Efficient adjustable corn and soybean relay intercropping growth factor optimal configuration system

By designing an efficient and adjustable corn soybean condom growth factor optimization configuration system, using real-time acquisition and monitoring of growth status, and automatically adjusting light and other growth factors, the problem of low efficiency of corn-soybean condom in the existing technology is solved, achieving high efficiency , high-quality corn-soybean strip-shaped composite planting.

CN119073117AInactive Publication Date: 2024-12-06NINGXIA HUI AUTONOMOUS REGION WATER CONSERVANCY RES INST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411016216.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-27
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the prior art, corn-soybean strip-shaped composite planting has the problem of low efficiency, and it is difficult to achieve high yield and efficient corn-soybean condom growth.

Method used

A highly efficient and adjustable corn soybean set-up optimization configuration system is designed, including set-up growth factor acquisition device, status monitoring device, data processing unit and adjustment device. By collecting and monitoring the growth status in real time, the foldable and retractable sunlight is used. The reflector adjusts the light, combines the bee optimization algorithm to calculate growth factors, and automatically adjusts the light, temperature, water, humidity and other factors.

Benefits of technology

It realizes efficient and high-quality growth of corn and soybean conjunction, improves the yield and efficiency of corn-soybean strip-like composite planting, and reduces manual intervention and reduces equipment setup overhead by automatically adjusting growth factors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119073117A_ABST
    Figure CN119073117A_ABST
Patent Text Reader

Abstract

The invention relates to an efficient and adjustable corn and soybean relay intercropping growth factor optimal configuration system, and solves the technical problems that the scheme is complex, inaccurate and high in cost. A relay intercropping growth state monitoring device; the data processing unit is internally provided with an associated data algorithm library of growth factors and growth states; the control device is used for calculating target relay intercropping growth factors according to the growth cycle state and controlling the relay intercropping growth factor adjusting device to adjust real-time relay intercropping growth factor parameters; the relay intercropping growth factor adjusting device is used for adjusting relay intercropping growth factor parameters of corn and soybeans according to the control of the data processing unit; the relay intercropping growth factor adjusting device comprises an illumination adjusting device, the illumination adjusting device comprises a supporting rod arranged on the corn belt, the top of the supporting rod is provided with an angle-adjustable sunlight reflecting plate, and the angle of the sunlight reflecting plate is adjusted according to an illumination adjusting analysis result of the data processing unit; by means of the technical scheme, the problems are well solved, and the corn and soybean condom management device can be used for corn and soybean condom management.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of agricultural production, and in particular to a highly efficient and adjustable corn and soybean intercropping growth factor optimization configuration system. Background Art

[0002] The cultivated land area in my country is decreasing, while the population is increasing year by year, and the problem of grain production is becoming increasingly serious. Corn-soybean strip composite planting is one of the main modes of strip intercropping. In order to achieve high yield and high efficiency of corn-soybean strip composite planting, it is particularly important to carry out relevant theoretical and technical research on bandwidth optimization, group configuration, etc.

[0003] The present invention mainly provides a highly efficient and adjustable corn-soybean intercropping growth factor optimization configuration system, which is used to ensure the high quality and high efficiency of the corn-soybean intercropping growth. Summary of the invention

[0004] The technical problem to be solved by the present invention is the complex and inefficient technical problem existing in the prior art. A new high-efficiency and adjustable corn and soybean intercropping growth factor optimization configuration system is provided, which has the characteristics of simplicity and high efficiency.

[0005] In order to solve the above technical problems, the technical solutions adopted are as follows:

[0006] An efficient and adjustable corn and soybean intercropping growth factor optimization configuration system, comprising:

[0007] A device for collecting intercropping growth factors, used for collecting real-time parameters of intercropping growth factors;

[0008] Intercropping growth status monitoring device, used to collect and evaluate the growth cycle status of intercropped corn and soybeans;

[0009] A data processing unit, with a built-in data algorithm library for associating growth factors with growth states; used to calculate target intercropping growth factors according to the growth cycle state, and control the intercropping growth factor adjustment device to adjust the real-time intercropping growth factor parameters;

[0010] The intercropping growth factor adjustment device is used to adjust the intercropping growth factor parameters of corn and soybean according to the control of the data processing unit;

[0011] like Figure 2 The intercropping growth factor adjustment device includes a light adjustment device, which includes a support pole arranged on the corn belt, and a sunlight reflection plate with an adjustable angle is arranged on the top of the support pole. The angle of the sunlight reflection plate is adjusted according to the light adjustment analysis result of the data processing unit; the sunlight reflection plate is a foldable and telescopic structure.

[0012] Working principle of the present invention: The present invention collects growth factors of corn and soybean intercropping in real time, monitors and evaluates the growth status of corn and soybean, and automatically adjusts the growth factors according to the corresponding growth factors required by the historical growth status. The most important growth factor of corn and soybean intercropping is light, because the growth of corn during intercropping may have an important impact on the light of soybean. Therefore, the present invention provides a simple and efficient light adjustment device, that is, through a foldable and retractable sunlight reflection plate, the light of corn and soybean is adjusted according to the light time period and light area.

[0013] In the above scheme, for optimization, the intercropping growth status monitoring device includes a mobile mechanism, a visual acquisition device arranged on the mobile mechanism, and a solar power supply device for powering the intercropping growth status monitoring device, and the visual acquisition device is used to collect growth images of corn and soybeans.

[0014] The preferred solution can efficiently collect the growth images of corn and soybeans. In order to reduce the cost of equipment settings, a mobile acquisition device is selected. In addition to using video acquisition, infrared or tactile mechanisms can also be used to collect the characteristics of the growth appearance of corn and soybeans, thereby realizing the characteristic acquisition of the growth status.

[0015] Furthermore, the collection and evaluation of the growth cycle status of corn and soybeans is carried out in the following steps:

[0016] Step z1, processing and classifying the growth images of corn and soybean collected by the visual collection device to obtain corn growth images and soybean growth images, and performing feature sampling on the growth images, which is divided into time series sampling and space series sampling;

[0017] Step z2, define the covariance of the feature sampling data in the historical database and the corresponding growth state. There are K growth states in the feature sampling data in the historical database, and the sampling feature dimension is p. Define is the sample covariance matrix of the kth growth state in the historical database; for Diagonal element matrix in the matrix; calculate and estimate the characteristic variance matrix of the growth state

[0018]

[0019] in, is the sample covariance matrix of the kth growth state A matrix without diagonal elements; s ij express The element in row i and column j in Indicates seeking ijTwo different grouping states, T = {(i,j)|δ ij ≠0, i≠j}, δ ij express The value of the element in the jth row and jth column of the matrix;

[0020] Step z3, define the detection sliding window width W×L as the detection three-dimensional window, where W is the time sequence window and L is the space sequence window. Calculate the detection three-dimensional window W×L Indicates the matching degree between the growth state of the detected three-dimensional window and the k-th growth state;

[0021] It is the new sample co-matrix estimation of a single plant in different time ranges W under the time series window, is the new sample co-matrix estimation of different plant strains at the same time under the spatial sequence window L;

[0022]

[0023] Step z4, traverse K growth modes and obtain The minimum value of the element in G is used as the estimated result of the growth cycle state of corn and soybean.

[0024] The present invention designs a unique spatiotemporal estimation algorithm to estimate the growth state of corn or soybean, and abandons the inapplicability of single plant estimation for parameter adjustment of agricultural planting. The present application uses a window interception method to evaluate the growth state of corn or soybean in time and space, and determine the growth state. Through the comprehensive positioning of the growth state, it provides a strong basis for determining the target growth factor according to the growth state.

[0025] Further, the calculation of the target intercropping growth factor according to the growth cycle state includes:

[0026] Step m1, retrieve the intercropping growth factors required for the current growth state cycle and the corresponding impact weight values ​​of each factor according to the expert strategy or historical database;

[0027] Step m2, weighted calculation of an adjustment weight value based on the influence weight value of each growth factor combined with the economic loss value of the growth factor, if the adjustment weight value is lower than a predefined threshold, the growth factor is excluded from the adjustment range;

[0028] Step m3, taking the adjusted growth factor range obtained in step m2 as the target growth factor.

[0029] The present invention creatively weights the influencing factors and weights of the growth status, and introduces the economic loss value of parameter adjustment as an additional weighted factor, and does not adjust the factors that affect the growth but have obviously weak economic benefits.

[0030] Further, step m2 comprises:

[0031] Step s1, initialize the algorithm parameters, use the growth factors, corresponding influencing factors, and weight factors as three-dimensional coordinates to construct a weight parameter space model, characterize the economic loss value as the optimized path distance, determine the initial target and optimization target in the weight model parameter space, define m randomly distributed bee positions, the maximum number of iterations Gmax, and the maximum limit number Lmax;

[0032] Step s2, define α zi is the growth factor influencing factor, β zi is the weight factor corresponding to the impact factor, zi=1,2...zn;

[0033] Step s3, randomly distribute m bees, determine the initial position of the bees, and let the bees randomly select the next position point as the next node of the optimization path until the optimization goal is reached;

[0034] Step s4, for each bee, the initial iteration number G = 0, randomly generate zm search vectors in the search space, the distance dimension of the search space is D, and the search equation is defined as:

[0035]

[0036]

[0037] Among them, v ′ di represents the best position of the ith search when the search radius is d, v di The i-th search position when the search radius is d; is the optimal value among the normalized values ​​of the influence weights of all search positions when the search radius is d; di and x dj is the normalized value of the influence weight of the i-th search position and the normalized value of the influence weight of the j-th search position when the search radius is d, j≠i and j∈{1,2,3,...KN};

[0038] The influence weight normalized value function is: d=1,2,3...D;

[0039] cr is the crossover coefficient preset in the algorithm; ψ ′ is rand(-1,1); μ ′ is rand(0,K), where K is a predefined non-negative constant; rand(a d ,b d ) is a uniform random number function, indicating that in a d to b dPick a uniform random number between;

[0040] Among them, the probability of selecting the i-th search position as a path point is: is the normalized value of the influence weight of the i-th path point, KN is the number of next path points whose normalized value of influence weight is higher than the predefined threshold;

[0041] Step s5, updating the normalized value of the global influence weight;

[0042]

[0043] in, Indicates that in this iteration, the search between positions i and j is due to bee m k Increased influence weight normalization value, Δfit ij(g) represents the sum of normalized values ​​of the added influence weights, and g is the number of iterations;

[0044] Step s6, when the number of iterations g reaches the maximum number of iterations Gmax, the optimal path of the current bees is calculated. The optimal path is sorted by the influence weight / distance normalization function value, and the one with the highest sorting is taken as the optimal path;

[0045] Step s7, traverse all bees, calculate the optimal path distance of all bees, and the distance between the optimal path nodes of all bees, normalize the optimal path nodes into a grid, and select the shortest path as the parameter optimization adjustment strategy.

[0046] The present invention specifically realizes the weighted calculation of economic loss, influencing factors and weight coefficients through a unique algorithm, and equates economic loss to the optimized distance, thereby realizing an efficient and accurate comprehensive weighting method. It takes into account both the crop growth in the current window and the economic loss.

[0047] Furthermore, the growth factors include light, temperature, water, humidity, fertility, and drug control. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0049] Figure 1 , Schematic diagram of the efficient and adjustable corn-soybean intercropping growth factor optimization configuration system. Figure 2 , schematic diagram of the intercropping growth factor adjustment device. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] Example 1

[0052] This embodiment provides a highly efficient and adjustable system for optimizing the configuration of growth factors of corn and soybean intercropping. Figure 1 ,include:

[0053] A device for collecting intercropping growth factors, used for collecting real-time parameters of intercropping growth factors;

[0054] Intercropping growth status monitoring device, used to collect and evaluate the growth cycle status of intercropped corn and soybeans;

[0055] A data processing unit, with a built-in data algorithm library for associating growth factors with growth states; used to calculate target intercropping growth factors according to the growth cycle state, and control the intercropping growth factor adjustment device to adjust the real-time intercropping growth factor parameters;

[0056] The intercropping growth factor adjustment device is used to adjust the intercropping growth factor parameters of corn and soybean according to the control of the data processing unit;

[0057] The intercropping growth factor adjustment device includes a light adjustment device, which includes a support rod arranged on the corn belt, and a sunlight reflection plate with an adjustable angle is arranged on the top of the support rod. The angle of the sunlight reflection plate is adjusted according to the light adjustment analysis result of the data processing unit; the sunlight reflection plate is a foldable and telescopic structure.

[0058] This embodiment collects the growth factors of corn and soybean intercropping in real time, monitors and evaluates the growth status of corn and soybean, and automatically adjusts the growth factors according to the corresponding growth factors required by the historical growth status. The most important growth factor of corn and soybean intercropping is light, because the growth of corn during intercropping may have an important impact on the light of soybean. Therefore, the present invention provides a simple and efficient light adjustment device, that is, through a foldable and retractable sunlight reflection plate, the light of corn and soybean is adjusted according to the light period and light area.

[0059] Preferably, the intercropping growth status monitoring device includes a mobile mechanism, a visual acquisition device arranged on the mobile mechanism, and a solar power supply device for powering the intercropping growth status monitoring device, and the visual acquisition device is used to collect growth images of corn and soybeans.

[0060] The preferred solution can efficiently collect the growth images of corn and soybeans. In order to reduce the cost of equipment settings, a mobile acquisition device is selected. In addition to using video acquisition, infrared or tactile mechanisms can also be used to collect the characteristics of the growth appearance of corn and soybeans, thereby realizing the characteristic acquisition of the growth status.

[0061] Preferably, the collection and evaluation of the growth cycle status of corn and soybeans is carried out by the following steps:

[0062] Step z1, processing and classifying the growth images of corn and soybean collected by the visual collection device to obtain corn growth images and soybean growth images, and performing feature sampling on the growth images, which is divided into time series sampling and space series sampling;

[0063] Step z2, define the covariance of the feature sampling data in the historical database and the corresponding growth state. There are K growth states in the feature sampling data in the historical database, and the sampling feature dimension is p. Define is the sample covariance matrix of the kth growth state in the historical database; for Diagonal element matrix in the matrix; calculate and estimate the characteristic variance matrix of the growth state

[0064]

[0065] in, is the sample covariance matrix of the kth growth state A matrix without diagonal elements; s ij express The element in row i and column j in Indicates seeking ij Two different grouping states, T = {(i,j)|δ ij ≠0, i≠j}, δ ij express The value of the element in the jth row and jth column of the matrix;

[0066] Step z3, define the detection sliding window width W×L as the detection three-dimensional window, where W is the time sequence window and L is the space sequence window. Calculate the detection three-dimensional window W×L Indicates the matching degree between the growth state of the detected three-dimensional window and the k-th growth state;

[0067] It is the new sample co-matrix estimation of a single plant in different time ranges W under the time series window, is the new sample co-matrix estimation of different plant strains at the same time under the spatial sequence window L;

[0068]

[0069] Step z4, traverse K growth modes and obtain The minimum value of the element in G is used as the estimated result of the growth cycle state of corn and soybean.

[0070] The present invention designs a unique spatiotemporal estimation algorithm to estimate the growth state of corn or soybean, and abandons the inapplicability of single plant estimation for parameter adjustment of agricultural planting. The present application uses a window interception method to evaluate the growth state of corn or soybean in time and space, and determine the growth state. Through the comprehensive positioning of the growth state, it provides a strong basis for determining the target growth factor according to the growth state.

[0071] Preferably, the step of calculating the target intercropping growth factor according to the growth cycle state comprises:

[0072] Step m1, retrieve the intercropping growth factors required for the current growth state cycle and the corresponding impact weight values ​​of each factor according to the expert strategy or historical database;

[0073] Step m2, weighted calculation of an adjustment weight value based on the influence weight value of each growth factor combined with the economic loss value of the growth factor, if the adjustment weight value is lower than a predefined threshold, the growth factor is excluded from the adjustment range;

[0074] Step m3, taking the adjusted growth factor range obtained in step m2 as the target growth factor.

[0075] The present invention creatively weights the influencing factors and weights of the growth status, and introduces the economic loss value of parameter adjustment as an additional weighted factor, and does not adjust the factors that affect the growth but have obviously weak economic benefits.

[0076] Preferably, step m2 comprises:

[0077] Step s1, initialize the algorithm parameters, use the growth factors, corresponding influencing factors, and weight factors as three-dimensional coordinates to construct a weight parameter space model, characterize the economic loss value as the optimized path distance, determine the initial target and optimization target in the weight model parameter space, define m randomly distributed bee positions, the maximum number of iterations Gmax, and the maximum limit number Lmax;

[0078] Step s2, define α zi is the growth factor influencing factor, β zi is the weight factor corresponding to the impact factor, zi=1,2...zn;

[0079] Step s3, randomly distribute m bees, determine the initial position of the bees, and let the bees randomly select the next position point as the next node of the optimization path until the optimization goal is reached;

[0080] Step s4, for each bee, the initial iteration number G = 0, randomly generate zm search vectors in the search space, the distance dimension of the search space is D, and the search equation is defined as:

[0081]

[0082]

[0083] Among them, v ′ di represents the best position of the ith search when the search radius is d, v di The i-th search position when the search radius is d; is the optimal value among the normalized values ​​of the influence weights of all search positions when the search radius is d; di and x dj is the normalized value of the influence weight of the i-th search position and the normalized value of the influence weight of the j-th search position when the search radius is d, j≠i and j∈{1,2,3,...KN};

[0084] The influence weight normalized value function is: d=1,2,3...D;

[0085] cr is the crossover coefficient preset in the algorithm; ψ ′ is rand(-1,1); μ ′ is rand(0,K), where K is a predefined non-negative constant; rand(a d ,b d ) is a uniform random number function, indicating that in a d to b d Pick a uniform random number between;

[0086] Among them, the probability of selecting the i-th search position as a path point is: fz i is the normalized value of the influence weight of the i-th path point, KN is the number of next path points whose normalized value of influence weight is higher than the predefined threshold;

[0087] Step s5, updating the normalized value of the global influence weight;

[0088]

[0089] in, Indicates that in this iteration, the search between positions i and j is due to bee m k Increased influence weight normalization value, Δfit ij(g) represents the sum of normalized values ​​of the added influence weights, and g is the number of iterations;

[0090] Step s6, when the number of iterations g reaches the maximum number of iterations Gmax, the optimal path of the current bees is calculated. The optimal path is sorted by the influence weight / distance normalization function value, and the one with the highest sorting is taken as the optimal path;

[0091] Step s7, traverse all bees, calculate the optimal path distance of all bees, and the distance between the optimal path nodes of all bees, normalize the optimal path nodes into a grid, and select the shortest path as the parameter optimization adjustment strategy.

[0092] The present invention specifically realizes the weighted calculation of economic loss, influencing factors and weight coefficients through a unique algorithm, and equates economic loss to the optimized distance, thereby realizing an efficient and accurate comprehensive weighting method. It takes into account both the crop growth in the current window and the economic loss.

[0093] Specifically, the growth factors include light, temperature, water, humidity, fertility, and drug control.

[0094] This embodiment does not elaborate on the modules and devices of the prior art. Although the above describes the illustrative specific implementations of the present invention so that those skilled in the art can understand the present invention, the present invention is not limited to the scope of the specific implementations. For those skilled in the art, as long as the various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, all inventions and creations using the concept of the present invention are protected.

Claims

1. An efficient and adjustable system for optimizing the growth factors of corn and soybean intercropping. Features: The corn and soybean intercropping growth factor optimization configuration system comprises: A device for collecting intercropping growth factors, used for collecting real-time parameters of intercropping growth factors; Intercropping growth status monitoring device, used to collect and evaluate the growth cycle status of intercropped corn and soybeans; A data processing unit, with a built-in data algorithm library for associating growth factors with growth states; used to calculate target intercropping growth factors according to the growth cycle state, and control the intercropping growth factor adjustment device to adjust the real-time intercropping growth factor parameters; The intercropping growth factor adjustment device is used to adjust the intercropping growth factor parameters of corn and soybean according to the control of the data processing unit; The intercropping growth factor adjustment device includes a light adjustment device, which includes a support rod arranged on the corn belt, and a sunlight reflection plate with an adjustable angle is arranged on the top of the support rod. The angle of the sunlight reflection plate is adjusted according to the light adjustment analysis result of the data processing unit; the sunlight reflection plate is a foldable and telescopic structure.

2. The highly efficient and adjustable corn and soybean intercropping growth factor optimization configuration system according to claim 1, Features: The intercropping growth status monitoring device comprises a mobile mechanism, a visual collection device arranged on the mobile mechanism, and a solar power supply device for supplying power to the intercropping growth status monitoring device, wherein the visual collection device is used to collect growth images of corn and soybeans.

3. The efficient and adjustable corn-soybean intercropping growth factor optimization configuration system according to claim 2, Features: The following steps are used to collect and evaluate the growth cycle status of corn and soybeans: Step z1, processing and classifying the growth images of corn and soybean collected by the visual collection device to obtain corn growth images and soybean growth images, and performing feature sampling on the growth images, which is divided into time series sampling and space series sampling; Step z2, define the covariance of the feature sampling data in the historical database and the corresponding growth state. There are K growth states in the feature sampling data in the historical database, and the sampling feature dimension is p. Define is the sample covariance matrix of the kth growth state in the historical database; for Diagonal element matrix in the matrix; calculate and estimate the characteristic variance matrix of the growth state in, is the sample covariance matrix of the kth growth state A matrix without diagonal elements; s ij express The element in row i and column j in Indicates seeking ij Two different grouping states, T = {(i,j)|δ ij ≠0, i≠j}, δ ij express The value of the element in the jth row and jth column of the matrix; Step z3, define the detection sliding window width W×L as the detection three-dimensional window, where W is the time sequence window and L is the space sequence window. Calculate the detection three-dimensional window W×L Indicates the matching degree between the growth state of the detected three-dimensional window and the k-th growth state; It is the new sample co-matrix estimation of a single plant in different time ranges W under the time series window, is the new sample co-matrix estimation of different plant strains at the same time under the spatial sequence window L; Step z4, traverse K growth modes and obtain The minimum value of the element in G is used as the estimated result of the growth cycle state of corn and soybean.

4. The highly efficient and adjustable corn-soybean intercropping growth factor optimization configuration system according to claim 1, Features: Calculating the target intercropping growth factor according to the growth cycle state includes: Step m1, retrieve the intercropping growth factors required for the current growth state cycle and the corresponding impact weight values ​​of each factor according to the expert strategy or historical database; Step m2, weighted calculation of an adjustment weight value based on the influence weight value of each growth factor combined with the economic loss value of the growth factor, if the adjustment weight value is lower than a predefined threshold, the growth factor is excluded from the adjustment range; Step m3, taking the adjusted growth factor range obtained in step m2 as the target growth factor.

5. The highly efficient and adjustable corn-soybean intercropping growth factor optimization configuration system according to claim 1, Features: Step m2 includes: Step s1, initialize the algorithm parameters, use the growth factors, corresponding influencing factors, and weight factors as three-dimensional coordinates to construct a weight parameter space model, characterize the economic loss value as the optimized path distance, determine the initial target and optimization target in the weight model parameter space, define m randomly distributed bee positions, the maximum number of iterations Gmax, and the maximum limit number Lmax; Step s2, define α zi is the growth factor influencing factor, β zi is the weight factor corresponding to the impact factor, zi=1,2...zn; Step s3, randomly distribute m bees, determine the initial position of the bees, and let the bees randomly select the next position point as the next node of the optimization path until the optimization goal is reached; Step s4, for each bee, the initial iteration number G = 0, randomly generate zm search vectors in the search space, the distance dimension of the search space is D, and the search equation is defined as: Among them, v ′ di represents the best position of the ith search when the search radius is d, v di The i-th search position when the search radius is d; is the optimal value among the normalized values ​​of the influence weights of all search positions when the search radius is d; di and x dj is the normalized value of the influence weight of the i-th search position and the normalized value of the influence weight of the j-th search position when the search radius is d, j≠i and j∈{1,2,3,...KN}; The influence weight normalized value function is: cr is the crossover coefficient preset in the algorithm; ψ ′ is rand(-1,1); μ ′ is rand(0,K), where K is a predefined non-negative constant; rand(a d ,b d ) is a uniform random number function, indicating that in a d to b d Pick a uniform random number between; Among them, the probability of selecting the i-th search position as a path point is: fz i is the normalized value of the influence weight of the i-th path point, KN is the number of next path points whose normalized value of influence weight is higher than the predefined threshold; Step s5, updating the normalized value of the global influence weight; in, Indicates that in this iteration, the search between positions i and j is due to bee m k Increased influence weight normalization value, Δfit ij(g) represents the sum of normalized values ​​of the added influence weights, and g is the number of iterations; Step s6, when the number of iterations g reaches the maximum number of iterations Gmax, the optimal path of the current bees is calculated. The optimal path is sorted by the influence weight / distance normalization function value, and the one with the highest sorting is taken as the optimal path; Step s7, traverse all bees, calculate the optimal path distance of all bees, and the distance between the optimal path nodes of all bees, normalize the optimal path nodes into a grid, and select the shortest path as the parameter optimization adjustment strategy.

6. The highly efficient and adjustable corn-soybean intercropping growth factor optimization configuration system according to claim 1, Features: The growth factors include light, temperature, water, humidity, fertility, and drug control.