuration of the BP neural network is output, and the important features are input into the BP neural network model with the optimal weight parameter configuration to determine the air conditioning operation plan of the cultivation environment. This enables real-time data to predict the load of the corresponding room. The system can automatically adjust the start and stop time of the air conditioner based on the predicted load demand, ensuring that the air conditioner starts and stops at the appropriate time to avoid unnecessary energy consumption.

[0080] See also Figure 3 , Figure 3Schematic diagram of a load forecasting system based on hybrid rice algorithm optimization provided in the embodiment of the present application. Figure 3 As shown, the system comprises:

[0081] The acquisition module S201 is used to acquire the associated parameters of the hybrid rice cultivation environment and pre-process the associated parameters, wherein the associated parameters include air conditioning operation parameters and environmental parameters;

[0082] An evaluation module S202 is used to evaluate the importance of the associated parameters through a preset algorithm, determine the important features in the associated parameters, and construct a BP neural network model for predicting the cultivation environment load based on the number of the important features as a dimension;

[0083] The weight module S203 is used to obtain and initialize the gene sequence of hybrid rice, adjust the initial weight of the BP neural network model with the gene sequence, and use the important features as input to perform model training on the BP neural network model;

[0084] The training module S204 is used to group the hybrid rice into different lines using the prediction accuracy of the cultivation environment load in the model weight training as the fitness value, and to update and optimize the hybrid rice based on different line groups, and to perform initial weight training on the BP neural network model using the updated and optimized hybrid rice;

[0085] The output module S205 is used to stop the update optimization when the detection update optimization process triggers the termination condition, output the optimal weight parameter configuration of the BP neural network, and input the important features into the BP neural network model with the optimal weight parameter configuration to determine the air conditioning operation plan of the cultivation environment.

[0086] In one embodiment, the system further comprises:

[0087] A first optimization module is used to hybridize the sterile line with the maintainer line, and determine whether to update and optimize the sterile line based on the fitness value of the hybridization result;

[0088] The second optimization module is used to perform self-pollination on the restoration line and determine whether to update and optimize the restoration line based on the maximum number of self-pollination times.

[0089] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (Field-Programmable Gate Array, FPGA), an integrated circuit (Integrated Circuit, IC), etc.

[0090] Each processing unit and / or module of the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0091] See also Figure 3 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, the electronic device can be used to implement Figure 1 The method in the embodiment shown. Figure 3 As shown, the electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0092] The communication bus 302 is used to realize the connection and communication between these components.

[0093] The user interface 303 may include a display screen (Display) and a camera (Camera). The optional user interface 303 may also include a standard wired interface and a wireless interface.

[0094] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0095] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts of the entire electronic device 300, and executes various functions and processes data of the terminal 300 by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or more combinations of processors (Central Processing Unit, CPU), image processors (Graphics Processing Unit, GPU) and modems. Among them, the CPU mainly processes operating systems, user interfaces, and applications; the GPU is responsible for rendering and drawing the content that needs to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0096] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 305 may also be optionally at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0097] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the interactive application based on image generation stored in the memory 305, and specifically perform the following operations: obtain the inspection image collected when the drone performs the inspection task, and the inspection route corresponding to the inspection task, and determine the image position corresponding to the inspection image and the environmental information of the image position in combination with the identification target in the inspection image; detect the clarity score of the inspection image, when the clarity score is lower than the preset score, establish a training image data set based on the clarity score, construct a first neural network model, use the blurred image as input data and the clear image as output data, back propagate and optimize the weights, and obtain the trained first neural network model, the training image data set includes the blurred image and the clear image; input the environmental information and the clarity score into the second neural network model for training, and iterate the training to obtain the trained second neural network model; when a real-time inspection task is received, obtain the real-time environmental information of the route corresponding to the real-time inspection task, input the real-time environmental information into the second neural network model, output the estimated clarity score, and configure the corresponding first neural network model based on the estimated clarity score to enhance the captured image in real time.

[0098] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0099] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0100] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0101] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0104] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program code.

[0105] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct the relevant hardware. The program may be stored in a computer-readable memory, and the memory may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0106] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A load forecasting method based on hybrid rice algorithm optimization, characterized in that: include: Acquiring correlation parameters of a hybrid rice cultivation environment and preprocessing the correlation parameters, wherein the correlation parameters include air conditioning operation parameters and environmental parameters; The importance of the associated parameters is evaluated by a preset algorithm, the important features in the associated parameters are determined, and the number of the important features is used as a dimension to construct a BP neural network model for predicting the cultivation environment load; Obtaining a gene sequence of hybrid rice and initializing it, adjusting the initial weight of the BP neural network model with the gene sequence, taking the important features as input, and performing model training on the BP neural network model; The prediction accuracy of the cultivation environment load in the model weight training is used as the fitness value, the hybrid rice is grouped into different lines, and the hybrid rice is updated and optimized based on different line groups, and the BP neural network model is initially trained with the updated and optimized hybrid rice; When the detection update optimization process triggers the termination condition, the update optimization is stopped, the optimal weight parameter configuration of the BP neural network is output, the important features are input into the BP neural network model with the optimal weight parameter configuration, and the air conditioning operation plan of the cultivation environment is determined.

2. The load forecasting method based on hybrid rice algorithm optimization according to claim 1, characterized in that: The department groups include: Maintainer lines, restorer lines and sterile lines; The method of renewing and optimizing the hybrid rice based on different lineage groups comprises: hybridizing the sterile line with the maintainer line, and judging whether to update and optimize the sterile line based on the fitness value of the hybridization result; The restoration line is self-pollinated, and whether to update and optimize the restoration line is determined based on the maximum number of self-pollinations.

3. The load forecasting method based on hybrid rice algorithm optimization according to claim 2, characterized in that: The step of hybridizing the sterile line with the maintainer line and judging whether to update and optimize the sterile line based on the fitness value of the hybridization result comprises: The sterile line and the maintainer line are hybridized by a hybridization formula, and the fitness value of the offspring rice seeds in the hybridization result is detected based on the BP neural network model, and when the fitness value is greater than the fitness value of the maintainer line, the sterile line is replaced with the offspring rice seeds, otherwise the sterile line is retained; The hybridization formula includes: Among them, the above formula is the process of hybridization in the tth generation, is the dth gene in the gene sequence of the i-th rice seed in the sterile line, is the dth gene in the k2th rice seed gene sequence selected from the maintainer line, is the dth gene in the k2th rice seed gene sequence selected from the sterile line, r2 and r3 are random numbers in the range of [-1, 1], and r2+r3≠0.

4. The load forecasting method based on hybrid rice algorithm optimization according to claim 2, characterized in that: The selfing of the restorer line and judging whether to update and optimize the restorer line based on the maximum number of selfings include: When the restorer line completes selfing, determining whether the number of selfing of the restorer line reaches a preset maximum number of selfings, and if it does not reach the preset maximum number of selfings, the restorer line self-pollinates according to a selfing formula to produce progeny rice seeds; The self-intersection formula includes: in, Represents the i-th recovery system New individuals produced by self-fertilization represents the kth individual randomly selected from the recovery line, r4 is a uniform random number in the range of [0, 1], x best represents the current optimal individual; The fitness value of the offspring rice seeds in the self-pollination results is detected based on the BP neural network model, and the fitness value of the offspring rice seeds is compared with that of the previous generation rice seeds. When the fitness value of the offspring rice seeds is high, the offspring rice seeds are used to update and optimize the previous generation rice seeds and the number of self-pollination is set to 0. Otherwise, the previous generation rice seeds are retained and the number of self-pollination is increased by 1.

5. The load forecasting method based on hybrid rice algorithm optimization according to claim 4 is characterized in that: The method further comprises: When it is detected that the number of self-pollination reaches the maximum number of self-pollination, the rice seeds are reset by the following formula: in, Restore system New rice seeds generated by the reset operation, x min 、x max are the upper and lower limits of gene quantization, and r5 is a uniform random number in the range of [0, 1].

6. The load forecasting method based on hybrid rice algorithm optimization according to claim 1, characterized in that: The step of inputting the important features into the BP neural network model configured with the optimal weight parameters to determine the air conditioning operation plan of the cultivation environment includes: Inputting the important features into the BP neural network model configured with optimal weight parameters to obtain the output final load forecast result; The load type and load value of the load forecast result are detected, and the air conditioning operation plan of the cultivation environment is determined in combination with the environmental parameters.

7. A load forecasting system based on hybrid rice algorithm optimization, characterized in that: The system comprises: An acquisition module, used for acquiring the associated parameters of the hybrid rice cultivation environment and preprocessing the associated parameters, wherein the associated parameters include air conditioning operation parameters and environmental parameters; An evaluation module, used to evaluate the importance of the associated parameters through a preset algorithm, determine the important features in the associated parameters, and construct a BP neural network model for predicting the cultivation environment load with the number of the important features as a dimension; A weight module, used for obtaining and initializing the gene sequence of hybrid rice, adjusting the initial weight of the BP neural network model with the gene sequence, taking the important features as input, and performing model training on the BP neural network model; A training module, for grouping the hybrid rice by strain using the prediction accuracy of the cultivation environment load in the model weight training as the fitness value, and updating and optimizing the hybrid rice based on different strain groups, and performing initial weight training on the BP neural network model through the updated and optimized hybrid rice; The output module is used to stop the update optimization when the detection update optimization process triggers the termination condition, output the optimal weight parameter configuration of the BP neural network, input the important features into the BP neural network model with the optimal weight parameter configuration, and determine the air conditioning operation plan of the cultivation environment.

8. The load forecasting system based on hybrid rice algorithm optimization according to claim 1, characterized in that: The system further comprises: A first optimization module is used to hybridize the sterile line with the maintainer line, and determine whether to update and optimize the sterile line based on the fitness value of the hybridization result; The second optimization module is used to perform self-pollination on the restoration line and determine whether to update and optimize the restoration line based on the maximum number of self-pollination times.

9. An electronic device comprising a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 6 when executed by a processor.

Images