Crop water-saving irrigation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of agricultural water-saving irrigation, in particular to a crop water-saving irrigation method and device, electronic equipment and a storage medium. Analyzing the growth speed of the crops according to the crop growth amount data queue to obtain the growth characteristics and growth stages of the crops; performing periodic feature extraction on the plurality of factor data queues to obtain a plurality of first factor features; finally, the growth characteristics, the growth stages and the multiple factor characteristics are input into a growth trend analysis model, and an irrigation strategy is optimized through the growth trend analysis model. According to the method, the irrigation strategy is optimized by inputting the analyzed crop growth characteristics, the growth stages and the state characteristics of the factors into the growth trend analysis model constructed through the artificial neural network, and the dual purposes of guaranteeing the yield and saving water are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of agricultural water-saving irrigation technology, and in particular to a crop water-saving irrigation method, device, electronic equipment and storage medium. BACKGROUND

[0002] With the increasingly serious global climate change and water resource shortage problem, agricultural water-saving irrigation technology has become an important direction of global agricultural development. In particular, in arid and semi-arid areas, the development and application of water-saving irrigation technology is particularly important. The popularization and application of water-saving irrigation technology is of great significance.

[0003] Water-saving irrigation technology has experienced a development process from traditional irrigation methods to modernization and intelligentization. Traditional irrigation methods, such as flood irrigation, not only waste water resources, but also easily lead to soil salinization and other problems. Modern water-saving irrigation technologies, such as sprinkling irrigation, drip irrigation, and micro-spraying irrigation, significantly improve the utilization efficiency of irrigation water by reducing the loss and evaporation of irrigation water.

[0004] However, due to the lack of professional knowledge and special skills of farmers, they cannot choose the corresponding water-saving irrigation form when irrigating in different environments; they cannot determine the influence of irrigation and fertilization scheme on crop yield.

[0005] Therefore, it is necessary to develop a crop water-saving irrigation method. SUMMARY

[0006] The present application provides a crop water-saving irrigation method, device, electronic equipment and storage medium, which solves the problem that the crop irrigation strategy in the prior art cannot balance water saving and crop yield.

[0007] In a first aspect, the present application provides a crop water-saving irrigation method, comprising: obtaining a plurality of influence factors affecting crop growth; analyzing the growth speed of the crop according to the crop growth amount data queue to obtain the growth characteristics and growth stage of the crop; periodically extracting a plurality of factor characteristics from a plurality of factor data queues, wherein the factor data queue is obtained according to the influence factor, and each factor characteristic corresponds to an influence factor; inputting the growth characteristics, the growth stage and the plurality of factor characteristics into a growth trend analysis model, and optimizing the irrigation strategy through the growth trend analysis model, wherein the growth trend analysis model determines the growth trend of the crop according to the growth law of the crop and the trend of a plurality of factors.

[0008] In a possible implementation, the growth speed of the crop is analyzed according to the crop growth data queue, the growth characteristics and the growth stage of the crop are obtained, and the method comprises the following steps of: According to the length of the first time period, the crop growth data queue is divided into a plurality of first sub-queues; For each first sub-queue, a plurality of growth basic models are respectively fitted, and a model with the minimum deviation is selected from the plurality of growth basic models as a candidate model; According to the fitting deviations, a model with the minimum comprehensive fitting deviation is selected from the plurality of candidate models as a target model; The target model is fitted by using the crop growth data queue, and a crop growth characteristic model is obtained; According to the last crop growth data and the crop growth characteristic model, the growth stage and the growth characteristics of the crop are determined, wherein the last crop growth data is the data at the end of the crop growth data queue.

[0009] In a possible implementation, for each first sub-queue, a plurality of growth basic models are respectively fitted, and a model with the minimum deviation is selected from the plurality of growth basic models as a candidate model, which comprises the following steps of: For each first sub-queue, the following steps are performed: A model is taken out from the plurality of growth basic models as a to-be-fitted model in a traversal manner; A plurality of parameter arrays are generated; The plurality of parameter arrays are respectively substituted into the to-be-fitted model, and a plurality of process models are obtained; For each process model, a plurality of data are extracted from the process model according to a plurality of time nodes corresponding to the first sub-queue, as a model queue; According to a first formula, the first sub-queue and the plurality of model queues, a plurality of process fitting deviations are determined, wherein each process fitting deviation corresponds to a process model, and the first formula is:

[0010] In the formula, Y is the process fitting deviation, X is the first data of the first sub-queue, Y is the first data of the model queue, and N is the total number of data in the first sub-queue. Each process fitting deviation is added to a corresponding fitting deviation queue. ​​​​​​If the number of iterations has not been reached, for each parameter array, a global optimal parameter array and a historical optimal parameter array are selected according to a plurality of fitting deviation queues and a plurality of process fitting deviations, the parameters in the array are adjusted according to the global optimal parameter array and the historical optimal parameter array, and the process jumps to the step of respectively substituting the plurality of parameter arrays into the models to be fitted to obtain a plurality of process models; otherwise, adding the minimum value among the plurality of process fitting deviations into a model deviation queue; If the traversal of the plurality of growth basic models is not completed, jumping to the step of traversally extracting a model from the plurality of growth basic models as a model to be fitted; Otherwise, the model corresponding to the minimum value in the model deviation queue is used as the candidate model.

[0011] In one possible implementation, performing periodic feature extraction on each of the multiple factor data queues to obtain multiple first factor features includes: For each factor data queue, perform the following steps: Obtaining a basic fluctuation period of an influencing factor corresponding to the factor data queue, and using a frequency corresponding to the basic fluctuation period as a reference frequency; Extracting multiple frequency amplitudes from the factor data queue according to the reference frequency, and constructing the obtained multiple frequency amplitudes into an amplitude vector; taking the comprehensive distances from the amplitude vector to the centers of a plurality of vector clusters as a plurality of reference distances, wherein the center of a vector cluster is the center of a vector cluster obtained by clustering a plurality of historical amplitude vectors; The vector class corresponding to the reference distance with the smallest value is used as the target class, and the identifier of the target class is used as the first factor feature of the factor data queue.

[0012] In one possible implementation, extracting multiple frequency amplitudes from the factor data queue according to the reference frequency includes: Extracting multiple frequency amplitudes from the factor data queue according to the second formula and the reference frequency includes:

[0013] Where, For the reference frequency The frequency amplitude of the doubled frequency, The first data, is the total number of data in the factor data queue, is a natural constant, is the imaginary unit, is the reference frequency, a number of data in the first data segment within a basic cycle length, pi is a constant; The comprehensive distance of the amplitude vector to the vector class center is a plurality of reference distances, comprising: Calculate the cosine distance of the amplitude vector to the vector class center as a plurality of first distances; Calculate the Euclidean distance of the amplitude vector to the vector class center as a plurality of second distances; Select the maximum distance and the minimum distance from the plurality of second distances as the maximum distance and the minimum distance; Determine the reference distance according to the third formula, the maximum distance, the minimum distance, the plurality of first distances and the plurality of second distances, wherein the third formula is:

[0014] In the formula, is the reference distance of the amplitude vector to the first vector class center, is the second distance of the amplitude vector to the first vector class center, is the maximum distance, is the minimum distance, is the first distance of the amplitude vector to the first vector class center.

[0015] In one possible implementation, the growth characteristics, the growth stage and the plurality of factor characteristics are input into a growth trend analysis model, and the irrigation strategy is optimized by the growth trend analysis model, comprising: Obtain a plurality of irrigation water quantity queues, soil texture and current soil moisture, wherein the plurality of data of the irrigation water quantity queue correspond to a plurality of time nodes; Each irrigation water quantity queue is input into a growth trend analysis model together with the soil texture, the current soil moisture, the growth characteristics, the growth stage and the plurality of factor characteristics as input data, and the output of the model is used as a crop growth speed estimate; A plurality of crop growth speed estimates are added to a plurality of estimation queues, wherein each estimation queue corresponds to an irrigation water quantity queue; The irrigation water quantity queue corresponding to the maximum crop growth speed estimate in the plurality of crop growth speed estimates is used as a target irrigation water quantity queue; If the number of iterations is not reached, adjusting, for each irrigation water quantity queue, according to a historical optimal irrigation water quantity queue and the target irrigation water quantity queue, wherein the historical optimal irrigation water quantity queue is a historical irrigation water quantity queue corresponding to a crop growth speed estimation with the largest queue median in the estimation queue; Otherwise, determining an irrigation strategy according to the target irrigation water quantity queue.

[0016] In a possible implementation, the growth trend analysis model is constructed based on an artificial neural network, comprising: Obtaining a plurality of crop growth samples, wherein each crop growth sample is a dataset constructed according to soil texture, irrigation strategy, soil moisture, crop growth characteristics, crop growth stage, and a plurality of factor characteristics, and each crop growth sample corresponds to a crop growth speed; Dividing the plurality of crop growth samples into a training group and a verification group; Iteratively inputting the crop growth samples of the training group into an artificial neural network model, adjusting a plurality of parameters of the artificial neural network model using gradient descent method according to a prediction error of the model, until the prediction error of the model is less than a first error threshold, and obtaining a training model, wherein the prediction error is determined according to a crop growth speed corresponding to the crop growth sample and a predicted crop growth speed of the model; Iteratively inputting the crop growth samples of the verification group into the training model, and determining a comprehensive prediction error of the training model; If the comprehensive prediction error is greater than a second error threshold, reducing the number of neurons in the artificial neural network model according to a deviation degree of the comprehensive prediction error from the second error threshold, wherein the second error threshold is greater than the first error threshold; Otherwise, taking the training model as the growth trend analysis model.

[0017] In a second aspect, an embodiment of the present application provides a crop water-saving irrigation device for implementing the crop water-saving irrigation method in the first aspect or any possible implementation manner of the first aspect, and the crop water-saving irrigation device comprises: A factor obtaining module is configured to obtain a plurality of influence factors affecting crop growth; A crop growth characteristic analysis module is configured to analyze a growth speed of the crop according to the crop growth quantity data queue, and obtain growth characteristics and a growth stage of the crop; A factor analysis module is configured to perform periodic feature extraction on the plurality of factor data queues respectively, and obtain a plurality of first factor characteristics, wherein the factor data queue is obtained according to the influence factor, and each factor characteristic corresponds to an influence factor; and, An irrigation strategy determination module is configured to input the growth characteristics, the growth stage and the plurality of factor characteristics into a growth trend analysis model, and to optimize an irrigation strategy by the growth trend analysis model, wherein the growth trend analysis model determines a growth trend of the crop according to a growth rule of the crop and a state of the plurality of factors.

[0018] In a third aspect, an electronic device is provided, which includes a memory and a processor, the memory storing a computer program capable of running on the processor, and the processor implements the steps of the method according to the first aspect or any possible implementation manner of the first aspect when executing the computer program.

[0019] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program implements the steps of the method according to the first aspect or any possible implementation manner of the first aspect when executed by a processor.

[0020] Compared with the prior art, the embodiments of the present application have the following beneficial effects: The embodiments of the present application disclose a crop water-saving irrigation method, which first acquires a plurality of influencing factors affecting crop growth; then analyzes the growth speed of the crop according to a crop growth quantity data queue to obtain growth characteristics and a growth stage of the crop; then performs periodic feature extraction on a plurality of factor data queues to obtain a plurality of first factor characteristics, wherein the factor data queue is acquired according to the influencing factors, and each factor characteristic corresponds to an influencing factor; and finally inputs the growth characteristics, the growth stage and the plurality of factor characteristics into a growth trend analysis model to optimize an irrigation strategy by the growth trend analysis model, wherein the growth trend analysis model determines a growth trend of the crop according to a growth rule of the crop and a state of the plurality of factors. The method of the present application inputs the analyzed crop growth characteristics, growth stage and state characteristics of factors into a growth trend analysis model constructed by an artificial neural network to optimize the irrigation strategy, and realizes the dual goals of guaranteeing yield and saving water. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0022] Figure 1 is a flowchart of the crop water-saving irrigation method provided by the embodiments of the present application; Figure 2 is a crop growth characteristic model construction process principle diagram provided by the embodiment of the present application; Figure 3 is a crop water-saving irrigation device function block diagram provided by the embodiment of the present application; Figure 4 is an electronic device function block diagram provided by the embodiment of the present application. DETAILED DESCRIPTION

[0023] In the following description, for the purpose of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0024] In order to make the objects, technical solutions and advantages of the present application clearer, the following will be described by specific embodiments in conjunction with the accompanying drawings.

[0025] The following will be described in detail for the embodiments of the present application, and the present example is implemented on the premise of the technical solutions of the present application, and detailed implementation manners and specific operation processes are given, but the protection scope of the present application is not limited to the following embodiments.

[0026] Figure 1 is a flow chart of a crop water-saving irrigation method provided by the embodiment of the present application.

[0027] As shown in Figure 1 , it shows an implementation flow chart of a crop water-saving irrigation method provided by the embodiment of the present application, and the details are as follows: In step 101, a plurality of influence factors affecting crop growth are obtained.

[0028] In step 102, the growth speed of the crop is analyzed according to the crop growth amount data queue, and the growth characteristics and growth stage of the crop are obtained.

[0029] In some embodiments, the growth speed of the crop is analyzed according to the crop growth amount data queue, and the growth characteristics and growth stage of the crop are obtained, including: According to the first time period length, the crop growth amount data queue is divided into a plurality of first sub-queues; For each first sub-queue, a plurality of growth basic models are respectively fitted, and the model with the smallest deviation is selected from the plurality of growth basic models as a candidate model; According to the plurality of fitting deviations, the model with the smallest comprehensive fitting deviation is selected from the plurality of candidate models as a target model; Fitting the target model using the crop growth data queue to obtain a crop growth characteristic model; The growth stage and growth characteristics of the crop are determined according to the last crop growth data and the crop growth characteristic model, wherein the last crop growth data is the last data in the crop growth data queue.

[0030] In some embodiments, for each first sub-queue, fitting multiple basic growth models respectively, and selecting a model with the smallest deviation from the multiple basic growth models as a candidate model includes: For each first sub-queue, perform the following steps: ergodicly extracting a model from the plurality of growth basic models as a model to be fitted; Generate multiple parameter arrays; Substituting the multiple parameter arrays into the models to be fitted respectively to obtain multiple process models; For each process model, extract multiple data from the process model according to multiple time nodes corresponding to the first sub-queue as a model queue; A plurality of process fitting deviations are determined according to a first formula, a first subqueue, and a plurality of model queues, wherein each process fitting deviation corresponds to a process model, and the first formula is:

[0031] Where, is the process fitting deviation, The first sub-queue data, The first data, is the total number of data in the first subqueue; Add each process fitting deviation to the corresponding fitting deviation queue; If the number of iterations has not been reached, for each parameter array, a global optimal parameter array and a historical optimal parameter array are selected according to a plurality of fitting deviation queues and a plurality of process fitting deviations, the parameters in the array are adjusted according to the global optimal parameter array and the historical optimal parameter array, and the process jumps to the step of respectively substituting the plurality of parameter arrays into the models to be fitted to obtain a plurality of process models; otherwise, adding the minimum value among the plurality of process fitting deviations into a model deviation queue; If the traversal of the plurality of growth basic models is not completed, jumping to the step of traversally extracting a model from the plurality of growth basic models as a model to be fitted; Otherwise, the model corresponding to the minimum value in the model deviation queue is taken as the candidate model.

[0032] Exemplarily, the embodiment of the present application aims to provide a method for determining the irrigation strategy of crops according to the variation law of the growth characteristics, growth stage and external influencing factors of crops.

[0033] In terms of the growth characteristics and growth stage, the growth characteristics and current growth stage of crops are determined according to the growth curve by selecting an adaptive growth curve from several typical growth curves. In terms of the variation law of external influencing factors, the fluctuation analysis is performed according to the factor monitoring data in the previous period of time and is classified into a factor state, for example, the influencing factors include air temperature, light intensity, wind speed and air humidity. Taking the air temperature as an example, the monitoring data in the previous week is subjected to fluctuation analysis to determine the state characteristics of the current air temperature condition. In terms of determining the irrigation strategy of crops, the growth characteristics, current growth stage and state characteristics of external factors obtained in the foregoing steps are sent into the crop growth speed prediction model constructed based on an artificial neural network together with the irrigation strategy, the irrigation strategy is optimized, and thus a better irrigation strategy is determined.

[0034] In order to achieve the above-mentioned purposes, as shown in the accompanying drawings, Figure 2 Specifically, in terms of determining the growth characteristics and current growth stage of crops, the crop growth amount data (growth amount data determined according to the plant height, diameter, plant coverage area, leaf area or leaf number of crops in some scenarios) observed in the previous period of time is arranged in sequence to obtain a crop growth amount data queue 201, a plurality of first sub-queues 202 are obtained by dividing the crop growth amount data queue 201, a growth basic model 203 is fitted for each first sub-queue 202, the most adaptive model 205 for the first sub-queue 202 is selected from a plurality of fitting deviations 204, and finally the model with the best comprehensive adaptability is selected from the adaptive models of the plurality of first sub-queues as the growth characteristics model of crops.

[0035] In terms of the basic model, the common linear model has the following form:

[0036] In the formula, is the crop growth amount data, is the initial value, is the growth rate constant, is the time.

[0037] The Logistic model has the following form:

[0038] In the formula, crop growth data, initial crop growth constant, intrinsic growth rate constant, maximum crop growth.

[0039] There is an exponential growth model, which is as follows:

[0040] In the formula, crop growth data, initial crop growth, exponential growth rate constant, time.

[0041] For the above basic model, when fitting through the first sub-queue, the parameters in the model (such as the parameters in the formula , , ) are set, then according to the time node corresponding to the data in the first sub-queue as the model input, the output obtained is sorted according to the time node, and the fitting deviation is calculated by using the first formula:

[0042] In the formula, process fitting deviation, the first data in the first sub-queue, the first data in the model queue, the total number of data in the first sub-queue. The fitting deviation is used as the basis for modifying the parameters of the model to adjust the parameters of the model.

[0043] In some methods, for the same model, multiple models are generated at the same time, and the fitting deviations of multiple models are obtained by the first formula. The parameters are adjusted by the model with the smallest fitting deviation and the historical optimal model with the smallest deviation in the previous iteration. The specific adjustment method can be a particle swarm optimization algorithm or a grey wolf algorithm.

[0044] After several iterations, the first sub-queue selects the model with the smallest fitting deviation from the above basic model, and then finds the model with the smallest comprehensive fitting deviation from multiple first sub-queues, which is the growth model of the crop. After the growth model is determined, the type of the model and the parameters related to the growth rate (such as ,

[0045] , ​) as the growth characteristic of the crop. Regarding the growth stage, the linear model has no obvious growth stage. For the logistic model, the ratio of the current crop growth data to the maximum crop growth data is used as its growth stage. For the exponential growth model, the ratio of its derivative to the exponential growth rate constant is used as its growth stage.

[0046] In step 103, periodic feature extraction is performed on the multiple factor data queues to obtain multiple first factor features, wherein the factor data queues are obtained according to influencing factors, and each factor feature corresponds to one influencing factor.

[0047] In some embodiments, performing periodic feature extraction on multiple factor data queues to obtain multiple first factor features includes: For each factor data queue, perform the following steps: Obtaining a basic fluctuation period of an influencing factor corresponding to the factor data queue, and using a frequency corresponding to the basic fluctuation period as a reference frequency; Extracting multiple frequency amplitudes from the factor data queue according to the reference frequency, and constructing the obtained multiple frequency amplitudes into an amplitude vector; taking the comprehensive distances from the amplitude vector to the centers of a plurality of vector clusters as a plurality of reference distances, wherein the center of a vector cluster is the center of a vector cluster obtained by clustering a plurality of historical amplitude vectors; The vector class corresponding to the reference distance with the smallest value is used as the target class, and the identifier of the target class is used as the first factor feature of the factor data queue.

[0048] In some embodiments, extracting multiple frequency amplitudes from the factor data queue according to the reference frequency includes: Extracting multiple frequency amplitudes from the factor data queue according to the second formula and the reference frequency includes:

[0049] Where, For the reference frequency The frequency amplitude of the doubled frequency, The first data, is the total number of data in the factor data queue, is a natural constant, is the imaginary unit, is the reference frequency, is the amount of data in the first data segment within the basic cycle duration, is pi; The comprehensive distances from the amplitude vector to the centers of multiple vector classes are used as multiple reference distances, including: Calculating cosine distances from the amplitude vector to centers of multiple vector classes as multiple first distances; Calculating the Euclidean distances from the amplitude vector to the centers of multiple vector classes as multiple second distances; Selecting a distance with a maximum value and a distance with a minimum value from the plurality of second distances as a maximum distance and a minimum distance; A reference distance is determined according to a third formula, the maximum distance, the minimum distance, the plurality of first distances, and the plurality of second distances, wherein the third formula is:

[0050] Where, is the magnitude vector to The reference distance of the vector cluster center, is the magnitude vector to The second distance between the centers of the vector classes, is the maximum distance, is the minimum distance, is the magnitude vector to The first distance between the centers of the vector classes.

[0051] For example, in determining the factor characteristics of each influencing factor, the present invention first defines a basic fluctuation period. For example, the fluctuation period of temperature is one day. The frequency corresponding to this period is used as the reference frequency. Then, the second formula is used to extract the amplitudes of multiple frequencies of the reference frequency:

[0052] Where, For the reference frequency The frequency amplitude of the doubled frequency, The first data, is the total number of data in the factor data queue, is a natural constant, is the imaginary unit, is the reference frequency, is the amount of data in the first data segment within the basic cycle duration, is pi.

[0053] Arrange the above amplitudes according to the number of times of frequency doubling to obtain an amplitude vector. This amplitude vector is then used to calculate the comprehensive distance with multiple class center vectors. The class where the class center with the smallest comprehensive distance is located is selected as its belonging class, and its class identifier is used as its factor feature. Among them, the comprehensive distance is a distance determined by Euclidean distance and cosine distance. Specifically, it is a distance obtained by normalizing the maximum and minimum values ​​in the Euclidean distance and subtracting the cosine distance. The formula is expressed as:

[0054] Where, is the magnitude vector to The reference distance of the vector cluster center, is the magnitude vector to The second distance between the centers of the vector classes, is the maximum distance, is the minimum distance, is the magnitude vector to The first distance between the centers of the vector classes.

[0055] As for the process of obtaining the class center, it is obtained by extracting the frequency amplitude of the historical factor data queue through the aforementioned process, constructing a historical amplitude vector, and obtaining a vector class by clustering multiple historical amplitude vectors.

[0056] In step 104, the growth characteristics, the growth stage, and the multiple factor characteristics are input into a growth trend analysis model, and the irrigation strategy is optimized through the growth trend analysis model, wherein the growth trend analysis model determines the growth trend of the crop based on the growth law of the crop and the status of multiple factors.

[0057] In some embodiments, inputting the growth characteristics, the growth stage, and the multiple factor features into a growth trend analysis model, and optimizing the irrigation strategy using the growth trend analysis model, comprises: Obtain multiple irrigation water queues, soil texture, and current soil moisture conditions, where multiple data of the irrigation water queues correspond to multiple time nodes; Inputting each irrigation water amount queue together with the soil texture, the current soil moisture condition, the growth characteristics, the growth stage, and the multiple factor characteristics into a growth trend analysis model as input data, and using the output of the model as a crop growth rate estimate; Adding multiple crop growth rate estimates to multiple estimation queues accordingly, wherein each estimation queue corresponds to an irrigation water amount queue; taking the irrigation water quantity queue corresponding to the crop growth rate estimate with the largest median value among the plurality of crop growth rate estimates as the target irrigation water quantity queue; If the number of iterations is not reached, for each irrigation water quantity queue, adjusting according to a historical optimal irrigation water quantity queue and the target irrigation water quantity queue, wherein the historical optimal irrigation water quantity queue is a historical irrigation water quantity queue corresponding to a crop growth speed estimate with the largest queue median in the estimation queue; Otherwise, determining the irrigation strategy according to the target irrigation water quantity queue.

[0058] In some embodiments, the growth trend analysis model is constructed based on an artificial neural network, comprising: Obtaining a plurality of crop growth samples, wherein each crop growth sample is a dataset constructed according to soil texture, irrigation strategy, soil moisture, crop growth characteristics, crop growth stage, and a plurality of factor characteristics, and each crop growth sample corresponds to a crop growth speed; Dividing the plurality of crop growth samples into a training group and a validation group; Iteratively inputting the crop growth samples of the training group into the artificial neural network model, adjusting a plurality of parameters of the artificial neural network model using gradient descent method according to the prediction error of the model, until the prediction error of the model is less than a first error threshold, obtaining a training model, wherein the prediction error is determined according to the crop growth speed corresponding to the crop growth sample and the predicted crop growth speed of the model; Iteratively inputting the crop growth samples of the validation group into the training model, determining the comprehensive prediction error of the training model; If the comprehensive prediction error is greater than a second error threshold, reducing the number of neurons in the artificial neural network model according to the deviation degree of the comprehensive prediction error and the second error threshold, wherein the second error threshold is greater than the first error threshold; Otherwise, taking the training model as the growth trend analysis model.

[0059] For example, for optimizing the irrigation strategy, the present application initializes a plurality of irrigation water quantity queues, inputs each irrigation water quantity queue together with soil texture, current soil moisture, growth characteristics and growth stage obtained in the foregoing steps, and a plurality of factor characteristics as input data into the growth trend analysis model, and takes the output of the model as a crop growth speed estimate. From a plurality of growth speed estimates, select the estimate with the largest value, and take the irrigation water quantity queue of this estimate as the globally optimal irrigation water quantity queue. For each irrigation water quantity queue, adjust it with its historical optimal irrigation water quantity queue and the globally optimal irrigation water quantity queue. After adjustment, repeat the above process of inputting into the model. After such back-and-forth for a predetermined number of times, the final globally optimal irrigation water quantity queue is the target irrigation strategy.

[0060] For the growth trend analysis model, the present application is obtained by adjusting and training artificial neural network model based on crop growth samples. Specifically, the crop growth samples are constructed based on soil texture, irrigation strategy, soil moisture, crop growth characteristics, crop growth stage, and multiple factor characteristics, and each crop growth sample corresponds to a crop growth rate. The multiple crop growth samples are divided into a training group and a validation group. The training group is used to train the artificial neural network, so that the artificial neural network can accurately simulate the relationship between the crop growth sample and the crop growth rate. The validation group is used to verify whether the artificial neural network still has good effect on data other than the training group.

[0061] During training, the data of the training group is input into the artificial neural network model through traversal. According to the crop growth rate corresponding to the crop growth sample and the output result of the model, the prediction error is determined. Then, the parameters of the model are adjusted through gradient descent method. After adjustment, the input step of traversal is returned. This process is repeated until the prediction error reaches an acceptable level.

[0062] For the validation process, the crop growth samples of the validation group are input into the trained model through traversal. According to the output of the model and the corresponding crop growth rate of the validation group, the comprehensive prediction error of the model is determined. If the comprehensive prediction error is large, the number of neurons is reduced according to the size of the comprehensive error, usually the number of neurons in the hidden layer. After reduction, the training process is returned again. This process is repeated until the comprehensive prediction error is acceptable. The artificial neural network model is the growth trend analysis model.

[0063] In the embodiment of the crop water-saving irrigation method of the present application, multiple influencing factors affecting crop growth are first obtained. Then, the growth rate of the crop is analyzed according to the crop growth data queue to obtain the growth characteristics and growth stage of the crop. Then, the periodic characteristics of the multiple factor data queues are extracted to obtain multiple first factor characteristics. Each factor characteristic corresponds to an influencing factor. Finally, the growth characteristics, the growth stage, and the multiple factor characteristics are input into the growth trend analysis model to optimize the irrigation strategy through the growth trend analysis model. The growth trend analysis model determines the growth trend of the crop according to the growth law of the crop and the state of multiple factors. The method of the present application relies on inputting the analyzed crop growth characteristics, growth stage, and state characteristics of factors into the growth trend analysis model constructed by artificial neural network to optimize the irrigation strategy, achieving the dual goals of ensuring yield and saving water.

[0064] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0065] The following is the device embodiment of the present application, and for details not described in detail, please refer to the corresponding method embodiments described above.

[0066] Figure 3 is a functional block diagram of a crop water-saving irrigation device provided by the embodiments of the present application, referring to Figure 3 , the crop water-saving irrigation device comprises a factor acquisition module 301, a crop growth characteristic analysis module 302, a factor analysis module 303, and an irrigation strategy determination module 304, wherein: The factor acquisition module 301 is configured to acquire a plurality of influence factors affecting the growth of crops. The crop growth characteristic analysis module 302 is configured to analyze the growth speed of crops according to a crop growth amount data queue, and obtain the growth characteristics and growth stage of crops. The factor analysis module 303 is configured to perform periodic feature extraction on a plurality of factor data queues respectively, and obtain a plurality of first factor features, wherein the factor data queue is acquired according to the influence factor, and each factor feature corresponds to an influence factor. The irrigation strategy determination module 304 is configured to input the growth characteristics, the growth stage, and the plurality of factor features into a growth trend analysis model, and optimize the irrigation strategy through the growth trend analysis model, wherein the growth trend analysis model determines the growth trend of crops according to the growth law of crops and the trend of a plurality of factors.

[0067] Figure 4 is a functional block diagram of an electronic device provided by the embodiments of the present application. As shown in Figure 4 , the electronic device 4 of the embodiment comprises a processor 400 and a memory 401, and the memory 401 stores a computer program 402 which can run on the processor 400. The processor 400 implements the steps in the above-mentioned various crop water-saving irrigation methods and embodiments when executing the computer program 402, such as Figure 1 the steps 101 to 104 shown in the figure.

[0068] For example, the computer program 402 can be divided into one or more modules / units, which are stored in the memory 401 and executed by the processor 400 to complete the present application.

[0069] The electronic device 4 can be a desktop computer, a notebook computer, a palm computer, a cloud server, and the like. The electronic device 4 can include, but is not limited to, a processor 400 and a memory 401. Those skilled in the art can understand that Figure 4 The electronic device 4 is only an example and does not limit the electronic device 4, and can include more or less components than shown, or combine certain components, or different components, for example, the electronic device 4 can also include an input / output device, a network access device, a bus, and the like.

[0070] The processor 400 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, and the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0071] The memory 401 can be an internal storage unit of the electronic device 4, such as a hard disk or a memory of the electronic device 4. The memory 401 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like. Further, the memory 401 can include both the internal storage unit and the external storage device of the electronic device 4. The memory 401 is used to store the computer program 402 and other programs and data required by the electronic device 4. The memory 401 can also be used to temporarily store data that has been output or will be output.

[0072] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or software function unit. In addition, the specific name of each functional unit and module is only for the convenience of mutual distinction, and does not limit the protection scope of the present application. The specific working process of the unit and module in the above system can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

[0073] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0074] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0075] In the embodiments provided by the present application, it should be understood that the disclosed apparatus / equipment and method can be implemented in other ways. For example, the above-described apparatus / equipment embodiments are merely illustrative. For example, the division of the modules or units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or in other forms.

[0076] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment scheme.

[0077] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0078] The integrated module / unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method and device embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0079] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for water-saving irrigation of crops, characterized in that: include: Obtain multiple factors affecting crop growth; Analyze the growth rate of crops based on the crop growth data queue to obtain the growth characteristics and growth stages of crops; Performing periodic feature extraction on the multiple factor data queues to obtain multiple first factor features, wherein the factor data queues are obtained according to influencing factors, and each factor feature corresponds to one influencing factor; The growth characteristics, the growth stage and the characteristics of the multiple factors are input into a growth trend analysis model, and the irrigation strategy is optimized through the growth trend analysis model, wherein the growth trend analysis model determines the growth trend of the crop according to the growth law of the crop and the situation of multiple factors.

2. The crop water-saving irrigation method according to claim 1, characterized in that: The analysis of the crop growth rate based on the crop growth data queue to obtain the crop growth characteristics and growth stages includes: dividing the crop growth data queue into a plurality of first sub-queues according to a first time period length; For each first sub-cohort, multiple basic growth models are fitted respectively, and a model with the smallest deviation is selected from the multiple basic growth models as an alternative model; According to multiple fitting deviations, a model with the smallest comprehensive fitting deviation is selected from multiple alternative models as the target model; Fitting the target model using the crop growth data queue to obtain a crop growth characteristic model; The growth stage and growth characteristics of the crop are determined according to the last crop growth data and the crop growth characteristic model, wherein the last crop growth data is the last data in the crop growth data queue.

3. The crop water-saving irrigation method according to claim 2, characterized in that: The step of fitting multiple basic growth models for each first sub-queue and selecting a model with the smallest deviation from the multiple basic growth models as a candidate model includes: For each first sub-queue, perform the following steps: ergodicly extracting a model from the plurality of growth basic models as a model to be fitted; Generate multiple parameter arrays; Substituting the multiple parameter arrays into the models to be fitted respectively to obtain multiple process models; For each process model, extract multiple data from the process model according to multiple time nodes corresponding to the first sub-queue as a model queue; A plurality of process fitting deviations are determined according to a first formula, a first sub-queue, and a plurality of model queues, wherein each process fitting deviation corresponds to a process model, and the first formula is: Where, is the process fitting deviation, The first sub-queue data, The first data, is the total number of data in the first subqueue; Add each process fitting deviation to the corresponding fitting deviation queue; If the number of iterations has not been reached, for each parameter array, a global optimal parameter array and a historical optimal parameter array are selected according to a plurality of fitting deviation queues and a plurality of process fitting deviations, the parameters in the array are adjusted according to the global optimal parameter array and the historical optimal parameter array, and the process jumps to the step of respectively substituting the plurality of parameter arrays into the models to be fitted to obtain a plurality of process models; otherwise, adding the minimum value among the plurality of process fitting deviations into a model deviation queue; If the traversal of the plurality of growth basic models is not completed, jumping to the step of traversally extracting a model from the plurality of growth basic models as a model to be fitted; Otherwise, the model corresponding to the minimum value in the model deviation queue is used as the candidate model.

4. The crop water-saving irrigation method according to claim 1, characterized in that: The step of performing periodic feature extraction on the multiple factor data queues to obtain multiple first factor features includes: For each factor data queue, perform the following steps: Obtaining a basic fluctuation period of an influencing factor corresponding to the factor data queue, and using a frequency corresponding to the basic fluctuation period as a reference frequency; Extracting multiple frequency amplitudes from the factor data queue according to the reference frequency, and constructing the obtained multiple frequency amplitudes into an amplitude vector; taking the comprehensive distances from the amplitude vector to the centers of a plurality of vector clusters as a plurality of reference distances, wherein the center of a vector cluster is the center of a vector cluster obtained by clustering a plurality of historical amplitude vectors; The vector class corresponding to the reference distance with the smallest value is used as the target class, and the identifier of the target class is used as the first factor feature of the factor data queue.

5. The crop water-saving irrigation method according to claim 4, characterized in that: The extracting of multiple frequency amplitudes from the factor data queue according to the reference frequency includes: Extracting multiple frequency amplitudes from the factor data queue according to the second formula and the reference frequency includes: Where, For the reference frequency The frequency amplitude of the doubled frequency, The first data, is the total number of data in the factor data queue, is a natural constant, is the imaginary unit, is the reference frequency, is the amount of data in the first data segment within the basic cycle duration, is pi; The comprehensive distances from the amplitude vector to the centers of multiple vector classes are used as multiple reference distances, including: Calculating cosine distances from the amplitude vector to centers of multiple vector classes as multiple first distances; Calculating the Euclidean distances from the amplitude vector to the centers of multiple vector classes as multiple second distances; Selecting a distance with a maximum value and a distance with a minimum value from the plurality of second distances as a maximum distance and a minimum distance; A reference distance is determined according to a third formula, the maximum distance, the minimum distance, the plurality of first distances, and the plurality of second distances, wherein the third formula is: Where, is the magnitude vector to The reference distance of the vector cluster center, is the magnitude vector to The second distance between the centers of the vector classes, is the maximum distance, is the minimum distance, is the magnitude vector to The first distance between the centers of the vector classes.

6. The crop water-saving irrigation method according to any one of claims 1 to 5, characterized in that: Inputting the growth characteristics, the growth stage, and the multiple factor features into a growth trend analysis model, and optimizing the irrigation strategy through the growth trend analysis model, includes: Obtain multiple irrigation water queues, soil texture, and current soil moisture conditions, where multiple data of the irrigation water queues correspond to multiple time nodes; Inputting each irrigation water amount queue together with the soil texture, the current soil moisture condition, the growth characteristics, the growth stage, and the multiple factor characteristics into a growth trend analysis model as input data, and using the output of the model as a crop growth rate estimate; Adding multiple crop growth rate estimates to multiple estimation queues accordingly, wherein each estimation queue corresponds to an irrigation water amount queue; taking the irrigation water quantity queue corresponding to the crop growth rate estimate with the largest median value among the plurality of crop growth rate estimates as the target irrigation water quantity queue; If the number of iterations is not reached, then for each irrigation water amount queue, adjustments are made based on the historical optimal irrigation water amount queue and the target irrigation water amount queue, wherein the historical optimal irrigation water amount queue is the historical irrigation water amount queue corresponding to the crop growth rate estimate with the largest median value in the estimated queue; Otherwise, an irrigation strategy is determined according to the target irrigation water quantity queue.

7. The crop water-saving irrigation method according to claim 6, characterized in that: The growth trend analysis model is constructed based on an artificial neural network and includes: Acquire multiple crop growth samples, where each crop growth sample is a data set constructed based on soil texture, irrigation strategy, soil moisture, crop growth characteristics, crop growth stage, and multiple factor characteristics, and each crop growth sample corresponds to a crop growth rate; Dividing the plurality of crop growth samples into a training group and a validation group; ergodic inputting crop growth samples of a training group into an artificial neural network model, and adjusting multiple parameters of the artificial neural network model using a gradient descent method according to a prediction error of the model until the prediction error of the model is less than a first error threshold, thereby obtaining a training model, wherein the prediction error is determined based on a crop growth rate corresponding to the crop growth samples and a crop growth rate predicted by the model; traversally inputting the crop growth samples of the validation group into the training model to determine the comprehensive prediction error of the training model; If the comprehensive prediction error is greater than a second error threshold, reducing the number of neurons in the artificial neural network model according to the degree of deviation between the comprehensive prediction error and the second error threshold, wherein the second error threshold is greater than the first error threshold; Otherwise, the training model is used as the growth trend analysis model.

8. A crop water-saving irrigation device, characterized in that: Used to implement the crop water-saving irrigation method according to any one of claims 1 to 7, the crop water-saving irrigation device comprises: A factor acquisition module is used to obtain multiple factors affecting crop growth; The crop growth characteristic analysis module is used to analyze the growth rate of crops based on the crop growth data queue to obtain the growth characteristics and growth stages of crops; A factor analysis module is used to perform periodic feature extraction on multiple factor data queues to obtain multiple first factor features, wherein the factor data queues are obtained based on influencing factors, and each factor feature corresponds to an influencing factor; as well as, An irrigation strategy determination module is used to input the growth characteristics, the growth stage and the multiple factor characteristics into a growth trend analysis model, and optimize the irrigation strategy through the growth trend analysis model, wherein the growth trend analysis model determines the growth trend of the crop based on the growth law of the crop and the situation of multiple factors.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, 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