Agricultural product early warning management system based on big data statistics

Abstract

The present invention provides an agricultural product early warning management system based on big data statistics, including building an agricultural product supply and demand relationship early warning management framework based on big data statistics; the framework includes a data collection module, a supply and demand analysis module and an early warning release module; the system obtains historical data of each period in the N-1th trading day, and substitutes the historical data into the early warning management framework; solves the early warning management framework substituted with the historical data, obtains the decision variables of the early warning management framework, and uses the decision variables as the early warning results of the system on the Nth trading day. The present invention can provide timely and accurate supply and demand early warnings for the agricultural product market, thereby improving the stability and efficiency of the agricultural product market.

Description

Technical Field

[0001] The present invention relates to the field of big data analysis and early warning management, and more specifically, to an agricultural product early warning management system based on big data statistics. Background Art

[0002] Existing agricultural product early warning management systems usually rely on traditional data collection and analysis methods, which often lack the ability to process large amounts of real-time data, resulting in insufficient accuracy and timeliness of early warning information. In addition, traditional early warning systems often focus on only a single or a few influencing factors, such as climate or market transaction data, while ignoring the combined effects of other important factors such as soil conditions and crop growth. In terms of technical principles, these systems usually use simple statistical analysis or empirical models, lacking the ability to deeply explore and predict complex data relationships.

[0003] In implementing the steps of the embodiments of the present invention, research has found that there are at least the following problems or defects in the prior art: the existing agricultural product early warning management system fails to fully utilize the advantages of big data technology and fails to comprehensively consider various factors affecting the supply and demand relationship of agricultural products, resulting in limited accuracy and practicality of the early warning results; at the same time, the existing system has limitations in data processing and analysis methods and cannot effectively respond to the rapidity and complexity of market changes. Summary of the invention

[0004] The present invention provides an agricultural product early warning management system based on big data statistics, the system construction:

[0005] Construct an agricultural product supply and demand relationship early warning management framework based on big data statistics; the framework includes a data collection module, a supply and demand analysis module and an early warning release module; in the data collection module, the goal is to collect agricultural product related data, including climate data, soil data, crop growth data and market transaction data; in the supply and demand analysis module, a prediction model is constructed with the goal of predicting the supply and demand relationship of agricultural products, and data analysis is performed based on statistical principles; in the early warning release module, the goal is to provide timely and accurate early warning information on the supply and demand relationship of agricultural products market, and early warnings are released according to the analysis results;

[0006] The system obtains the historical data of each period in the N-1th trading day, and substitutes the historical data into the early warning management framework;

[0007] Solve the early warning management framework that substitutes historical data to obtain decision variables of the early warning management framework, and use the decision variables as the early warning results of the system on the Nth trading day.

[0008] Further, the early warning management framework of the historical data is substituted into the solution to obtain the decision variables of the early warning management framework, and the following is performed:

[0009] Initialize the algorithm parameters and system parameters;

[0010] Encode the decision variables of the data collection module and initialize the first generation population of the data collection module; starting from the first generation population, evaluate the decision space formed by the decision variables of the individuals in each generation of sub-groups and the target space formed by the target values ​​of the individuals and update the population in turn until the number of iterations is reached, and pass the individual decision variables corresponding to the optimal target value as the optimal decision variables into the supply and demand analysis module;

[0011] According to the optimal decision variables output by the data collection module, adjust the parameters of the agricultural product supply and demand forecasting model; is the supply and demand forecast value of agricultural product i in period t; the upper limit of the supply and demand forecast value of agricultural product i is , the upper limit of the forecast value of total agricultural product supply and demand Greater than or equal to the sum of the upper limits of all agricultural product supply and demand forecasts, that is , n is the total number of agricultural product types;

[0012] The prediction parameters of different agricultural products are used as decision variables of the supply and demand analysis module to encode and initialize the first generation population of the supply and demand analysis module; starting from the first generation population, the individuals in each generation population are reversed in turn, and the individuals that meet the parameters of the agricultural product supply and demand prediction model are selected. The decision space formed by the decision variables of the individuals selected in the current generation population and the target space formed by the target values ​​of the individuals are evaluated and the population is updated until the number of iterations is reached, and the decision variables of the individuals corresponding to the optimal target values ​​are passed into the early warning release module as the optimal decision variables;

[0013] The data collection module recalculates the decision variables according to the optimal decision variables at the lowest level, and makes secondary decisions on the remaining decision variables in the data collection module while keeping the decision variables unchanged, so as to obtain the final optimal decision variables as the corresponding early warning results.

[0014] Furthermore, the agricultural product supply and demand forecasting model is expressed as:

[0015]

[0016] in, represents the supply and demand forecast value of agricultural product i in period t, represents climate data, Represents soil data, represents the growth data of crop i, Represents market transaction data, is the weight coefficient.

[0017] Furthermore, the constraints of the supply and demand analysis module are expressed as:

[0018]

[0019]

[0020] In the formula, and Represent the maximum and minimum values ​​of climate data, and Represent the maximum and minimum values ​​of soil data respectively.

[0021] Furthermore, the constraints of the warning release module are expressed as:

[0022]

[0023] In the formula, represents the warning status of agricultural product i in period t, It represents the demand for agricultural product i in period t.

[0024] Furthermore, the objective function of the warning release module is expressed as:

[0025]

[0026] In the formula, n represents the number of agricultural products. represents the supply and demand forecast value of agricultural product i in period t, It represents the demand for agricultural product i in period t.

[0027] Furthermore, the incentive cost of the warning release module is expressed as:

[0028]

[0029] In the formula, represents the incentive cost of agricultural product i in period t, and k represents the incentive rate.

[0030] Furthermore, the cost of the warning release module is expressed as:

[0031]

[0032] In the formula, represents the total cost, , , , Represent the costs of climate data, soil data, crop growth data, and market transaction data, respectively. is the weight coefficient.

[0033] Furthermore, the discomfort cost function of the warning issuance module is expressed as:

[0034]

[0035] In the formula, represents the discomfort cost of agricultural product i in period t, , , They represent the quadratic term coefficient, linear term coefficient and constant term of the discomfort cost function respectively.

[0036] Furthermore, in the warning release module, All of them are historical data collected; are all decision variables.

[0037] The above-mentioned embodiment of the present invention has at least the following beneficial effects: the agricultural product early warning management system based on big data statistics builds a comprehensive data analysis framework by integrating climate data, soil data, crop growth data and market transaction data. The system can accurately predict the supply and demand relationship of agricultural products and provide dynamic early warning information through real-time updated data input. This can not only improve the accuracy of early warning, but also enhance the response speed and adaptability of the agricultural product market.

[0038] In addition, the system uses advanced forecasting models and optimization algorithms to effectively process and analyze large and complex data sets. By continuously iterating and optimizing decision variables, the system is able to find the optimal early warning release strategy to minimize market risks and maximize economic benefits. This approach can improve the stability of the agricultural product market, reduce economic losses caused by supply and demand imbalances, and also provide policymakers and agricultural producers with a powerful decision support tool. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0040] Figure 1 A schematic diagram of a process flow of an agricultural product early warning management system based on big data statistics provided by an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of the structure of an agricultural product early warning management system based on big data statistics provided by an embodiment of the present invention;

[0042] Figure 3 The schematic diagram schematically shows the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0044] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0045] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0046] Reference below Figure 1 and Figure 2 , Figure 1 A schematic diagram of a process flow of an agricultural product early warning management system based on big data statistics provided by an embodiment of the present invention; Figure 2 The structural diagram of the agricultural product early warning management system based on big data statistics provided by one embodiment of the present invention is as follows Figure 1 and Figure 2 As shown, the construction step 100 of an agricultural product early warning management system 200 based on big data statistics includes:

[0047] Step 101, constructing an agricultural product supply and demand relationship early warning management framework based on big data statistics; the framework includes a data collection module 201, a supply and demand analysis module 202 and an early warning release module 203; in the data collection module, the goal is to collect agricultural product related data, including climate data, soil data, crop growth data and market transaction data; in the supply and demand analysis module, a prediction model is constructed with the goal of predicting the agricultural product supply and demand relationship, and data analysis is performed based on statistical principles; in the early warning release module, the goal is to provide timely and accurate agricultural product market supply and demand relationship early warning information, and an early warning is released according to the analysis results;

[0048] Step 102, the system obtains historical data for each period in the N-1th trading day, and substitutes the historical data into the early warning management framework;

[0049] Step 103, solving the early warning management framework substituted into the historical data, obtaining the decision variables of the early warning management framework, and using the decision variables as the early warning results of the system on the Nth trading day.

[0050] It should be noted that the construction of an early warning management framework for agricultural product supply and demand based on big data statistics is the core of this system, which integrates multiple modules to achieve comprehensive monitoring and early warning of the agricultural product market. This framework not only includes three main modules: data collection, supply and demand analysis, and early warning release, but also involves the processing of historical data and the prediction of future market conditions.

[0051] Specifically, the data collection module is the foundation of the system, which is responsible for collecting various data related to the supply and demand of agricultural products. These data include but are not limited to climate data, such as temperature, precipitation, soil data, such as pH value, fertility, crop growth data, such as growth cycle, pest and disease conditions, and market transaction data, such as price fluctuations and transaction volume. The supply and demand analysis module uses these data to build a prediction model, and uses statistical principles to conduct in-depth analysis to predict the supply and demand relationship of agricultural products. The early warning release module releases market supply and demand early warning information in a timely manner based on the analysis results to help relevant parties respond.

[0052] Preferably, the decision variables of the early warning management framework can be optimized by machine learning algorithms to improve the accuracy of the prediction. For example, a genetic algorithm can be used to encode and update the population of the decision variables of the data collection module to find the optimal decision variables. In the supply and demand analysis module, the parameters of the prediction model, such as the upper limit of the supply and demand forecast value of agricultural products, can be adjusted to ensure the rationality of the prediction results. In addition, the early warning release module can be further refined, for example, by setting different early warning levels to meet the needs of different agricultural products and market conditions.

[0053] In some embodiments, the solving of the early warning management framework by substituting historical data to obtain decision variables of the early warning management framework is performed:

[0054] Initialize the algorithm parameters and system parameters;

[0055] Encode the decision variables of the data collection module and initialize the first generation population of the data collection module; starting from the first generation population, evaluate the decision space formed by the decision variables of the individuals in each generation of sub-groups and the target space formed by the target values ​​of the individuals and update the population in turn until the number of iterations is reached, and pass the individual decision variables corresponding to the optimal target value as the optimal decision variables into the supply and demand analysis module;

[0056] According to the optimal decision variables output by the data collection module, adjust the parameters of the agricultural product supply and demand forecasting model; is the supply and demand forecast value of agricultural product i in period t; the upper limit of the supply and demand forecast value of agricultural product i is equal to , the upper limit of the forecast value of total agricultural product supply and demand Greater than or equal to the sum of the upper limits of all agricultural product supply and demand forecasts, that is , n is the total number of agricultural product types;

[0057] The prediction parameters of different agricultural products are used as decision variables of the supply and demand analysis module to encode and initialize the first generation population of the supply and demand analysis module; starting from the first generation population, the individuals in each generation population are reversed in turn, and the individuals that meet the parameters of the agricultural product supply and demand prediction model are selected. The decision space formed by the decision variables of the individuals selected in the current generation population and the target space formed by the target values ​​of the individuals are evaluated and the population is updated until the number of iterations is reached, and the decision variables of the individuals corresponding to the optimal target values ​​are passed into the early warning release module as the optimal decision variables;

[0058] The data collection module recalculates the decision variables according to the optimal decision variables at the lowest level, and makes secondary decisions on the remaining decision variables in the data collection module while keeping the decision variables unchanged, so as to obtain the final optimal decision variables as the corresponding early warning results.

[0059] It should be noted that this embodiment describes in detail how to solve the decision variables in the early warning management framework through algorithm optimization and iterative steps. This step involves initializing the algorithm parameters and system parameters, and encoding and iteratively updating the population of data collection modules until the optimal decision variables are found.

[0060] Specifically, the algorithm parameters and system parameters are initialized first, which includes setting the number of iterations, population size, crossover rate, and mutation rate of the algorithm. The decision variable encoding of the data collection module refers to converting the actual agricultural product data into a form that the algorithm can process, for example, using binary encoding or real number encoding. Initialize the first generation population of the data collection module, which involves randomly generating a set of possible solutions that represent different data collection strategies. Then, starting from the first generation population, the individuals in each generation of the population are evaluated, which includes calculating the target value of each individual, that is, their performance in meeting the agricultural product supply and demand forecasting model. Population updating involves selecting individuals with better performance to enter the next generation, while eliminating individuals with poor performance.

[0061] Preferably, in order to improve the efficiency and accuracy of the solution, a variety of optimization algorithms can be used, such as particle swarm optimization PSO, simulated annealing SA or genetic algorithm GA. In the iterative step, a local search strategy can be introduced to refine the search space and increase the probability of finding the global optimal solution. In addition, dynamically adjusted parameters can be set, such as a mutation rate that gradually decreases with the number of iterations, so as to explore a wider solution space in the early stage of the search, and focus on a fine search near the currently found optimal solution in the later stage. In the supply and demand analysis module, multi-objective optimization can be introduced, taking into account both prediction accuracy and computational efficiency, to find the optimal supply and demand forecasting model parameters.

[0062] In some embodiments, the agricultural product supply and demand forecasting model is expressed as:

[0063]

[0064] in, represents the supply and demand forecast value of agricultural product i in period t, represents climate data, Represents soil data, represents the growth data of crop i, Represents market transaction data, is the weight coefficient.

[0065] It should be noted that this implementation method describes in detail the specific construction method of the agricultural product supply and demand forecasting model, which is a key component used in the early warning management system to predict the supply and demand relationship of agricultural products. The model predicts the supply and demand of agricultural products by comprehensively considering multiple influencing factors, such as climate, soil, crop growth and market transaction data.

[0066] Specifically, the agricultural product supply and demand forecasting model is a mathematical model that expresses the predicted output of agricultural product i in time period t as the weighted sum of climate data, soil data, crop growth data and market transaction data. In this model, climate data may include temperature, precipitation, etc.; soil data may include soil type, fertility, etc.; crop growth data may include crop growth stage, pest and disease conditions, etc.; market transaction data may include price, transaction volume, etc. The weight coefficients α, β, γ, and δ represent the importance of these data in the forecasting model, respectively, and these weight coefficients can be determined through regression analysis of historical data.

[0067] Preferably, in order to improve the accuracy and adaptability of the prediction model, a machine learning method can be used to dynamically adjust the weight coefficients. For example, algorithms such as random forests or gradient boosting machines (GBM) can be used to automatically learn the optimal weight coefficients based on historical data. In addition, the model can be designed to be adaptive and automatically adjust the prediction parameters according to changes in real-time data. In the model building step, interaction terms can also be introduced to consider the impact of interactions between different data on the supply and demand of agricultural products. For example, the combination of climatic conditions and soil fertility may have a specific impact on crop growth, and this interaction effect can be captured by additional terms in the model.

[0068] In some embodiments, the constraints of the supply and demand analysis module are expressed as:

[0069]

[0070]

[0071] In the formula, and Represent the maximum and minimum values ​​of climate data, and Represent the maximum and minimum values ​​of soil data respectively.

[0072] Specifically, constraints include the maximum and minimum values ​​of climate data and soil data. These values ​​define the range of data that the model considers when making supply and demand forecasts. For example, the maximum and minimum values ​​of climate data can be set based on historical climate records to ensure that the model only makes predictions under reasonable climate conditions. Similarly, the maximum and minimum values ​​of soil data can be determined based on historical data on soil type and fertility. These constraints not only help improve the accuracy of predictions, but also prevent the model from making mistakes when dealing with abnormal data.

[0073] Preferably, in order to further improve the robustness of the model, more constraints can be introduced. For example, maximum and minimum values ​​can also be set for crop growth data and market transaction data. In addition, a dynamic constraint method can be adopted, that is, the range of constraints can be dynamically adjusted according to the changes in real-time data. This method can make the model better adapt to changing environmental conditions and market conditions. It is also possible to consider introducing probabilistic constraints, that is, considering the probability distribution of data in the constraints, so that data fluctuations can be tolerated to a certain extent while still maintaining the accuracy of the prediction.

[0074] In some embodiments, the constraints of the warning issuing module are expressed as:

[0075]

[0076] In the formula, represents the warning status of agricultural product i in period t, It represents the demand for agricultural product i in period t.

[0077] Specifically, the determination of the warning status is based on the comparison between the demand for agricultural product i in time period t and the warning threshold. If the demand does not exceed the warning threshold, the system will issue a warning signal 1, indicating that the market supply and demand are balanced; if the demand exceeds the warning threshold, the system will issue a warning signal 0, indicating that there may be a risk of insufficient supply for market participants. The warning threshold can be set based on historical supply and demand data, market trends and seasonal factors to ensure the accuracy and timeliness of the warning signal.

[0078] Preferably, in order to improve the accuracy and practicality of early warning, a dynamically adjusted early warning threshold can be adopted. For example, the early warning threshold can be automatically adjusted based on real-time market data and the output of the forecasting model to adapt to market changes. In addition, a multi-level early warning system can be introduced to issue early warning signals of different levels according to the size of the supply-demand gap, providing more detailed guidance for market participants. It is also possible to consider introducing an expert system to further verify and adjust the early warning signals in combination with the knowledge and experience of industry experts to improve the reliability of early warnings.

[0079] In some embodiments, the objective function of the warning issuing module is expressed as:

[0080]

[0081] In the formula, n represents the number of agricultural products. represents the supply and demand forecast value of agricultural product i in period t, It represents the demand for agricultural product i in period t.

[0082] It should be noted that this embodiment describes in detail the construction and application of the objective function of the early warning release module. The objective function is a key tool for evaluating and optimizing the performance of the agricultural product supply and demand forecasting model. It guides the adjustment of the model by quantifying the difference between the predicted output and the actual demand.

[0083] Specifically, the objective function is defined by calculating the sum of the absolute values ​​of the differences between the predicted output and demand of all agricultural products in a specific period of time. In this function, n represents the number of agricultural products, and and Respectively represent the supply and demand forecast value and demand of the i-th agricultural product at time t. The purpose of this function is to minimize the prediction error, thereby improving the accuracy of supply and demand prediction.

[0084] Preferably, in order to make the objective function more comprehensive and effective, weight factors can be introduced to adjust the importance of different agricultural products or different time periods. For example, different weights can be assigned according to the market value of agricultural products, supply stability, or importance to consumers. In addition, nonlinear or dynamically adjusted objective functions can be adopted to better reflect the impact of market changes and uncertainties. For example, a time decay factor can be introduced so that the impact of recent forecast errors on the objective function is greater than that of long-term forecast errors, thereby better reflecting the current market conditions. It is also possible to consider introducing penalty terms to impose greater penalties on agricultural products or time periods with larger forecast errors, so as to encourage the model to pay more attention to the forecast accuracy of these key points.

[0085] In some embodiments, the incentive cost of the warning issuance module is expressed as:

[0086]

[0087] In the formula, represents the incentive cost of agricultural product i in period t, and k represents the incentive rate.

[0088] Specifically, the incentive cost is determined by calculating the absolute value of the difference between the predicted output and demand of agricultural product i in time period t, and then multiplying it by an incentive rate k. In this calculation, represents the incentive cost of period t, and Respectively represent the predicted output and demand of the i-th agricultural product at time t, and k is a positive incentive rate used to quantify the impact of forecast errors on the incentives of market participants. The incentive rate k can be set based on market research, historical data or expert opinions to ensure the rationality and effectiveness of the incentive cost.

[0089] Preferably, in order to make the calculation of incentive costs more accurate and practical, a dynamically adjusted incentive rate can be introduced. For example, the incentive rate can be adjusted according to market volatility, seasonal factors, or the tension between supply and demand. In addition, a multi-factor incentive cost model can be adopted to take into account other factors that affect the incentives of market participants, such as market risks, competition conditions, or policy changes. It is also possible to consider introducing a threshold mechanism to increase the incentive cost when the forecast error exceeds a certain threshold, so as to more effectively motivate market participants to pay attention to and respond to supply and demand forecasts. In addition, machine learning technology can be used to automatically learn and adjust the incentive rate based on historical data to improve the accuracy and adaptability of incentive cost calculation.

[0090] In some embodiments, the cost of the warning release module is expressed as:

[0091]

[0092] In the formula, represents the total cost, , , Represent the costs of climate data, soil data, crop growth data, and market transaction data, respectively. is the weight coefficient.

[0093] Specifically, the total cost is calculated by adding the costs of climate data, soil data, crop growth data, and market transaction data. represents the total cost, , , , Represent the costs of climate data, soil data, crop growth data, and market transaction data, respectively. These costs can be determined through historical data analysis, market research, or expert evaluation. The specific parameter setting should take into account the importance and frequency of use of various types of data in the prediction step.

[0094] Preferably, in order to make the calculation of the total cost more comprehensive and accurate, additional cost factors such as data acquisition cost, data processing cost and model maintenance cost can be introduced. In addition, a dynamic cost model can be adopted to adjust the cost of various types of data in real time according to market changes and data usage. For example, in certain seasons or when the market fluctuates greatly, the cost of relevant data can be increased to reflect its importance. At the same time, it is possible to consider introducing a cost-benefit analysis to evaluate the impact of different data sources and processing methods on the total cost, so as to optimize resource allocation and decision-making steps. Machine learning technology can also be used to automatically analyze historical data and identify trends in cost changes so as to adjust cost parameters in a timely manner and improve the economic benefits of the system.

[0095] In some embodiments, the discomfort cost function of the warning issuance module is expressed as:

[0096]

[0097] In the formula, represents the discomfort cost of agricultural product i in period t, , , They represent the quadratic term coefficient, linear term coefficient and constant term of the discomfort cost function respectively.

[0098] It should be noted that this embodiment describes in detail the construction and application of the discomfort cost function. The discomfort cost function is an important tool in the early warning release module for quantifying the inconvenience or loss caused by forecast errors to market participants. By calculating the discomfort cost, the system can better evaluate and optimize the accuracy of agricultural product supply and demand forecasts.

[0099] Specifically, the discomfort cost function is determined by calculating the square of the difference between the predicted output and demand of agricultural product i in time period t, and then adding a linear term and a constant term. In this function, represents the discomfort cost of time period t, and Respectively represent the supply and demand forecast value and demand of the i-th agricultural product at time t. The quadratic term coefficient, the linear term coefficient and the constant term are used to adjust the impact of the forecast error on the discomfort cost. These parameters can be set based on market research, historical data or expert opinions.

[0100] Preferably, in order to make the discomfort cost function more accurate and practical, dynamically adjusted parameters can be introduced. For example, the coefficients of the quadratic term, the linear term, and the constant term can be adjusted according to market volatility, seasonal factors, or the tension of the supply and demand relationship. In addition, a multi-factor discomfort cost model can be adopted to take into account other factors that affect the inconvenience or loss of market participants, such as logistics costs, storage costs, or consumer satisfaction. It is also possible to consider introducing a threshold mechanism to increase the discomfort cost when the forecast error exceeds a certain threshold to more effectively reflect the actual impact of the forecast error on market participants. In addition, machine learning techniques can be used to automatically learn and adjust the parameters of the discomfort cost function based on historical data to improve the accuracy and adaptability of its predictions. Through these methods, the inconvenience or loss caused to market participants by agricultural product supply and demand forecasts can be more comprehensively evaluated, thereby optimizing the performance of the early warning management system.

[0101] In some embodiments, in the warning release module, All of them are historical data collected; are all decision variables.

[0102] Specifically, historical data includes, but is not limited to, records of climate conditions over a period of time, soil quality analysis results, crop growth monitoring data, and market transaction records. These data provide a reference baseline for the system to establish and calibrate the prediction model. Decision variables may include weight coefficients, threshold settings, cost parameters, etc. in the prediction model, which can be adjusted and optimized according to the system's goals and constraints.

[0103] Preferably, in order to improve the flexibility and adaptability of the system, machine learning algorithms can be used to dynamically adjust decision variables. For example, algorithms such as neural networks or support vector machines can be used to automatically adjust weight coefficients and other parameters according to changes in real-time data and historical data. In addition, multi-objective optimization techniques can be introduced to consider multiple objectives such as prediction accuracy, computational efficiency, and cost-effectiveness to find the best decision variable settings. Global optimization methods such as simulated annealing or genetic algorithms can also be considered to avoid local optimal solutions and find the globally optimal decision variable configuration. Through these methods, the robustness and effectiveness of the early warning system under different market conditions and environmental changes can be ensured.

[0104] The above-mentioned embodiments of the present invention have the following beneficial effects: the agricultural product early warning management system based on big data statistics can collect and analyze climate data, soil data, crop growth data and market transaction data in real time, and accurately predict the supply and demand relationship of agricultural products by building an efficient prediction model. Through intelligent data processing and analysis, the system can timely release accurate market early warning information, help agricultural producers, dealers and policy makers make more scientific decisions, thereby reducing market volatility risks and improving the market competitiveness of agricultural products.

[0105] The implementation of the system can also optimize resource allocation and reduce economic losses caused by imbalance between supply and demand. Through continuous iteration and optimization of algorithms, the system can adapt to market changes and provide early warning strategies that better meet actual needs. In addition, by integrating multiple data sources and using advanced statistical analysis methods, the system can improve the accuracy and reliability of early warning information, making agricultural product market management more efficient and transparent.

[0106] Reference below Figure 3 , which shows a schematic diagram of a structure 300 of an electronic device suitable for implementing some embodiments of the present invention. The electronic devices in some embodiments of the present invention may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0107] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 to a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0108] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0109] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0110] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. An agricultural product early warning management system based on big data statistics, characterized in that: The system construction steps are: Construct an agricultural product supply and demand relationship early warning management framework based on big data statistics; the framework includes a data collection module, a supply and demand analysis module and an early warning release module; in the data collection module, the goal is to collect agricultural product related data, including climate data, soil data, crop growth data and market transaction data; in the supply and demand analysis module, a prediction model is constructed with the goal of predicting the supply and demand relationship of agricultural products, and data analysis is performed based on statistical principles; in the early warning release module, the goal is to provide timely and accurate early warning information on the supply and demand relationship of agricultural products market, and early warnings are released according to the analysis results; The system obtains the historical data of each period in the N-1th trading day, and substitutes the historical data into the early warning management framework; Solve the early warning management framework into which the historical data is substituted, obtain the decision variables of the early warning management framework, and use the decision variables as the early warning results of the system on the Nth trading day; The solution substitutes the early warning management framework into the historical data to obtain the decision variables of the early warning management framework, and executes: Initialize the algorithm parameters and system parameters; Encode the decision variables of the data collection module and initialize the first generation population of the data collection module; starting from the first generation population, evaluate the decision space formed by the decision variables of the individuals in each generation of sub-groups and the target space formed by the target values ​​of the individuals and update the population in turn until the number of iterations is reached, and pass the individual decision variables corresponding to the optimal target value as the optimal decision variables into the supply and demand analysis module; According to the optimal decision variables output by the data collection module, adjust the parameters of the agricultural product supply and demand forecasting model; among them, P i (t) is the supply and demand forecast value of agricultural product i in period t; the upper limit of the supply and demand forecast value of agricultural product i is P i max , the upper limit of the forecast value of total agricultural product supply and demand P total,max Greater than or equal to the sum of the upper limits of all agricultural product supply and demand forecasts, that is n is the total number of agricultural product types; The prediction parameters of different agricultural products are used as decision variables of the supply and demand analysis module to encode and initialize the first generation population of the supply and demand analysis module; starting from the first generation population, the individuals in each generation population are reversed in turn, and the individuals that meet the parameters of the agricultural product supply and demand prediction model are selected. The decision space formed by the decision variables of the individuals selected in the current generation population and the target space formed by the target values ​​of the individuals are evaluated and the population is updated until the number of iterations is reached, and the decision variables of the individuals corresponding to the optimal target values ​​are passed into the early warning release module as the optimal decision variables; The data collection module recalculates the decision variables according to the optimal decision variables at the lowest level, and makes secondary decisions on the remaining decision variables in the data collection module while keeping the decision variables unchanged, so as to obtain the final optimal decision variables as the corresponding early warning results.

2. The agricultural product early warning management system based on big data statistics according to claim 1 is characterized in that: The agricultural product supply and demand forecasting model is expressed as: P i (t)=αC(t)+βS(t)+γG i (t)+δM(t) Among them, P i (t) represents the supply and demand forecast value of agricultural product i in period t, C(t) represents climate data, S(t) represents soil data, G i (t) represents the growth data of crop i, M(t) represents the market transaction data, and α, β, γ, δ are weight coefficients.

3. The agricultural product early warning management system based on big data statistics according to claim 2 is characterized in that: The constraints of the supply and demand analysis module are expressed as: C max ≥C(t)≥C min S max ≥S(t)≥S min In the formula, C max and C min Represent the maximum and minimum values ​​of climate data, S max and S min Represent the maximum and minimum values ​​of soil data respectively.

4. The agricultural product early warning management system based on big data statistics according to claim 3 is characterized in that: The constraints of the warning release module are expressed as: Where W i (t) represents the warning status of agricultural product i in period t, D i (t) represents the demand for agricultural product i in period t.

5. The agricultural product early warning management system based on big data statistics according to claim 4 is characterized in that: The objective function of the warning release module is expressed as: In the formula, n represents the number of agricultural products, P i (t) represents the supply and demand forecast value of agricultural product i in period t, D i (t) represents the demand for agricultural product i in period t.

6. The agricultural product early warning management system based on big data statistics according to claim 5 is characterized in that: The incentive cost of the early warning release module is expressed as: IC i (t)=k·|P i (t)-D i (t)| Where, IC i (t) represents the incentive cost of agricultural product i in period t, and k represents the incentive rate.

7. The agricultural product early warning management system based on big data statistics according to claim 6 is characterized in that: The cost of the warning release module is expressed as: In the formula, TC represents the total cost, C i , S i , G i 、M i They represent the costs of climate data, soil data, crop growth data and market transaction data respectively, and λ,μ,v,ξ are weight coefficients.

8. The agricultural product early warning management system based on big data statistics according to claim 7 is characterized in that: The discomfort cost function of the warning release module is expressed as: UC i (t)=a i ·(P i (t)-D i (t)) 2 +b i ·(P i (t)-D i (t))+c i In the formula, UC i (t) represents the discomfort cost of agricultural product i in period t, a i 、b i 、c i They represent the quadratic term coefficient, linear term coefficient and constant term of the discomfort cost function respectively.

9. The agricultural product early warning management system based on big data statistics according to claim 8 is characterized in that: In the warning release module, C(t), S(t), G i P (t) and M (t) are all historical data collected; i (t), D i (t), W i (t), IC i (t),TC,UC i (t) are all decision variables.

Images