Agricultural product precision marketing system based on big data

Abstract

The invention discloses an agricultural product precision marketing system based on big data, and relates to the technical field of agricultural informatization. Comprising a vector construction module which is used for constructing environment kinetic energy characteristics according to acquired original data and constructing a multi-dimensional agricultural effect vector according to the environment kinetic energy characteristics; the environmental effect field generation module is used for inputting the input data into a preset required fluctuation energy calculation model, outputting required fluctuation energy and synthesizing an environmental effect field based on the required fluctuation energy; the dynamic regulation and control module is used for constructing a resource allocation function based on the normalized environmental effect field and the inventory rate to carry out dynamic resource allocation optimization, and calculating to obtain an optimal resource allocation value; and the strategy execution module is used for optimizing the resource allocation strategy and the agricultural product price according to the optimal resource allocation value and executing regulation and control. Through more accurate demand prediction, dynamic resource allocation and real-time feedback learning, the resource utilization efficiency is optimized, and the overall efficiency of agricultural product production, inventory management and marketing is improved.

Description

Technical Field

[0001] The present invention relates to the field of agricultural information technology, and in particular to a precision marketing and sales system for agricultural products based on big data. Background Art

[0002] With the development of big data technology, precision management of agricultural production and sales has become a crucial tool for enhancing the market competitiveness of agricultural products. Traditional agricultural product marketing often relies on experience and simple market research, lacking dynamic monitoring and optimization of environmental changes, consumer demand, and resource allocation. This leads to resource waste, fluctuating yields, and inefficient marketing. Therefore, accurately predicting market demand for agricultural products, dynamically allocating resources, and effectively managing them based on real-time data have become key challenges facing agricultural modernization.

[0003] Currently, some agricultural product marketing systems based on data analysis exist, but most lack accurate demand forecasting models, dynamic resource allocation mechanisms, and real-time data learning and feedback updates. Furthermore, traditional agricultural production and marketing systems often fail to fully consider the impact of multi-dimensional environmental data (such as weather, soil, pests and diseases), as well as consumer behavior, on agricultural production. This results in resource allocation and inventory management that are insufficient to cope with rapidly changing market demands.

[0004] Therefore, the present invention provides a precision marketing and sales system for agricultural products based on big data, which can comprehensively consider multi-dimensional environmental factors and changes in consumer demand, and realize efficient agricultural product production and marketing management through prediction models and dynamic resource regulation mechanisms, thereby maximizing resource utilization, reducing inventory risks, and improving market responsiveness. Summary of the Invention

[0005] Based on the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a precision marketing and sales system for agricultural products based on big data to solve the above-mentioned technical problems.

[0006] To achieve the above objectives, the present invention provides the following technical solutions: a precision marketing and sales system for agricultural products based on big data, comprising: Vector construction module: used to construct environmental kinetic energy characteristics based on the acquired raw data, construct a multidimensional agricultural efficiency vector based on the environmental kinetic energy characteristics, and set the multidimensional agricultural efficiency vector as input data; Environmental effect field generation module: used to input input data into a preset demand fluctuation energy calculation model, output demand fluctuation energy, and synthesize the environmental effect field based on the demand fluctuation energy; Dynamic control module: used to construct resource allocation function based on normalized environmental effect field and inventory rate to optimize dynamic resource allocation and calculate the optimal resource allocation value; Strategy execution module: used to optimize and regulate resource allocation strategies and agricultural product prices based on optimal resource allocation values, and implement strategies in the production and inventory management of agricultural products.

[0007] The present invention is further configured such that the original data includes meteorological data, soil data, biological stress data, and resource flow data; The meteorological data includes accumulated temperature, precipitation anomaly, and solar radiation; the soil data includes moisture content and nitrogen, phosphorus, and potassium content; the biotic stress data includes pest and disease density, weed coverage, and pathogen index; the resource flow data includes logistics costs and price fluctuations of competing products; Environmental kinetic characteristics include resource allocation characteristics, consumer kinetic characteristics, and habitat characteristics; Construct a multidimensional agricultural efficiency vector based on resource allocation characteristics, consumer kinetic characteristics and habitat characteristics; Resource allocation characteristics include agricultural product output, consumer kinetic characteristics include agricultural product demand, and habitat characteristics include meteorological data, soil data, biological stress data, and resource flow data.

[0008] The present invention is further configured such that the construction logic of the preset demand fluctuation energy calculation model includes: The historical data of multidimensional agricultural efficiency vectors in time series are set as input, and the enhanced Dickey-Fuller test is used to test the data for stationarity. If the data fails the stationarity test, the multidimensional agricultural efficiency vectors are subjected to sequence deconstruction and the order of sequence deconstruction is determined to obtain the stationary time series data after sequence deconstruction. The stationary time series data that have passed the stationary test or series deconstruction are seasonally decomposed using the seasonal trend decomposition method to obtain purified data; Based on the purified data, an autoregressive integrated moving average model is used to build a model, and the optimal parameters are selected by the Akaike information criterion to perform rolling predictions and output future predicted values, which are resource allocation values, resource demand values, or habitat characteristic values; The demand fluctuation energy is calculated based on the instantaneous deviation between the actual value and the predicted value, combined with the fluctuation rate obtained based on the purified data.

[0009] The present invention is further configured to synthesize an environmental effect field based on demand fluctuation energy, and the calculation logic of the environmental effect field is: ,in, For the moment The environmental effect field value, is the number of input features, is the feature weight, is the sensitivity coefficient, For the Features at the moment Energy demand fluctuations; Environmental effect field value Perform standardization operations to obtain , converting the environmental state into a unified measurement range.

[0010] The present invention is further configured such that the dynamic control module is specifically configured to: The resource allocation function of agricultural product demand and inventory is constructed using environmental effect field and inventory rate as input data, and the resource allocation function is optimized using gradient descent method. When the environmental effect field is detected to be greater than the preset environmental effect field threshold, the emergency resource control strategy is activated.

[0011] The present invention is further configured such that the calculation logic of the resource allocation function is: ,in, Allocate functions for resources, Assign values to resources, For the moment The environmental effect field value, is the inventory rate, Assign a value to the minimum resource, is the resource demand elasticity index, is the environmental effect field coupling coefficient, is the resource weighting factor.

[0012] The present invention is further configured such that the gradient descent method optimizes the resource allocation function, specifically for: Adjust the resource allocation by iteratively updating the current resource allocation value; When the difference between the resource allocation value of the next iteration step and the current resource allocation value is less than a preset iteration threshold, the iteration is stopped and it is considered that the resource allocation has converged to the optimal value.

[0013] The present invention is further configured such that the policy execution module is specifically configured to: Taking the optimal resource allocation value and the current inventory status as input data, the three-level resource allocation strategy is generated by adjusting resource allocation according to the inventory level; When the inventory ratio is greater than the first inventory benchmark, resource allocation and agricultural product prices are adjusted downwards; When the inventory ratio is greater than the second inventory benchmark and less than or equal to the first inventory benchmark, the current resource allocation and agricultural product prices are maintained; When the inventory ratio is less than or equal to the second inventory benchmark, resource allocation and agricultural product prices will be adjusted upwards; Comprehensively evaluate the benefits of each channel and prioritize the channels. The calculation logic of the benefit evaluation function is: ,in, For channels The benefits, For channels Historical conversion rates, For channels Real-time traffic quality, is the weight coefficient, according to Sort in descending order and allocate promotion resources first High-value channels; Use the customer value analysis model to group consumers and calculate each consumer's customer value score based on a weighted combination of the last purchase time, purchase frequency, and purchase amount; Set a customer value benchmark score and push personalized marketing plans to customers whose customer value scores are greater than the customer value benchmark score and customers whose customer value scores are less than the customer value benchmark score.

[0014] The present invention is further configured such that the system further includes a feedback learning module, specifically configured to: Continuously monitor the deviation between actual and predicted outputs during the production and supply of agricultural products, and gradually adjust parameters in the environmental effect field calculation logic, including feature weights and sensitivity coefficients; Optimize strategies based on real-time production and supply data to improve the accuracy of resource allocation and inventory management.

[0015] The present invention is further configured such that the system further includes a visualization module, specifically configured to: Quantify the effectiveness of resource allocation sensitivity, inventory turnover rate and marketing investment return rate indicators in real time through real-time monitoring dashboards; Automatically generate feedback reports that include resource demand and output curve trend charts, anomaly detection, and optimization suggestions. Based on the report analysis, the optimization suggestions propose specific optimization measures, including adjusting resource allocation strategies and improving resource utilization efficiency.

[0016] The present invention provides a precision marketing and sales system for agricultural products based on big data. The system comprises a vector construction module for constructing environmental kinetic energy characteristics based on acquired raw data, constructing a multidimensional agricultural efficiency vector based on the environmental kinetic energy characteristics, and setting the multidimensional agricultural efficiency vector as input data; an environmental effect field generation module for inputting the input data into a preset demand fluctuation energy calculation model, outputting demand fluctuation energy, and synthesizing an environmental effect field based on the demand fluctuation energy; a dynamic control module for constructing a resource allocation function based on the normalized environmental effect field and inventory rate to perform dynamic resource allocation optimization and calculate an optimal resource allocation value; and a strategy execution module for optimizing and controlling resource allocation strategies and agricultural product prices based on the optimal resource allocation value, and implementing the strategies in the production and inventory management of agricultural products. The beneficial effects produced include: 1. Accurate demand forecasting and resource allocation: By constructing multi-dimensional agricultural efficiency vectors and calculating demand fluctuation energy, combined with factors such as environmental kinetic energy characteristics, weather, soil, pests and diseases, it is possible to accurately predict the market demand and production status of agricultural products, dynamically optimize resource allocation, reduce resource waste, ensure the matching of output and demand, and improve the efficiency of production and supply chain management; 2. Improve resource utilization efficiency: Through the dynamic control module and the gradient descent optimization algorithm, the present invention can adjust resource allocation in real time under different production and market demand environments to maximize resource utilization efficiency. In terms of inventory management, it can accurately adjust resource allocation according to changes in inventory levels and market demand, avoid excessive or insufficient resource investment, improve inventory turnover, and reduce backlogs and waste. 3. Enhance production and market responsiveness: Through real-time monitoring, feedback learning, and strategy execution modules, it can quickly respond to market changes and adjust production plans and marketing strategies in a timely manner based on the deviation between actual and predicted output, thereby improving the resilience of agricultural product production and the market.

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without inventive efforts. In the drawings: Figure 1 The structure diagram of a precision marketing and sales system for agricultural products based on big data is shown as an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0020] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0021] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0022] Agricultural product precision marketing and sales system based on big data, such as Figure 1 Shown, including: Vector construction module: used to construct environmental kinetic energy characteristics based on the acquired raw data, construct a multidimensional agricultural efficiency vector based on the environmental kinetic energy characteristics, and set the multidimensional agricultural efficiency vector as input data; Environmental effect field generation module: used to input input data into a preset demand fluctuation energy calculation model, output demand fluctuation energy, and synthesize the environmental effect field based on the demand fluctuation energy; Dynamic control module: used to construct resource allocation function based on normalized environmental effect field and inventory rate to optimize dynamic resource allocation and calculate the optimal resource allocation value; Strategy execution module: used to optimize and control resource allocation strategies and agricultural product prices based on optimal resource allocation values, and implement strategies in the production and inventory management of agricultural products; Specifically, the main function of the vector construction module is to extract important information from the acquired raw data and convert this information into a mathematical representation that can be used for analysis and prediction, namely a multidimensional agricultural efficiency vector. The raw data includes meteorological data, soil data, pest and disease density and resource flow information. The environmental kinetic energy characteristics are obtained by analyzing the raw data, which include characteristics of the agricultural product production environment, such as climate change, soil quality, pest and disease threats, etc., and then further constructed into a multidimensional agricultural efficiency vector. The multidimensional agricultural efficiency vector represents the multidimensional data of the agricultural product production environment. Through vectorized representation, the model can better perform subsequent calculations and analysis; the main function of the environmental effect field generation module is to input the multidimensional agricultural efficiency vector into a demand fluctuation energy calculation model, and generate an environmental effect field based on the calculation results; the main function of the dynamic control module is to use the environmental effect field and inventory rate to dynamically adjust resource allocation, through Construct a resource allocation function, and the dynamic control module optimizes the allocation of resources to better match it with market demand and production environment. The resource allocation function is adjusted according to inventory conditions and demand fluctuations. The purpose is to optimize resource input, avoid excessive or insufficient resource allocation, and ensure the balance of production and sales processes. The dynamic optimization process usually uses the gradient descent method to continuously iterate and calculate, and finally obtain an optimal resource allocation value; the main function of the strategy execution module is to optimize and execute control on the resource allocation strategy and agricultural product prices according to the optimal resource allocation value, and apply these strategies to the production and inventory management of agricultural products. According to the optimal resource allocation value, formulate corresponding control strategies, such as increasing production when resources are short of resources and reducing production when inventory is excessive, to ensure that the strategy can be effectively implemented to support continuous optimization in the production and inventory management process and avoid unnecessary waste of resources and inventory backlogs.

[0023] The present invention is further configured such that the original data includes meteorological data, soil data, biological stress data, and resource flow data; The meteorological data includes accumulated temperature, precipitation anomaly, and solar radiation; the soil data includes moisture content and nitrogen, phosphorus, and potassium content; the biotic stress data includes pest and disease density, weed coverage, and pathogen index; the resource flow data includes logistics costs and price fluctuations of competing products; Environmental kinetic characteristics include resource allocation characteristics, consumer kinetic characteristics, and habitat characteristics; Construct a multidimensional agricultural efficiency vector based on resource allocation characteristics, consumer kinetic characteristics and habitat characteristics; Resource allocation characteristics include agricultural product output, consumer kinetic characteristics include agricultural product demand, and habitat characteristics include meteorological data, soil data, biotic stress data, and resource flow data; Specifically, accumulated temperature refers to the temperature accumulated over a certain period of time, which affects the growth cycle and development stage of agricultural products; precipitation anomaly refers to the deviation in precipitation, which affects the water supply of agricultural products, and extreme precipitation changes lead to droughts or floods; solar radiation refers to the radiation intensity of sunlight, which affects the photosynthesis and growth of agricultural products; moisture content refers to the moisture content in the soil; nitrogen, phosphorus and potassium content refer to the three major nutrients in the soil, which directly affect the nutritional supply and growth status of agricultural products; pest and disease density refers to the number or density of pests and diseases in the field, and high density of pests and diseases leads to reduced yields of agricultural products; weed cover refers to the growth of weeds affecting the resource competition of crops; pathogen index indicates the intensity of pathogen threats to agricultural products in the field; logistics cost refers to the transportation cost from the production site to the market, which affects the market competitiveness of agricultural products; price fluctuations of competing products refer to changes in the market prices of similar agricultural products, which affect the sales strategy of agricultural products and thus affect the production volume of agricultural products; meteorological data is used to analyze the impact of meteorological data on the production process. Meteorological stations and satellite remote sensing technology acquire real-time data on temperature, precipitation, and solar radiation. Soil data is monitored in real time through ground sensors and drones, combined with periodic sampling for comprehensive analysis. Biological stress data is monitored in real time and periodically tested through field surveys, IoT sensors, and drones. Resource flow data is obtained in real time through market monitoring systems, supply chain management platforms, and logistics tracking systems. Resource allocation characteristics include agricultural product output, reflecting the efficiency and scale of production. Consumer kinetic characteristics include demand for agricultural products, reflecting the intensity and changing trends of market demand. Habitat characteristics are composed of multiple aspects such as meteorological, soil, pests and diseases, and resource flow data, reflecting the environmental conditions of agricultural production. Combining these raw data with environmental kinetic characteristics, a multidimensional agricultural efficiency vector is constructed, which provides a precise input for the system to predict market demand, optimize resource allocation, and dynamically adjust production strategies. The multidimensional agricultural efficiency vector is expressed as follows: ,in, is a multidimensional agricultural efficiency vector, Assigning characteristics to resources, For consumer kinetic characteristics, For habitat characteristics.

[0024] The present invention is further configured such that the construction logic of the preset demand fluctuation energy calculation model includes: The historical data of multidimensional agricultural efficiency vectors in time series are set as input, and the enhanced Dickey-Fuller test is used to test the stationarity of the data. If the data fails the stationarity test, the multidimensional agricultural efficiency vectors are subjected to sequence deconstruction and the order of sequence deconstruction is determined to obtain the stationary time series data after sequence deconstruction. Specifically, the historical data of multidimensional agricultural efficiency vectors are expressed as follows: ; For time series Perform the enhanced Dickey-Fuller test. If the test passes, no sequence deconstruction is required. If the test fails, a sequence deconstruction is performed. , For the data after the first sequence deconstruction, the enhanced Dickey-Fuller test is performed on the data after the sequence deconstruction. If the test fails after the first sequence deconstruction, the second-order sequence deconstruction is performed. , For the data after the second-order sequence deconstruction, the enhanced Dickey-Fuller test is performed on the data after the second-order sequence deconstruction, and the minimum sequence deconstruction order is selected through the enhanced Dickey-Fuller test , so that the sequence after sequence deconstruction is stable; the calculation logic of the sequence deconstruction order is: , is the sequence deconstruction order, Deconstructing a sequence The statistics and critical values of the enhanced Dickey-Fuller test are used to determine whether the enhanced Dickey-Fuller test is passed based on the critical value of the significance level; The seasonal trend decomposition method is used to seasonally decompose the stationary time series data after the stationary test or sequence deconstruction to obtain purified data. Specifically, the seasonal trend decomposition method decomposes the time series data, and the decomposition logic is as follows: , For seasonal items, For trend items, is the residual term, and the purified data is expressed as: ; Based on the cleaned data, the autoregressive integrated moving average model is used for modeling, and the optimal parameters are selected by the Akaike information criterion to perform rolling forecasts and output future predicted values, which are resource allocation values, resource demand values, or habitat characteristic values. Specifically, the cleaned data set is expressed as follows: By minimizing the Akaike information criterion, the order suitable for the autoregressive integrated moving average model is found, thereby constructing the optimal autoregressive integrated moving average model. This is the existing technology and will not be described in detail here. The autoregressive integrated moving average model is used to perform rolling forecasts to calculate future forecast values. The calculation logic of the forecast value is: , is the predicted value for the next moment, For the moment The previous cleansed data, is the model error term, is the autoregressive coefficient, is the sliding average coefficient, and is the order of the autoregressive integrated moving average model; and are the orders of the autoregressive part and the moving average part, respectively, obtained by the Akaike information criterion; It is used to represent the difference between the model prediction value and the actual observation value, and the value is determined by the actual fluctuation of the data and the model prediction error; Used to express the past The degree of influence of the purified data at a certain moment on the current predicted value, with a value range of [-1,1]; Used to express the past The degree of influence of the prediction error at each moment on the current prediction value, with a value range of [-1,1]; The demand fluctuation energy is calculated based on the instantaneous deviation between the actual value and the predicted value, combined with the fluctuation rate obtained based on the purified data. Specifically, the calculation logic of the instantaneous deviation between the actual value and the predicted value is as follows: , For the moment The instantaneous deviation between the actual value and the predicted value, is the actual value, is the predicted value; the calculation logic of volatility is: , Net data at time The corresponding standard deviation, is the smoothing factor, and its value range is [0,1]. The calculation logic of demand fluctuation energy is: , Energy demand fluctuations, is a constant; Used to prevent the denominator from being zero, the value range is [ , ].

[0025] The present invention is further configured to synthesize an environmental effect field based on demand fluctuation energy, and the calculation logic of the environmental effect field is: ,in, For the moment The environmental effect field value, is the number of input features, is the feature weight, is the sensitivity coefficient, For the Features at the moment Demand fluctuation energy; environmental effect field value Perform standardization operations to obtain , converting the environmental state into a unified measurement range; specifically, through the demand fluctuation energy of each feature and the sensitivity coefficient and weight of each feature, an environmental effect field value is comprehensively calculated to quantify the overall impact of the environmental state on agricultural resource management. The characteristics include habitat characteristics, namely meteorology, soil and resources; It is used to indicate the degree of influence of each feature on the environmental effect field. The value range is [0,1], and the sum of the weights is 1. To measure the The sensitivity of each feature to environmental effects, ranging from [0,1]; The present invention is further configured such that the dynamic control module is specifically configured to: The resource allocation function of agricultural product demand and inventory is constructed using the environmental effect field and inventory rate as input data, and the gradient descent method is used to optimize the resource allocation function; when it is detected that the environmental effect field is greater than the preset environmental effect field threshold, the emergency resource regulation strategy is initiated; specifically, the resource allocation function is used to describe the relationship between agricultural product demand and inventory level; in the process of optimizing resource allocation, the gradient descent method is used to iteratively update the current resource allocation value to gradually approach the optimal resource allocation value to minimize the resource allocation function; the goal of the emergency strategy is to reduce the negative impact of environmental changes on agricultural product production and ensure the stability and production capacity of agricultural product production. The adjustment of the emergency resource regulation strategy includes increasing the emergency allocation of resources and readjusting the resource allocation ratio, giving priority to supporting the most critical links.

[0026] The present invention is further configured such that the calculation logic of the resource allocation function is: ,in, Allocate functions for resources, Assign values to resources, For the moment The environmental effect field value, is the inventory rate, Assign a value to the minimum resource, is the resource demand elasticity index, is the environmental effect field coupling coefficient, is the resource weighting factor; specifically, the resource allocation function calculates a value that measures the resource allocation benefit based on the environmental effect field, resource allocation value and inventory rate; the inventory rate Indicates the ratio of the previous inventory level to the ideal inventory level; It is used to reflect the sensitivity between output and resource allocation, with a value range of [0,1]; It is used to indicate the degree of influence of the environmental effect field on resource allocation, with a value range of [0,1]; The weight used to adjust the impact of inventory rate on resource allocation is in the range of [0,1]. By introducing the environmental effect field value, agricultural product production can adapt to changes in external environment such as climate and weather, adjust resource input in a timely manner, and avoid excessive consumption or waste of resources by controlling inventory rate and minimum resource demand.

[0027] The present invention is further configured such that the gradient descent method optimizes the resource allocation function, specifically for: The resource allocation is adjusted by iteratively updating the current resource allocation value. When the difference between the resource allocation value of the next iteration step and the current resource allocation value is less than the preset iteration threshold, the iteration is stopped and the resource allocation is considered to have converged to the optimal value. Specifically, the calculation logic of the iterative update is as follows: ,in, Assign a value to the current resource, Assign values to the updated resources, is the learning rate, 、 and is a constant, For the environmental effect field, is the inventory rate, Assign a value to the minimum resource; It is used to control the update step size of each gradient descent iteration and determine the update rate during the optimization process. The value range is [0.001, 1]; Used to control the nonlinear effect of resource allocation, the value range is [1,3]; Used to adjust the attenuation rate of the impact of the environmental effect field on resource allocation, with a value range of [0.1,1]; The penalty coefficient used to adjust resource allocation has a value range of [0,1]. and When the difference between them is less than the preset iteration threshold, it is considered that the iteration has achieved sufficient accuracy and further calculation is stopped; the optimal resource allocation value is gradually approached by the gradient descent method, and resource configuration can be automatically adjusted according to environmental changes and demand fluctuations to ensure efficient use of resources.

[0028] The present invention is further configured such that the policy execution module is specifically configured to: Taking the optimal resource allocation value and the current inventory status as input data, the three-level resource allocation strategy is generated by adjusting resource allocation according to the inventory level; When the inventory ratio is greater than the first inventory benchmark, resource allocation and agricultural product prices are adjusted downwards; When the inventory ratio is greater than the second inventory benchmark and less than or equal to the first inventory benchmark, the current resource allocation and agricultural product prices are maintained; When the inventory ratio is less than or equal to the second inventory benchmark, resource allocation and agricultural product prices are adjusted upwards. Specifically, the three-level resource allocation strategy is an inventory-driven dynamic resource adjustment to avoid waste caused by inventory backlogs and prevent insufficient inventory from affecting supply. Comprehensively evaluate the benefits of each channel and prioritize the channels. The calculation logic of the benefit evaluation function is: ,in, For channels The benefits, For channels Historical conversion rates, For channels Real-time traffic quality, is the weight coefficient, according to Sort in descending order and allocate promotion resources first Channels with high values; specifically, the benefit evaluation function is used to evaluate and rank the benefits of different resource delivery channels; historical conversion rate refers to each channel's past conversion performance, such as the historical sales data of an e-commerce platform; real-time traffic quality refers to the quality of the channel's current visits and purchasing behavior, and whether it is high-intent traffic; Used to adjust the historical conversion rate to benefit The contribution of the channel ranges from [0,1]; for all channels, , sorted in descending order, prioritizing the allocation of promotion resources to High-level channels, promotional resources include exposure, budget and traffic; Use the customer value analysis model to group consumers and calculate each consumer's customer value score based on a weighted combination of the last purchase time, purchase frequency, and purchase amount; Set a customer value benchmark score and push personalized marketing plans to customers whose customer value scores are greater than the customer value benchmark score and those whose customer value scores are less than the customer value benchmark score. Specifically, the calculation logic of the customer value score is: ,in, For the Customer value rating, For customers Time since the last purchase (number of days), for, client Number of purchases (number of purchases per unit time), For customers Cumulative purchase amount, 、 and is the weighting coefficient; 、 and For adjustment 、 and The contribution degree to customer value score ranges from [0,1]. 、 and The sum is 1; when the customer value score is greater than the customer value benchmark score, the push frequency is increased; when the customer value score is less than the customer value benchmark score, an incentive plan is pushed.

[0029] The present invention is further configured such that the system further includes a feedback learning module, specifically configured to: Continuously monitor the deviation between actual and predicted outputs during agricultural product production and supply, and gradually adjust the parameters in the environmental effect field calculation logic, including feature weights and sensitivity coefficients. Based on real-time production and supply data, optimize strategies to improve the accuracy of resource allocation and inventory management. Specifically, the feature weight adjustment logic is as follows: ,in, For the updated feature weights, is the learning rate, For the moment actual output; For the moment The forecast production For the The absolute value of the demand fluctuation capacity of each characteristic, is the sum of demand fluctuation energy of all features; The calculation logic is: ,in, Assign a value to the resource at the current moment, For the moment The environmental effect field value, For the current moment inventory levels, is the bias term, 、 and is the weight coefficient; 、 and It is used to reflect the contribution of resource allocation value, environmental effect field value and inventory level to production forecast. Each weight coefficient is adjusted independently and the value is obtained through training. It is used to adjust the benchmark output of the predicted output to make the predicted output closer to the actual output. The value depends on the characteristics of the actual data and the training result. Inventory levels The calculation logic is: ,in, is the inventory level at the previous moment, For the current moment The number of products produced, For the current moment the quantity of product sold or consumed; The parameter for adjusting the update amplitude of feature weights has a value range of [0,1]. The adjustment logic of the sensitivity coefficient is: ,in, After the update The sensitivity coefficient of each feature, For the The sensitivity coefficient of each feature, is the learning rate, is the partial derivative of the resource allocation function with respect to the environmental effect field, The environmental effect field The partial derivative of the characteristic demand fluctuation energy; Used to control the update step size, with a value range of [0,1]; strategy optimization is performed based on real-time production and supply data to improve the accuracy of resource allocation and inventory management. This means that during the production and supply of agricultural products, real-time production and supply conditions are continuously tracked and analyzed. Production conditions include output, inventory, and demand, and supply conditions include inventory consumption rate and external market demand. Resource allocation and inventory strategies are dynamically adjusted based on these data to ensure maximum efficiency of production and supply.

[0030] The present invention is further configured such that the system further includes a visualization module, specifically configured to: Quantify the effectiveness of resource allocation sensitivity, inventory turnover rate and marketing investment return rate indicators in real time through real-time monitoring dashboards; Automatically generate feedback reports that include resource demand and output trend charts, anomaly detection, and optimization suggestions. Based on the report analysis, the optimization suggestions propose specific optimization measures, including adjusting resource allocation strategies and improving resource utilization efficiency. Specifically, the main responsibility of the visualization module is to realize the real-time quantitative evaluation and strategy optimization feedback of the system operation effect, and transmit the results of the front-end execution back to the system for modifying the model and control plan to form a closed-loop system; the visualization module dynamically displays key performance indicators, including resource allocation sensitivity, inventory turnover rate and marketing investment return rate, through a real-time visualization interface, namely the monitoring dashboard; resource allocation sensitivity is used to measure the responsiveness of resource allocation to the external environment, reflecting the responsiveness of resource allocation strategies to environmental changes, such as demand fluctuations, weather changes or market changes, and how resource allocation responds dynamically. If the sensitivity is too low, resources may not be fully utilized or wasted; inventory turnover rate reflects the flow rate of agricultural products from storage to delivery. A high inventory turnover rate means that inventory management is good, there is no excessive backlog, and resources can be converted into sales as soon as possible to avoid expiration or waste; marketing The return on marketing investment is used to measure the ratio of marketing input to corresponding revenue. Marketing input includes advertising and promotional activities, and corresponding revenue includes sales. A high marketing return on investment means that marketing activities have generated higher returns, while a low marketing return on investment means that marketing investment has not been effectively rewarded and the strategy needs to be adjusted; the resource demand and output curve trend chart is used to show the relationship and trend between resource input and output. Resource input is further planned based on the resource allocation value. When the resource allocation value is larger, it means that there is higher output potential or resource demand under the current conditions, and it is suitable to increase investment; anomaly detection is used to monitor when certain data deviates from the predetermined standards or goals. The logic of anomaly detection can be performed by setting thresholds. For example, an anomaly is triggered when the inventory turnover rate is less than a preset threshold; through the visualization module, indicators of each link can be monitored in real time to ensure that resources are reasonably allocated, reduce waste, and optimize production efficiency.

[0031] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0032] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0033] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0034] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean 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 the present application.

[0035] Those skilled in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel 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.

[0036] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0037] In the several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0038] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0039] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0040] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method 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.

[0041] 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. The agricultural product precision marketing and sales system based on big data is characterized by: include: Vector construction module: used to construct environmental kinetic energy characteristics based on the acquired raw data, construct a multidimensional agricultural efficiency vector based on the environmental kinetic energy characteristics, and set the multidimensional agricultural efficiency vector as input data; Environmental effect field generation module: used to input input data into a preset demand fluctuation energy calculation model, output demand fluctuation energy, and synthesize the environmental effect field based on the demand fluctuation energy; Dynamic control module: used to construct resource allocation function based on normalized environmental effect field and inventory rate to optimize dynamic resource allocation and calculate the optimal resource allocation value; Strategy execution module: used to optimize and regulate resource allocation strategies and agricultural product prices based on optimal resource allocation values, and implement strategies in the production and inventory management of agricultural products.

2. The agricultural product precision marketing and sales system based on big data according to claim 1 is characterized in that: The original data include meteorological data, soil data, biological stress data, and resource flow data; The meteorological data includes accumulated temperature, precipitation anomaly, and solar radiation; the soil data includes moisture content and nitrogen, phosphorus, and potassium content; the biotic stress data includes pest and disease density, weed coverage, and pathogen index; the resource flow data includes logistics costs and price fluctuations of competing products; Environmental kinetic characteristics include resource allocation characteristics, consumer kinetic characteristics, and habitat characteristics; Construct a multidimensional agricultural efficiency vector based on resource allocation characteristics, consumer kinetic characteristics and habitat characteristics; Resource allocation characteristics include agricultural product output, consumer kinetic characteristics include agricultural product demand, and habitat characteristics include meteorological data, soil data, biological stress data, and resource flow data.

3. The agricultural product precision marketing and sales system based on big data according to claim 1 is characterized in that: The construction logic of the preset demand fluctuation energy calculation model includes: The historical data of multidimensional agricultural efficiency vectors in time series are set as input, and the enhanced Dickey-Fuller test is used to test the data for stationarity. If the data fails the stationarity test, the multidimensional agricultural efficiency vectors are subjected to sequence deconstruction and the order of sequence deconstruction is determined to obtain the stationary time series data after sequence deconstruction. The stationary time series data that have passed the stationary test or series deconstruction are seasonally decomposed using the seasonal trend decomposition method to obtain purified data; Based on the purified data, an autoregressive integrated moving average model is used to build a model, and the optimal parameters are selected by the Akaike information criterion to perform rolling predictions and output future predicted values, which are resource allocation values, resource demand values, or habitat characteristic values; The demand fluctuation energy is calculated based on the instantaneous deviation between the actual value and the predicted value, combined with the fluctuation rate obtained based on the purified data.

4. The agricultural product precision marketing and sales system based on big data according to claim 3 is characterized in that: The environmental effect field is synthesized based on the demand fluctuation energy. The calculation logic of the environmental effect field is as follows: ,in, For the moment The environmental effect field value, is the number of input features, is the feature weight, is the sensitivity coefficient, For the Features at the moment Energy demand fluctuations; Environmental effect field value Perform standardization operations to obtain , converting the environmental state into a unified measurement range.

5. The agricultural product precision marketing and sales system based on big data according to claim 1 is characterized in that: The dynamic control module is specifically used to: The resource allocation function of agricultural product demand and inventory is constructed using environmental effect field and inventory rate as input data, and the resource allocation function is optimized using gradient descent method. When the environmental effect field is detected to be greater than the preset environmental effect field threshold, the emergency resource control strategy is activated.

6. The agricultural product precision marketing and sales system based on big data according to claim 5 is characterized in that: The calculation logic of the resource allocation function is: ,in, Allocate functions for resources, Assign values to resources, For the moment The environmental effect field value, is the inventory rate, Assign a value to the minimum resource, is the resource demand elasticity index, is the environmental effect field coupling coefficient, is the resource weighting factor.

7. The agricultural product precision marketing and sales system based on big data according to claim 6 is characterized in that: The gradient descent method is used to optimize the resource allocation function, specifically for: Adjust the resource allocation by iteratively updating the current resource allocation value; When the difference between the resource allocation value of the next iteration step and the current resource allocation value is less than a preset iteration threshold, the iteration is stopped and it is considered that the resource allocation has converged to the optimal value.

8. The agricultural product precision marketing and sales system based on big data according to claim 1 is characterized in that: The policy execution module is specifically used to: Taking the optimal resource allocation value and the current inventory status as input data, the three-level resource allocation strategy is generated by adjusting resource allocation according to the inventory level; When the inventory ratio is greater than the first inventory benchmark, resource allocation and agricultural product prices are adjusted downwards; When the inventory ratio is greater than the second inventory benchmark and less than or equal to the first inventory benchmark, the current resource allocation and agricultural product prices are maintained; When the inventory ratio is less than or equal to the second inventory benchmark, resource allocation and agricultural product prices will be adjusted upwards; Comprehensively evaluate the benefits of each channel and prioritize the channels. The calculation logic of the benefit evaluation function is: ,in, For channels The benefits, For channels Historical conversion rates, For channels Real-time traffic quality, is the weight coefficient, according to Sort in descending order and allocate promotion resources first High-value channels; Use the customer value analysis model to group consumers and calculate each consumer's customer value score based on a weighted combination of the last purchase time, purchase frequency, and purchase amount; Set a customer value benchmark score and push personalized marketing plans to customers whose customer value scores are greater than the customer value benchmark score and customers whose customer value scores are less than the customer value benchmark score.

9. The agricultural product precision marketing and sales system based on big data according to claim 1 is characterized in that: The system also includes a feedback learning module, specifically configured to: Continuously monitor the deviation between actual and predicted outputs during the production and supply of agricultural products, and gradually adjust parameters in the environmental effect field calculation logic, including feature weights and sensitivity coefficients; Optimize strategies based on real-time production and supply data to improve the accuracy of resource allocation and inventory management.

10. The agricultural product precision marketing and sales system based on big data according to claim 1 is characterized in that: The system also includes a visualization module, specifically configured to: Quantify the effectiveness of resource allocation sensitivity, inventory turnover rate and marketing investment return rate indicators in real time through real-time monitoring dashboards; Automatically generate feedback reports that include resource demand and output curve trend charts, anomaly detection, and optimization suggestions. Based on the report analysis, the optimization suggestions propose specific optimization measures, including adjusting resource allocation strategies and improving resource utilization efficiency.

Images