An intelligent decision support system based on big data

Abstract

This invention discloses an intelligent decision support system based on big data, belonging to the field of decision support system technology. Based on historical planting scenarios, it generates limiting factors and uses a random generation tool to generate several parameter spaces according to a preset number of spaces. The loss value of each parameter space is calculated using an information function. The loss values ​​of all parameter spaces are then substituted into a dynamic filtering algorithm. After filtering out some parameter spaces, the remaining parameter spaces undergo content randomization. A space set is established for all randomized parameter spaces, outputting multiple space sets. The loss values ​​of these multiple space sets are compared, and the parameter space with the lowest loss value is selected as the management solution for the enterprise's current planting scenario. This support system, through dynamic solution generation and filtering, can globally select the optimal management solution to adapt to the enterprise's current planting scenario, exhibiting strong adaptability and improving decision-making efficiency.

Description

Technical Field

[0001] This invention relates to the field of decision support system technology, and more specifically to an intelligent decision support system based on big data. Background Technology

[0002] Agricultural production is influenced by a variety of factors, including climate conditions (temperature, precipitation, sunlight), soil quality, crop varieties, and management practices. An assessment system is a technical system used to analyze crops. Its main purpose is to scientifically assess the crop's production status, environmental conditions, and future yield, thereby providing a basis for agricultural management and decision-making.

[0003] The existing technology has the following shortcomings:

[0004] When implementing current agricultural planting management, enterprises usually set up management plans based on human experience or expert knowledge. However, this artificial approach has two drawbacks: first, it fails to take into account the environment and actual planting conditions of the planting area in recent years, which may lead to the management plan being unsuitable for the current planting scenario; second, the artificial approach is highly subjective, which may result in the management plan not being the optimal solution and reducing decision-making efficiency.

[0005] Based on this, the present invention proposes an intelligent decision support system based on big data. Through dynamic scheme generation and screening, it can select the optimal management scheme from the global perspective to adapt to the current planting scenario of the enterprise. It has strong adaptability and is conducive to improving decision-making efficiency. Summary of the Invention

[0006] The purpose of this invention is to provide an intelligent decision support system based on big data to address the shortcomings of the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an intelligent decision support system based on big data, the support system comprising the following steps:

[0008] S1: The data acquisition end connects to the enterprise's agricultural management platform through the API interface, obtains the current planting scenario of the enterprise through the enterprise's agricultural management platform, and obtains historical planting scenarios that match the current planting scenario from the big data database. Based on the historical planting scenario, it generates limiting elements and uses a random generation tool to generate several parameter spaces according to the preset number of spaces.

[0009] S2: Calculate the loss value of each parameter space through the information function, substitute the loss values ​​of all parameter spaces into the dynamic filtering algorithm, after filtering out some parameter spaces, perform content randomization operation on the remaining parameter spaces, and establish a space set for all parameter spaces that have completed the randomization operation.

[0010] S3: Repeat step S2 iteratively on the established spatial set. After the convergence condition is met, output multiple spatial sets. Compare the loss values ​​of the multiple spatial sets and select the parameter space with the smallest loss value as the management solution for the current planting scenario of the enterprise.

[0011] In a preferred embodiment, several parameter spaces are generated using a random generation tool based on a preset number of spaces. The content of the parameter spaces includes irrigation amount, fertilizer amount, and planting density.

[0012] In a preferred embodiment, the loss value for each parameter space is calculated using an information function, including the following steps:

[0013] The loss value for each parameter space is calculated using an information function, the expression of which is:

[0014] In the formula, loss z Let θ be the loss value, δ be the prediction error, δ be the mean predicted yield, τ be the land utilization rate, and β, α, and γ be the proportional coefficients of the prediction error, the mean predicted yield, and the land utilization rate, respectively. β, α, and γ are all greater than 0. The larger the loss value, the worse the parameter space performs in the current planting scenario.

[0015] In a preferred embodiment, the loss values ​​of all parameter spaces are substituted into the dynamic screening algorithm for calculation, including the following steps:

[0016] The fitness value in the parameter space is calculated based on the loss value, and the expression is: In the formula, Atd is the fitness value, and loss is... z This is the loss value;

[0017] The fitness values ​​of all parameter spaces are summed to obtain the total fitness value. The selection probability of each parameter space is obtained by dividing the fitness value by the total fitness value. The selection probability of each parameter space is then mapped onto a sector area of ​​the virtual roulette wheel.

[0018] Start the virtual roulette wheel to rotate. When the virtual roulette wheel stops, point the virtual pointer to the parameter space corresponding to the sector area and select it.

[0019] Repeatedly start the virtual roulette wheel rotation. When the number of selected parameter spaces equals the preset threshold, filter out the remaining parameter spaces on the virtual roulette wheel and retain the selected parameter spaces.

[0020] In a preferred embodiment, after filtering out a portion of the parameter space, the remaining parameter space is subjected to content randomization, and a space set is established for all parameter spaces that have undergone randomization, including the following steps:

[0021] After filtering out some parameter spaces, the remaining parameter spaces are subjected to content randomization operations. Randomization operations include content swapping operations and mutation operations. Content swapping operations involve swapping parts of the content between each pair of parameter spaces. After all parameter spaces have completed content swapping operations, content random mutation operations are performed on all parameter spaces that have completed content swapping operations. A space set is then established for all parameter spaces that have completed mutation operations.

[0022] In a preferred embodiment, step S2 is iterated repeatedly on the established spatial set. After the convergence condition is met, multiple sets of spatial sets are output, including the following steps:

[0023] Repeat step S2 iteratively on the established spatial set. When any spatial set contains a loss value less than or equal to the loss threshold or an iteration count equal to the number of iterations threshold, the convergence condition is satisfied, and multiple spatial sets {kj1, kj2, kj3, ..., kj} are output. m In the formula, m represents the number of spatial sets, and kj i Let i represent the i-th set of spaces.

[0024] In a preferred embodiment, multiple sets of spatial parameters are compared based on their loss values, and the parameter space with the smallest loss value is selected as the management solution for the enterprise's current planting scenario. This includes the following steps:

[0025] Obtain the content information of all parameter spaces in each set of spaces, as well as the loss value information corresponding to the parameter spaces. In the set of spaces, sort all parameter spaces in ascending order of loss value. Compare the loss values ​​of the parameter spaces ranked first in all sets of spaces, and select the parameter space with the smallest loss value as the management solution for the current planting scenario of the enterprise.

[0026] In a preferred embodiment, the prediction error is calculated as follows: In the formula, θ represents the prediction error, and n represents the number of predictions made by the production prediction model. Let y be the production value predicted by the production forecasting model for the i-th time, and y be the corresponding historical actual production value.

[0027] The formula for calculating the average predicted output is as follows: In the formula, δ represents the average predicted output, and n represents the number of predictions made by the output prediction model. Let be the output value predicted by the i-th production forecasting model;

[0028] The calculation logic for the land utilization rate is as follows: obtain the total planting area of ​​the parameter space, obtain the total planting area of ​​the enterprise, and divide the total planting area by the total planting area to obtain the land utilization rate.

[0029] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0030] This invention generates limiting factors based on historical planting scenarios. It uses a random generation tool to generate several parameter spaces according to a preset number of spaces. The loss value of each parameter space is calculated using an information function. These loss values ​​are then substituted into a dynamic filtering algorithm. After filtering out some parameter spaces, the remaining parameter spaces undergo content randomization. A space set is created from all randomized parameter spaces, outputting multiple space sets. The loss values ​​of these sets are compared, and the parameter space with the lowest loss value is selected as the management solution for the enterprise's current planting scenario. This support system, through dynamic solution generation and filtering, can globally select the optimal management solution to adapt to the enterprise's current planting scenario, exhibiting strong adaptability and improving decision-making efficiency. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0032] Figure 1 This is a system module diagram of the present invention.

[0033] Figure 2 Flow chart of the method of the present invention. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] Example 1: Please refer to Figure 1 As shown in the figure, the intelligent decision support system based on big data described in this embodiment includes a data acquisition module, a spatial set establishment module, and a solution output module;

[0036] The data acquisition module connects to the enterprise's agricultural management platform via an API interface, obtains the enterprise's current planting scenario through the platform, and retrieves historical planting scenarios that match the current planting scenario from a large database. Based on the historical planting scenarios, it generates limiting elements and uses a random generation tool to generate several parameter spaces according to a preset number of spaces. The parameter spaces are then sent to the space set creation module.

[0037] Space set establishment module: Calculates the loss value of each parameter space through the information function, substitutes the loss values ​​of all parameter spaces into the dynamic filtering algorithm, performs content randomization operation on the remaining parameter spaces after filtering out some parameter spaces, and establishes a space set for all parameter spaces that have completed the randomization operation. The space set is then sent to the solution output module.

[0038] Solution output module: Iterates repeatedly on the established spatial set. After the convergence condition is met, it outputs multiple spatial sets. The loss values ​​of the multiple spatial sets are compared, and the parameter space with the smallest loss value is selected as the management solution for the current planting scenario of the enterprise.

[0039] like Figure 2 As shown: The workflow of the support system is as follows:

[0040] S1: The data acquisition end connects to the enterprise's agricultural management platform through the API interface, obtains the current planting scenario of the enterprise through the enterprise's agricultural management platform, and obtains historical planting scenarios that match the current planting scenario from the big data database. Based on the historical planting scenario, it generates limiting elements and uses a random generation tool to generate several parameter spaces according to the preset number of spaces.

[0041] S2: Calculate the loss value of each parameter space through the information function, substitute the loss values ​​of all parameter spaces into the dynamic filtering algorithm, after filtering out some parameter spaces, perform content randomization operation on the remaining parameter spaces, and establish a space set for all parameter spaces that have completed the randomization operation.

[0042] S3: Repeat step S2 iteratively on the established spatial set. After the convergence condition is met, output multiple spatial sets. Compare the loss values ​​of the multiple spatial sets and select the parameter space with the smallest loss value as the management solution for the current planting scenario of the enterprise.

[0043] This application generates limiting factors based on historical planting scenarios. According to a preset number of spaces, it uses a random generation tool to generate several parameter spaces. The loss value of each parameter space is calculated using an information function. These loss values ​​are then substituted into a dynamic filtering algorithm. After filtering out some parameter spaces, the remaining parameter spaces undergo content randomization. A space set is created from all randomized parameter spaces, outputting multiple space sets. The loss values ​​of these sets are compared, and the parameter space with the lowest loss value is selected as the management solution for the enterprise's current planting scenario. This support system, through dynamic solution generation and filtering, can globally select the optimal management solution to adapt to the enterprise's current planting scenario, exhibiting strong adaptability and improving decision-making efficiency.

[0044] The evaluation system includes a parameter space initialization module, a space set establishment module, and a management scheme output module;

[0045] Parameter space initialization module: It connects with the enterprise agricultural management platform through the API interface, obtains the current planting scenario of the enterprise through the enterprise agricultural management platform, and obtains historical planting scenarios that match the current planting scenario from the big data. It generates restrictive elements based on the historical planting scenarios, and generates several parameter spaces using a random generation tool according to the preset number of spaces. The parameter spaces are sent to the space collection creation module.

[0046] Space set establishment module: Calculates the loss value of each parameter space through information function, substitutes the loss values ​​of all parameter spaces into the dynamic filtering algorithm, performs content randomization operation on the remaining parameter spaces after filtering out some parameter spaces, and establishes a space set for all parameter spaces that have completed the randomization operation. The space set is then sent to the management scheme output module.

[0047] Management solution output module: Repeat step S2 to iterate the established spatial set. After the convergence condition is met, output multiple spatial sets. Compare the loss values ​​of the multiple spatial sets and select the parameter space with the smallest loss value as the management solution for the current planting scenario of the enterprise.

[0048] Example 2: The data acquisition terminal connects to the enterprise's agricultural management platform via an API interface. It obtains the enterprise's current planting scenario from the platform and retrieves historical planting scenarios matching the current scenario from a large database. Based on these historical scenarios, it generates constraint elements and uses a random generation tool to generate several parameter spaces according to a preset number of spaces. The parameter spaces include irrigation volume, fertilizer application volume, and planting density. The process includes the following steps:

[0049] Step 1: Obtain the current planting scenario and historical data

[0050] Connect to the enterprise's agricultural management platform via API interface: The data collection end connects to the enterprise's agricultural management platform through API interface to obtain real-time information on the enterprise's current planting scenario, including basic data such as crop type, growth stage, and regional climate characteristics.

[0051] Obtain historical planting scenarios: Through the enterprise's agricultural management platform's large database, filter historical planting scenarios that match the characteristics of the current planting scenario, for example:

[0052] Similar climatic conditions (such as rainfall, temperature, etc.).

[0053] Similar soil types (such as pH value, organic matter content, etc.).

[0054] The same or similar crop types (such as wheat, rice, etc.).

[0055] Step 2: Generate limiting elements (constraints)

[0056] Constraints extracted based on historical scenarios: From matched historical planting scenarios, analyze the reasonable ranges for irrigation volume, fertilization volume, and planting density. For example: upper and lower limits for irrigation volume (e.g., 50-150 cubic meters per acre); upper and lower limits for fertilization volume (e.g., the range of nitrogen, phosphorus, and potassium fertilizer application); and the range for planting density (e.g., the number of crop plants per acre).

[0057] Dynamic adjustments based on environmental and policy factors: The above-mentioned scope is revised according to the current water resources status, soil fertility, and government policies (such as water restriction policies) of the region to form limiting factors.

[0058] Step 3: Randomly generate parameter space

[0059] Determine the number of parameter spaces: Based on enterprise needs or algorithm design, pre-generate several parameter spaces, such as generating 100 sets of parameter combinations.

[0060] Use random generation tools to randomly generate specific values ​​for irrigation amount, fertilizer amount, and planting density within the range of constrained elements, forming a parameter space, for example:

[0061] P1 = {Irrigation volume = 120m³} 3 Fertilizer application rate = 20 kg, planting density = 3000 plants / mu;

[0062] P2 = {Irrigation volume = 100m³} 3 Fertilizer application rate = 25 kg, planting density = 2800 plants / mu;

[0063] Forming a parameter space set:

[0064] The set of all randomly generated parameter spaces is denoted as: {P1, P2, ..., P...} N}

[0065] Through the above steps, historical scenarios that match the current planting scenario can be extracted from the enterprise's agricultural management platform and historical data. Under the condition of limiting factors, the parameter space of irrigation amount, fertilizer amount and planting density can be randomly generated to support the subsequent scenario optimization and management scheme generation.

[0066] The loss value for each parameter space is calculated using the information function, including the following steps:

[0067] The loss value for each parameter space is calculated using an information function, the expression of which is:

[0068] In the formula, loss z Let θ be the loss value, δ be the prediction error, δ be the mean predicted yield, τ be the land utilization rate, and β, α, and γ be the proportional coefficients of the prediction error, the mean predicted yield, and the land utilization rate, respectively. β, α, and γ are all greater than 0. The larger the loss value, the worse the parameter space performs in the current planting scenario.

[0069] The expression for calculating prediction error is: In the formula, θ represents the prediction error, and n represents the number of predictions made by the production prediction model. Let y be the yield value predicted by the yield prediction model for the i-th time, and y be the corresponding historical actual yield value. The larger the prediction error, the greater the loss value. When the prediction error is large, it indicates that the combination of parameters (such as irrigation amount, fertilizer amount and planting density) has led to the model's inaccurate estimation of actual yield, and the reliability of the current parameter space has decreased.

[0070] The formula for calculating the average predicted yield is: In the formula, δ represents the average predicted output, and n represents the number of predictions made by the output prediction model. Let be the production value predicted by the production prediction model for the i-th time. The lower the average predicted production value, the greater the loss value. When the average predicted production value is low, it indicates that the resource allocation efficiency of the current parameter space is poor, making it difficult to achieve the high production target, and the superiority of the current scheme is low.

[0071] In this application, the prediction model adopts the existing multiple linear regression model. By inputting the current irrigation amount, fertilizer amount and planting density into the trained multiple linear regression model, the multiple linear regression model can output the predicted yield. This technology belongs to the prior art and will not be described in detail in this application.

[0072] The calculation logic for land utilization rate is as follows: obtain the total planting area in the parameter space and the total planting area of ​​the enterprise. Divide the total planting area by the total planting area to obtain the land utilization rate. The lower the land utilization rate, the greater the loss value. When the land utilization rate is low, it indicates that the current planting density or land use method in the parameter space is not making full use of land resources, and the scheme is ineffective.

[0073] The loss values ​​from all parameter spaces are substituted into the dynamic filtering algorithm for calculation, including the following steps:

[0074] The fitness value in the parameter space is calculated based on the loss value, and the expression is: In the formula, Atd is the fitness value, and loss is... z The fitness value is the reciprocal of the loss value. Therefore, the larger the fitness value of the parameter space, the smaller the loss value of the parameter space, and the better the performance when applied to the current planting scenario.

[0075] The fitness values ​​of all parameter spaces are summed to obtain the total fitness value. The selection probability of each parameter space is obtained by dividing the fitness value by the total fitness value. The selection probability of each parameter space is mapped to a sector area of ​​the virtual roulette wheel. The higher the selection probability of a parameter space, the larger the sector area occupied by the parameter space on the virtual roulette wheel. The virtual roulette wheel is started to rotate. When the virtual roulette wheel stops, the virtual pointer points to the parameter space corresponding to the sector area and selects it. The rotation of the virtual roulette wheel is started repeatedly. When the number of selected parameter spaces is equal to the preset number threshold, the remaining parameter spaces on the virtual roulette wheel are filtered out, and the selected parameter spaces are retained.

[0076] After filtering out some parameter spaces, the remaining parameter spaces are randomized, and a space set is created for all parameter spaces that have undergone randomization. This includes the following steps:

[0077] After filtering out some parameter spaces, the remaining parameter spaces are subjected to content randomization operations. Randomization operations include content swapping operations and mutation operations. Content swapping operations involve swapping part of the content of each pair of parameter spaces (in order to avoid the situation where a single parameter space cannot achieve content swapping, the number threshold in this application is preset to an even number, so that all remaining parameter spaces can perform content swapping). After all parameter spaces have completed content swapping operations, all parameter spaces that have completed content swapping operations are subjected to content random mutation operations, thereby increasing the randomness of the parameter spaces, which is beneficial for global optimization and improving the robustness of the evaluation system. A space set is established for all parameter spaces that have completed mutation operations.

[0078] Initially reserved parameter space:

[0079] Assuming four parameter spaces are retained (because the quantity threshold is even), the content of each parameter space includes irrigation amount (m 3 The application rates (per acre), fertilizer application rate (kg / acre), and planting density (plants / acre) are shown below:

[0080] Parameter space 1: [120, 30, 2800];

[0081] Parameter space 2: [100, 25, 3000];

[0082] Parameter space 3: [110, 28, 2600];

[0083] Parameter space 4: [115, 35, 2900];

[0084] 1. Content exchange operation

[0085] The reserved parameter space is randomly grouped in pairs, and some of the contents are swapped.

[0086] Random grouping:

[0087] [parameter space 1, parameter space 2];

[0088] [Parameter space 3, parameter space 4];

[0089] Exchange rules:

[0090] Each group randomly selects one variable to swap. For example:

[0091] Group 1 (Parameter Spaces 1 and 2): Exchange Irrigation Quantity

[0092] Parameter space 1: [100, 30, 2800];

[0093] Parameter space 2: [120, 25, 3000];

[0094] Group 2 (parameter spaces 3 and 4): Exchange planting density

[0095] Parameter space 3: [110, 28, 2900];

[0096] Parameter space 4: [115, 35, 2600];

[0097] 2. Content random mutation operation

[0098] Randomly mutate all parameter spaces after the content exchange operation is completed to increase randomness and avoid getting trapped in local optima.

[0099] Mutation rule: Randomly select a variable and increase or decrease its value by a random number within a certain range (generated according to parameter constraints).

[0100] For example: an increase or decrease in irrigation volume of 5-10m 3 The fertilizer application rate is adjusted to 2-5 kg / mu, and the planting density is adjusted to 50-100 plants / mu.

[0101] Mutation results:

[0102] Parameter space 1: Irrigation amount 100→105 (increase by 5), other parameters remain unchanged. [105, 30, 2800];

[0103] Parameter space 2: Fertilizer application rate 25→28 (increase by 3), other parameters remain unchanged. [120, 28, 3000];

[0104] Parameter space 3: Planting density 2900→2850 (decreased by 50), other parameters remain unchanged. [110, 28, 2850];

[0105] Parameter space 4: Irrigation amount 115→120 (increase by 5), other parameters remain unchanged. [120, 35, 2600];

[0106] 3. Establish spatial sets

[0107] After completing the content randomization operation, all parameter spaces are formed into a new space set: = {[105, 30, 2800], [120, 28, 3000], [110, 28, 2850], [120, 35, 2600]};

[0108] Content exchange operation: Select variables to exchange in pairwise groups to promote information exchange in the parameter space and increase diversity.

[0109] Content mutation operation: Randomly adjust variables to increase exploration capabilities and avoid getting trapped in local optima.

[0110] Establish a space set: to provide a new parameter candidate space for subsequent iterations, and finally select the globally optimal solution.

[0111] These operations make the parameter space more random and diverse, enabling the evaluation system to explore better management solutions and improve overall optimization capabilities and robustness.

[0112] Repeat step S2 iteratively on the established spatial set. After the convergence condition is met, output multiple sets of spatial sets, including the following steps:

[0113] Repeat step S2 iteratively on the established spatial set. When any spatial set contains a loss value less than or equal to the loss threshold or an iteration count equal to the number of iterations threshold, the convergence condition is satisfied, and multiple spatial sets {kj1, kj2, kj3, ..., kj} are output. m In the formula, m represents the number of spatial sets, and kji Let i represent the i-th set of spaces.

[0114] The loss values ​​of multiple spatial sets are compared, and the parameter space with the smallest loss value is selected as the management solution for the enterprise's current planting scenario. This includes the following steps:

[0115] Obtain the content information of all parameter spaces in each set of spaces, as well as the loss value information corresponding to the parameter spaces. In the set of spaces, sort all parameter spaces in ascending order of loss value. Compare the loss values ​​of the parameter spaces ranked first in all sets of spaces, and select the parameter space with the smallest loss value as the management solution for the current planting scenario of the enterprise.

[0116] The company evaluates the combination of irrigation amount, fertilizer amount and planting density. After multiple rounds of randomization operations and iterations, multiple spatial sets are generated, and each parameter space corresponds to a loss value (the smaller the value, the better).

[0117] Suppose there exist three sets of spaces, each containing four parameter spaces and their corresponding loss values:

[0118] Space Set 1:

[0119] [105, 30, 2800] Loss value = 0.12;

[0120] [120, 28, 3000 loss value = 0.15;]

[0121] [110, 28, 2850] Loss value = 0.18;

[0122] [120, 35, 2600] Loss value = 0.22;

[0123] Space Set 2:

[0124] [100, 25, 2900] Loss value = 0.10;

[0125] [110, 30, 2800] Loss value = 0.13;

[0126] [115, 28, 3000] Loss value = 0.20;

[0127] [105, 35, 2700] Loss value = 0.25;

[0128] Space Set 3:

[0129] [115, 30, 2750] Loss value: 0.14;

[0130] [105, 32, 2800] Loss value = 0.16;

[0131] [110, 29, 2900] Loss value = 0.19;

[0132] [100, 30, 2850] Loss value = 0.23;

[0133] Step 1: Sort the parameter spaces within each space set. Space set 1:

[0134] Sort by loss value:

[0135] 1. [105, 30, 2800](0.12);

[0136] 2. [120, 28, 3000](0.15);

[0137] 3. [110, 28, 2850](0.18);

[0138] 4. [120, 35, 2600](0.22);

[0139] Space Set 2:

[0140] Sort by loss value:

[0141] 1. [100, 25, 2900](0.10);

[0142] 2. [110, 30, 2800](0.13);

[0143] 3. [115, 28, 3000](0.20);

[0144] 4. [105, 35, 2700] (0.25);

[0145] Space Set 3:

[0146] Sort by loss value:

[0147] 1. [115, 30, 2750](0.14);

[0148] 2. [105, 32, 2800](0.16);

[0149] 3. [110, 29, 2900](0.19);

[0150] 4. [100, 30, 2850](0.23);

[0151] Step 2: Extract the first-ranked parameter space from each set. Select the parameter space with the smallest loss value from each set of spaces: Space set 1: [105, 30, 2800] (0.12);

[0152] Space set 2: [100, 25, 2900](0.10);

[0153] Space set 3: [115, 30, 2750](0.14);

[0154] Step 3: Compare the loss values ​​of the selected parameter spaces.

[0155] Compare the loss values ​​of the top performer among the three sets:

[0156] Space set 1: 0.12;

[0157] Space set 2: 0.10;

[0158] Space set 3: 0.14;

[0159] Selection result:

[0160] The minimum loss value is [100, 25, 2900] (0.10).

[0161] Ultimately, [100, 25, 2900] was selected as the management solution for the company's current planting scenario.

[0162] By sorting the parameter spaces in each set of spaces according to their loss values ​​and comparing them with the parameter space ranked first, the globally optimal management scheme with the minimum loss value can be quickly determined. This method ensures effective exploration and selection of the global space, improving the rationality and scientific nature of the management scheme.

[0163] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0164] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0165] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0166] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those 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 this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0167] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A big data-based intelligent decision support system, characterized in that: It includes a data acquisition module, a spatial set creation module, and a solution output module; The data acquisition module connects to the enterprise's agricultural management platform via an API interface. It obtains the current planting scenario of the enterprise through the agricultural management platform and retrieves historical planting scenarios that match the current planting scenario from a large database. Based on the historical planting scenarios, it generates limiting elements and uses a random generation tool to generate several parameter spaces according to a preset number of spaces. The content of the parameter spaces includes irrigation amount, fertilizer amount and planting density. Space set establishment module: Calculate the loss value of each parameter space through the information function, substitute the loss values ​​of all parameter spaces into the dynamic filtering algorithm, after filtering out some parameter spaces, perform content randomization operation on the remaining parameter spaces, and establish a space set for all parameter spaces that have completed the randomization operation. The spatial set establishment module calculates the loss value of each parameter space through an information function, including the following steps: The loss value for each parameter space is calculated using an information function, the expression of which is: In the formula, loss z θ is the loss value, δ is the prediction error, δ is the mean predicted yield, τ is the land utilization rate, and β, α, and γ are the proportional coefficients of prediction error, mean predicted yield, and land utilization rate, respectively. β, α, and γ are all greater than 0. The larger the loss value, the worse the parameter space performs in the current planting scenario. The space set establishment module calculates the fitness value of the parameter space based on the loss value, and the expression is: In the formula, Atd is the fitness value, and loss is... z This is the loss value; The fitness values ​​of all parameter spaces are summed to obtain the total fitness value. The selection probability of each parameter space is obtained by dividing the fitness value by the total fitness value. The selection probability of each parameter space is then mapped onto a sector area of ​​the virtual roulette wheel. Start the virtual roulette wheel to rotate. When the virtual roulette wheel stops, point the virtual pointer to the parameter space corresponding to the sector area and select it. Repeatedly start the virtual roulette wheel rotation. When the number of selected parameter spaces equals the preset threshold, filter out the remaining parameter spaces on the virtual roulette wheel and retain the selected parameter spaces. Solution output module: Iterates repeatedly on the established spatial set. After the convergence condition is met, it outputs multiple spatial sets. The loss values ​​of the multiple spatial sets are compared, and the parameter space with the smallest loss value is selected as the management solution for the current planting scenario of the enterprise. The output module iterates repeatedly on the established spatial sets. When any spatial set contains a loss value less than or equal to the loss threshold or an iteration count equal to the number of iterations threshold, it determines that the convergence condition is met and outputs multiple spatial sets {kj1, kj2, kj3, ..., kj...}. m In the formula, m represents the number of spatial sets, and kj i Denotes the i-th set of spaces; The solution output module obtains the content information of all parameter spaces in each set of spaces and the loss value information corresponding to the parameter spaces. In the set of spaces, all parameter spaces are sorted from smallest to largest according to the loss value. The loss value of the first-ranked parameter space in all sets of spaces is compared, and the parameter space with the smallest loss value is selected as the management solution for the current planting scenario of the enterprise.

2. The intelligent decision support system based on big data according to claim 1, characterized in that: After filtering out some parameter spaces, the space set establishment module performs content randomization operations on the remaining parameter spaces. The randomization operations include content exchange operations and mutation operations. The content exchange operation includes exchanging part of the content of each pair of parameter spaces. After all parameter spaces have completed the content exchange operation, a content random mutation operation is performed on all parameter spaces that have completed the content exchange operation. A space set is established for all parameter spaces that have completed the mutation operation.

3. The intelligent decision support system based on big data according to claim 2, characterized in that: The expression for calculating the prediction error is as follows: In the formula, θ represents the prediction error, and n represents the number of predictions made by the production prediction model. Let y be the production value predicted by the production forecasting model for the i-th time, and y be the corresponding historical actual production value. The formula for calculating the average predicted output is as follows: In the formula, δ represents the average predicted output, and n represents the number of predictions made by the output prediction model. Let be the output value predicted by the i-th production forecasting model; The calculation logic for the land utilization rate is as follows: obtain the total planting area of ​​the parameter space, obtain the total planting area of ​​the enterprise, and divide the total planting area by the total planting area to obtain the land utilization rate.

Images