Farm fresh vegetable precise distribution system and method based on intelligent algorithm

Abstract

The present invention relates to the technical field of farm vegetable distribution, and more specifically to a system and method for precise distribution of fresh vegetables on farms based on intelligent algorithms. The system comprises a data collection module, an intelligent prediction module, a resource optimization and allocation module, a precise distribution module, and a user interaction module. The system comprises: the data collection module is responsible for collecting data from multiple sources; the intelligent prediction module predicts market demand dynamics and analyzes demand changes; the resource optimization and allocation module dynamically adjusts vegetable planting plans, planting area allocation, supply chain network design, and warehouse inventory levels; the precise distribution module is responsible for implementing distribution plans; and the user interaction module provides a user interface that allows consumers to view the types and quantities of vegetables that are about to arrive. The present invention not only makes farm production activities more flexible and efficient, but also minimizes costs and time, ensuring the efficient operation of the supply chain.

Description

Technical Field

[0001] The present invention relates to the technical field of farm vegetable distribution, and in particular to a system and method for accurately distributing fresh vegetables on a farm based on an intelligent algorithm. Background Art

[0002] In the current agricultural production and distribution field, especially in the supply chain management of fresh vegetables, there are a series of challenges, including how to accurately predict market demand, effectively manage resources, reduce logistics costs, and improve consumer satisfaction. Traditional methods often rely on experience-based judgment and static supply chain design, and lack the ability to respond quickly to dynamic changes in market demand, resulting in uneven resource allocation, low production efficiency, and time delays and increased costs in logistics and distribution. In addition, due to the lack of the ability to deeply analyze consumer behavior, it is difficult to accurately meet consumers' specific needs for fresh vegetables, affecting their purchasing experience and satisfaction.

[0003] The rapid development of information technology has provided new ideas and methods for solving these problems. By utilizing big data analysis and intelligent forecasting technologies, accurate forecasting and dynamic adaptation to market demand can be achieved, and resource allocation and supply chain management can be optimized. However, effectively integrating these technologies into the distribution system of agricultural products to achieve optimized management of the entire chain from farm to table still faces challenges in technology integration, data processing, and system design. Summary of the Invention

[0004] Based on the above objectives, the present invention provides a system and method for precise distribution of fresh vegetables on farms based on intelligent algorithms.

[0005] The farm fresh vegetable precision distribution system based on intelligent algorithms includes data collection module, intelligent prediction module, resource optimization and allocation module, precision distribution module and user interaction module, among which;

[0006] The data collection module is responsible for collecting data from multiple sources, including farm vegetable growth data, climate and environmental data, market demand data, and consumer behavior data;

[0007] The intelligent forecasting module uses a forecasting model to comprehensively analyze data from multiple sources to predict market demand dynamics. It uses scenario simulation technology to construct market scenarios, analyze demand changes, and provide decision support for resource optimization. The intelligent forecasting module also includes a real-time data feedback mechanism to adjust the forecasting model and consumer behavior analysis based on real-time market feedback.

[0008] The resource optimization and allocation module dynamically adjusts vegetable planting plans, planting area allocation, supply chain network design, and warehouse inventory levels based on the demand forecast results provided by the intelligent forecast module to minimize costs and time while meeting market demand;

[0009] The precise distribution module is responsible for implementing the distribution plan based on the output of the resource optimization and allocation module, and selecting the distribution route by using real-time traffic data and distribution network analysis;

[0010] The user interaction module provides a user interface that allows consumers to view the types and quantities of vegetables that are about to arrive, make reservations and purchases, and collect user feedback and purchase history to provide valuable consumer behavior data for the intelligent prediction module.

[0011] Furthermore, the data collection module includes:

[0012] Farm vegetable growth data collection: A sensor network installed on the farm collects real-time data on vegetable growth, including plant growth rate, leaf area index, soil moisture, and root zone temperature, and transmits the collected data.

[0013] Climate and environmental data collection: Combined with weather station and satellite data, climate and environmental data around the farm and within a wide area are collected. Climate and environmental data include temperature, precipitation, wind speed, and relative humidity.

[0014] Market demand data collection: Market demand data is collected through historical sales records, transaction data from online market platforms, and sales reports provided by partner retailers. Market demand data includes sales data, market trends and seasonal demand, competition analysis, and macroeconomic and social factors;

[0015] Consumer behavior data collection: Collect users' purchase history, evaluation feedback, and browsing habits, and combine social media tools to obtain consumers' preferences for agricultural products, purchase intentions, and opinions on brand and quality from public social networks and forums.

[0016] Furthermore, the intelligent prediction module includes:

[0017] Comprehensive analysis of multi-source data: Comprehensively collect data from multiple sources from the data collection module, and use data cleaning and pre-processing technology to ensure data quality and consistency;

[0018] Prediction model construction: Build a prediction model based on the comprehensive analysis data, identify patterns and trends in the data, and predict the dynamic changes in market demand;

[0019] Application of scenario simulation technology: Build multiple market scenarios through scenario simulation technology, and use forecasting models to analyze demand changes under various market scenarios;

[0020] Real-time data feedback mechanism: The intelligent forecasting module integrates a real-time data feedback mechanism to monitor market feedback and sales data in real time. By analyzing real-time data, it automatically adjusts and optimizes the forecasting model.

[0021] Consumer Behavior Analysis: Analyze unstructured data from social media, online reviews, and user feedback using natural language processing (NLP) and sentiment analysis techniques to understand consumer behavior and preferences.

[0022] Furthermore, the prediction model adopts a factorization machine (FM) model, and the factorization machine (FM) model includes:

[0023] Introducing the time factor: By introducing the time factor to reflect the impact of different time periods (such as seasons and months) on the demand for agricultural products, the calculation formula is:

[0024]

[0025] in, represents the demand forecast value based on product characteristics and time factors, v prod represents the product feature vector, T is the total number of time periods, v t The vector representation of the t-th time period, x prod and x t are indicator variables for product and time period, respectively;

[0026] Introducing geographic location coding: By introducing geographic location coding, we can capture the differences in demand for agricultural products in different regions. The calculation formula is:

[0027]

[0028] in, represents the final predicted value after considering the geographic location encoding, L is the total number of geographic locations, v locl The vector representing the lth geographical location, x locl is the indicator variable for geographic location l.

[0029] Furthermore, the scenario simulation technology application includes:

[0030] Scenario definition: Define multiple market scenarios, including economic fluctuations, seasonal changes, and changes in consumer trends. Under each scenario, set parameters and indicators to simulate different market environments and consumer behavior patterns;

[0031] Data preparation: For each market scenario, collect and prepare relevant historical and forecast data, including historical sales data, seasonal factors, economic indicators (such as GDP growth rate, unemployment rate, etc.), and consumer survey data;

[0032] Scenario simulation: Utilizing scenario simulation technology, according to each defined market scenario, by adjusting the corresponding parameters and indicators, the market environment under the corresponding scenario is simulated, including economic fluctuation scenario, seasonal change scenario and consumption trend change scenario, among which;

[0033] The economic fluctuation scenario simulates the impact of different economic environments (such as economic growth and recession) on vegetable demand by adjusting the values ​​of economic indicators (such as economic growth rate and unemployment rate);

[0034] The seasonal change scenario simulates the impact of seasonal factors on vegetable demand based on the climate characteristics of different seasons and changes in consumer purchasing habits;

[0035] The consumption trend change scenario simulates the potential impact of the changing trend on vegetable demand based on the changing trend of consumer preferences;

[0036] Demand change analysis: Apply the factorization machine (FM) forecasting model, use the various scenario parameters obtained from scenario simulation as input, calculate the vegetable demand forecast value under each scenario through the forecasting model, compare the demand forecast results under different scenarios, and obtain the impact of economic fluctuations, seasonal changes, and changes in consumption trends on vegetable demand.

[0037] Furthermore, the consumer behavior analysis includes:

[0038] Data collection: Collect unstructured text data from online reviews on social media platforms, e-commerce websites, and direct user feedback;

[0039] Text preprocessing: This cleanses text data and reduces noise for subsequent processing by performing basic NLP operations such as stop word removal, stemming, and part-of-speech tagging.

[0040] Sentiment analysis: Apply sentiment analysis technology to judge the sentiment tendency of the preprocessed text, and use logistic regression to calculate the sentiment score S(d) of text d. The calculation formula is:

[0041]

[0042] Among them, x1,…,x n is the eigenvector, β0,β1,…,β n It is the weight parameter learned through training data;

[0043] Consumer Preference Extraction: Based on sentiment analysis results, extract and summarize consumer preferences and demands for agricultural products. Use the LDA topic model to identify the main topics and preferences in the reviews. Given a word w in document d, the topic distribution of word w is calculated as:

[0044] p(z|d,w)∝p(z|d) p(w|z);

[0045] Here, p(z|d) is the distribution of topic z in document d, and p(w|z) is the distribution of word w under topic z.

[0046] Furthermore, the resource optimization configuration module includes:

[0047] Demand forecast result reception: receiving information on vegetable types, expected demand, and demand fluctuations provided by the intelligent forecast module;

[0048] Adjustment of vegetable planting plan: Based on the forecast results, calculate the optimal planting ratio and planting area of ​​various vegetables. The calculation formula is: A opt =D pred / Y avg ;

[0049] Among them, A opt is the optimized planting area, D pred is the forecast demand, Y avg is the average yield per unit area;

[0050] Supply chain network optimization: Analyze the logistics cost and time between each supply chain node (such as farms, processing plants, warehouses), optimize the logistics path and supply chain structure, and calculate the formula: C min =min∑ i,j (T ij C ij );

[0051] Among them, C min represents the minimum logistics cost, T ij is the transportation time from node i to node j, C ij is the corresponding unit cost;

[0052] Warehouse inventory level optimization: Using forecasted demand and historical sales data, determine the optimal inventory level for each warehouse location to reduce inventory costs and the risk of unsold goods. The calculation formula is:

[0053] Among them, S opt is the optimized inventory level, σ is the safety stock coefficient, D var is the variance of demand fluctuations.

[0054] Furthermore, the precise distribution module includes:

[0055] Receive delivery plan: Receive the delivery plan, which includes the type, quantity, destination and scheduled delivery time of vegetables to be delivered;

[0056] Real-time traffic data acquisition: Real-time collection of traffic data, including road conditions, traffic restrictions, and estimated travel times, using various traffic information sources, including GPS navigation and traffic management department data;

[0057] Distribution network analysis: Analyze the distribution network structure, including warehouse locations, distribution point distribution, and transportation routes, to determine distribution path options;

[0058] Delivery route selection: Combining real-time traffic data and distribution network analysis, we use optimization algorithms to determine the delivery route;

[0059] Delivery execution and monitoring: Execute delivery tasks based on the selected delivery route and monitor the delivery status in real time.

[0060] Furthermore, the calculation formula of the optimization algorithm is:

[0061]

[0062] Among them, P best represents the optimal delivery path, is the set of all delivery routes, T i and C i are the estimated travel time and delivery cost of path i, respectively, and n is the number of paths.

[0063] The farm fresh vegetable precision distribution method based on intelligent algorithms is implemented by the above-mentioned farm fresh vegetable precision distribution system based on intelligent algorithms, and includes the following steps:

[0064] S1, data collection: Collect data from multiple sources, including farm vegetable growth data, climate and environmental data, market demand data, and consumer behavior data;

[0065] S2, Demand Forecasting and Scenario Simulation: Use forecasting models to comprehensively analyze data collected from multiple sources to predict dynamic changes in market demand. Use scenario simulation technology to construct different market scenarios and analyze demand changes under different market scenarios. Use a real-time data feedback mechanism to adjust the forecasting model based on real-time market feedback.

[0066] S3, resource optimization and allocation: Based on the demand forecast results provided by the intelligent forecasting module, the vegetable planting plan, planting area allocation, supply chain network design, and storage inventory levels are dynamically adjusted;

[0067] S4, Precision Delivery Implementation: Based on the output of resource optimization allocation, responsible for formulating and implementing delivery plans, using real-time traffic data and distribution networks to select delivery routes;

[0068] S5, User Interaction and Feedback Collection: Provides a user interface that allows consumers to view the types and quantities of vegetables that are about to arrive, and make reservations and purchases. By collecting user feedback and purchase history, it provides consumer behavior data to optimize prediction accuracy and delivery efficiency.

[0069] Beneficial effects of the present invention:

[0070] The present invention provides real-time and historical data support for the intelligent prediction module and resource optimization configuration module by collecting farm vegetable growth data, climate and environmental data, market demand data, and consumer behavior data from multiple dimensions, ensuring that the decisions of the entire system are based on the latest and most accurate information. This not only enhances the accuracy and timeliness of the prediction, but also provides strong data support for the optimization of farm management, resource allocation, and distribution strategies, thereby significantly improving production efficiency and resource utilization and reducing resource waste.

[0071] The present invention, through an intelligent prediction module combined with scenario simulation technology and a real-time data feedback mechanism, can dynamically adapt to changes in market demand and promptly adjust vegetable planting plans, supply chain designs, and warehouse inventory levels. This dynamic adaptability not only makes farm production activities more flexible and efficient, but also minimizes costs and time, ensuring the efficient operation of the supply chain. By precisely controlling agricultural production activities, it further achieves the sustainable use of water resources and energy, minimizing the impact on the environment.

[0072] The present invention ensures that vegetables are delivered to consumers quickly and freshly by optimizing the delivery route. In addition, the introduction of the user interaction module provides an intuitive and friendly user interface, allowing consumers to easily view, reserve and purchase fresh vegetables. At the same time, by collecting user feedback and purchase history, the prediction model and delivery strategy are further optimized, which not only improves the consumer's purchasing experience, but also enhances the market's response speed and service quality, ultimately achieving the goals of reducing waste, lowering costs and improving consumer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0074] Figure 1 Schematic diagram of system function modules according to an embodiment of the present invention;

[0075] Figure 2 Schematic diagram of the delivery method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0076] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0077] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0078] like Figure 1 As shown, the farm fresh vegetable precision distribution system based on intelligent algorithm includes data collection module, intelligent prediction module, resource optimization configuration module, precision distribution module and user interaction module, among which;

[0079] The data collection module is responsible for collecting data from multiple sources, including farm vegetable growth data, climate and environmental data, market demand data, and consumer behavior data. The data collection module provides real-time and historical data support to ensure that other modules operate based on the latest and most accurate information;

[0080] The intelligent forecasting module uses a forecasting model to comprehensively analyze data from multiple sources to predict market demand dynamics. It uses scenario simulation technology to construct market scenarios, analyze demand changes, and provide decision support for resource optimization. The intelligent forecasting module also includes a real-time data feedback mechanism to adjust the forecasting model and consumer behavior analysis based on real-time market feedback.

[0081] The resource optimization module dynamically adjusts vegetable planting plans, planting area allocation, supply chain network design, and warehouse inventory levels based on the demand forecast results provided by the intelligent prediction module to minimize costs and time while meeting market demand. By precisely controlling agricultural production activities, it achieves sustainable use of water and energy and reduces resource waste.

[0082] The precision distribution module is responsible for implementing the distribution plan based on the output of the resource optimization module. It uses real-time traffic data and distribution network analysis to select distribution routes to ensure that vegetables are delivered to consumers quickly and freshly.

[0083] The user interaction module provides a user interface that allows consumers to view the types and quantities of vegetables that are about to arrive, make reservations, and purchase them. The user interaction module collects user feedback and purchase history, providing valuable consumer behavior data for the intelligent prediction module;

[0084] Through the design and interaction of the above modules, the present invention realizes intelligent management of the entire process of vegetable growth to distribution. Through the intelligent prediction module and resource optimization configuration module, it can dynamically adapt to changes in market demand, optimize resource allocation, and improve distribution efficiency, ultimately achieving the goals of reducing waste, lowering costs and improving consumer satisfaction.

[0085] The data collection modules include:

[0086] Farm vegetable growth data collection: A sensor network installed on the farm collects real-time data on vegetable growth, including plant growth rate, leaf area index, soil moisture, and root zone temperature. The collected data is then transmitted for subsequent analysis and decision support.

[0087] Climate and environmental data collection: Combine weather station and satellite data to collect climate and environmental data around the farm and within a wider area. Climate and environmental data includes temperature, precipitation, wind speed, and relative humidity. Through the API interface, the data provided by the meteorological service platform is integrated to obtain more comprehensive and accurate climate information.

[0088] Market demand data collection: Market demand data is collected through historical sales records, transaction data from online market platforms, and sales reports provided by partner retailers. Market demand data includes sales data, market trends and seasonal demand, competition analysis, and macroeconomic and social factors;

[0089] Consumer behavior data collection: Collect users' purchase history, evaluation feedback, and browsing habits. Combined with social media tools, this data can be used to obtain consumer preferences for agricultural products, purchase intentions, and opinions on brand and quality from public social networks and forums.

[0090] Through the above methods, the data collection module can comprehensively collect farm vegetable growth data, climate and environmental data, market demand data, and consumer behavior data from multiple dimensions. The comprehensive analysis and application of these data provide accurate decision-making support information for the intelligent prediction module and resource optimization allocation module, thereby improving vegetable production efficiency, reducing resource waste, and optimizing the distribution process to ensure that consumers can obtain fresh agricultural products in a timely manner.

[0091] The intelligent prediction module includes:

[0092] Comprehensive analysis of multi-source data: Comprehensively collect data from multiple sources from the data collection module, and use data cleaning and pre-processing technology to ensure data quality and consistency;

[0093] Prediction model construction: Build a prediction model based on the comprehensive analysis data, identify patterns and trends in the data, and predict the dynamic changes in market demand;

[0094] Application of scenario simulation technology: Through scenario simulation technology, we can construct various market scenarios and use forecasting models to analyze demand changes under various market scenarios. Through multi-dimensional decision support tools, we can make the most appropriate adjustments to resource optimization allocation based on different market conditions.

[0095] Real-time data feedback mechanism: The intelligent forecasting module integrates a real-time data feedback mechanism to monitor market feedback and sales data in real time. By analyzing real-time data, it automatically adjusts and optimizes the forecasting model to improve forecast accuracy.

[0096] Consumer behavior analysis: Using natural language processing (NLP) and sentiment analysis techniques, we analyze unstructured data from social media, online reviews, and user feedback to understand consumer behavior and preferences. The results are used to refine market demand forecasts and predict demand for vegetable varieties.

[0097] Through the above method, the intelligent forecasting module can not only accurately predict the dynamic changes in market demand, but also flexibly adjust the forecasting model according to different scenarios and real-time market feedback, ensuring that the resource optimization and allocation module can make decisions based on the latest and most accurate demand forecasts, thereby optimizing the operating efficiency of the entire system and improving the production and distribution of fresh vegetables on the farm.

[0098] The prediction model uses the Factorization Machine (FM) model, which includes:

[0099] Introducing the time factor: By introducing the time factor to reflect the impact of different time periods (such as seasons and months) on the demand for agricultural products, the calculation formula is:

[0100]

[0101] in, represents the demand forecast value based on product characteristics and time factors, v prod represents the product feature vector, T is the total number of time periods, v t The vector representation of the t-th time period, x prod and x t are indicator variables for product and time period, respectively;

[0102] Introducing geographic location coding: By introducing geographic location coding, we can capture the differences in demand for agricultural products in different regions. The calculation formula is:

[0103]

[0104] in, represents the final predicted value after considering the geographic location encoding, L is the total number of geographic locations, v locl The vector representing the lth geographical location, x locl is the indicator variable of geographical location l;

[0105] The factor decomposition machine model can effectively capture and predict the demand for agricultural products based on seasonal and geographical differences. The introduced time factor allows the model to understand and predict changes in demand for agricultural products in different seasons or specific time periods. For example, the demand for certain vegetables may increase significantly in summer, while the demand decreases in winter. The model can make accurate demand forecasts by learning these seasonal patterns. The introduced geographic location coding takes into account the differences in demand for agricultural products in different regions. Due to differences in climate, eating habits and other factors, the demand for the same agricultural product in different regions may vary greatly. The geographic location coding enables the model to take into account the influence of these geographical factors when making demand forecasts. Therefore, the factor decomposition machine model not only improves the accuracy of agricultural product demand forecasts, but also provides strong data support in resource allocation, production planning and optimization of distribution routes.

[0106] Applications of scenario simulation technology include:

[0107] Scenario definition: Define multiple market scenarios, including economic fluctuations, seasonal changes, and changes in consumer trends. Under each scenario, set parameters and indicators to simulate different market environments and consumer behavior patterns;

[0108] Data preparation: For each market scenario, collect and prepare relevant historical and forecast data, including historical sales data, seasonal factors, economic indicators (such as GDP growth rate, unemployment rate, etc.), and consumer survey data;

[0109] Scenario simulation: Utilizing scenario simulation technology, according to each defined market scenario, by adjusting the corresponding parameters and indicators, the market environment under the corresponding scenario is simulated, including economic fluctuation scenario, seasonal change scenario and consumption trend change scenario, among which;

[0110] The economic fluctuation scenario simulates the impact of different economic environments (such as economic growth and recession) on vegetable demand by adjusting the values ​​of economic indicators (such as economic growth rate and unemployment rate);

[0111] The seasonal change scenario simulates the impact of seasonal factors on vegetable demand based on the climate characteristics of different seasons and changes in consumer purchasing habits;

[0112] The consumption trend change scenario simulates the potential impact of changing trends on vegetable demand based on the changing trends in consumer preferences, such as the rise of healthy eating trends;

[0113] Demand change analysis: Using a factorization machine (FM) forecasting model, we used various scenario parameters obtained from scenario simulation as input. The forecast model calculated the vegetable demand forecast for each scenario, compared the demand forecast results under different scenarios, and analyzed the impact of economic fluctuations, seasonal changes, and changes in consumption trends on vegetable demand.

[0114] Through the above steps, the scenario simulation technology application of the present invention can effectively construct and analyze demand changes under different market scenarios, and provide scientific data support for the production planning, inventory management and distribution strategy optimization of fresh vegetables on the farm.

[0115] Consumer behavior analysis includes:

[0116] Data collection: Collect unstructured text data from online reviews on social media platforms, e-commerce websites, and direct user feedback;

[0117] Text preprocessing: This cleanses text data and reduces noise for subsequent processing by performing basic NLP operations such as stop word removal, stemming, and part-of-speech tagging.

[0118] Sentiment analysis: Apply sentiment analysis technology to the preprocessed text to judge the sentiment tendency, such as whether the text expresses positive emotions, negative emotions, or neutral emotions. Logistic regression is used to calculate the sentiment score S(d) of the text d. The calculation formula is:

[0119]

[0120] Among them, x1,…,x n is a feature vector, including word frequency, the occurrence of specific sentiment words, etc., β0,β1,…,β n It is the weight parameter learned through training data;

[0121] Consumer Preference Extraction: Based on sentiment analysis results, extract and summarize consumer preferences and demands for agricultural products. Use the LDA topic model to identify the main topics and preferences in the reviews. Given a word w in document d, the topic distribution of word w is calculated as:

[0122] p(z|d,w)∝p(z|d)·p(w|z);

[0123] Where p(z|d) is the distribution of topic z in document d, and p(w|z) is the distribution of word w under topic z;

[0124] By deeply analyzing consumers' comments and feedback on social media and online platforms, we can effectively understand consumers' emotional tendencies and consumption preferences for different vegetable varieties. This information is of great value for predicting market demand, adjusting product supply, optimizing distribution plans, and improving consumer satisfaction. Through the application of NLP and sentiment analysis technology, valuable insights can be automatically extracted from large amounts of unstructured data to support a more data-driven decision-making process. This not only improves the efficiency of the distribution system, but also enhances the ability to respond to changes in consumer demand, thereby gaining an advantage in the highly competitive market.

[0125] The resource optimization configuration module includes:

[0126] Demand forecast result reception: receiving information on vegetable types, expected demand, and demand fluctuations provided by the intelligent forecast module;

[0127] Adjustment of vegetable planting plan: Based on the forecast results, calculate the optimal planting ratio and planting area of ​​various vegetables. The calculation formula is: A opt =D pred / Y avg ;

[0128] Among them, A opt is the optimized planting area, D pred is the forecast demand, Y avg is the average yield per unit area;

[0129] Supply chain network optimization: Analyze the logistics cost and time between each supply chain node (such as farms, processing plants, warehouses), optimize the logistics path and supply chain structure, and calculate the formula: C min =min∑ i,j (T ij ·C ij );

[0130] Among them, C min represents the minimum logistics cost, T ij is the transportation time from node i to node j, C ij is the corresponding unit cost;

[0131] Warehouse inventory level optimization: Using forecasted demand and historical sales data, determine the optimal inventory level for each warehouse location to reduce inventory costs and the risk of unsold goods. The calculation formula is:

[0132] Among them, S opt is the optimized inventory level, σ is the safety stock coefficient, D varis the variance of demand fluctuations;

[0133] Through the above steps, the resource optimization and allocation module can achieve flexible adjustments to planting plans, supply chain networks, and warehousing management according to the dynamic changes in market demand, aiming to minimize costs and time while ensuring efficient satisfaction of market demand. This not only improves overall efficiency and response speed, but also enhances the ability to adapt to market changes, providing strong support for the precise distribution of agricultural products and optimized management of the supply chain.

[0134] The precision delivery module includes:

[0135] Receive delivery plan: Receive the delivery plan, which includes the type, quantity, destination and scheduled delivery time of vegetables to be delivered;

[0136] Real-time traffic data acquisition: Real-time collection of traffic data, including road conditions, traffic restrictions, and estimated travel times, using various traffic information sources, including GPS navigation and traffic management department data;

[0137] Distribution network analysis: Analyze the distribution network structure, including warehouse locations, distribution point distribution, and transportation routes, to determine distribution path options;

[0138] Delivery route selection: Combining real-time traffic data and distribution network analysis, we use optimization algorithms to determine the delivery route. The optimization goal is to minimize delivery time and cost while ensuring on-time delivery.

[0139] Delivery execution and monitoring: Execute delivery tasks based on the selected delivery route and monitor delivery status in real time to respond to possible traffic changes and other emergencies, ensuring efficient and timely delivery;

[0140] Through the above steps, the precise distribution module can effectively achieve fast and timely delivery of vegetables, minimizing delivery costs and time. This module not only improves delivery efficiency and customer satisfaction, but also enhances the adaptability and responsiveness of the entire supply chain, providing solid technical support for the precise distribution of fresh vegetables on the farm.

[0141] The calculation formula of the optimization algorithm is:

[0142]

[0143] Among them, P best represents the optimal delivery path, is the set of all delivery routes, T i and C i are the estimated travel time and delivery cost of path i, respectively, and n is the number of paths.

[0144] like Figure 2 As shown, the farm fresh vegetable precise distribution method based on intelligent algorithm is implemented by the above farm fresh vegetable precise distribution system based on intelligent algorithm, including the following steps:

[0145] S1, data collection: Collect data from multiple sources, including farm vegetable growth data, climate and environmental data, market demand data, and consumer behavior data;

[0146] S2, Demand Forecasting and Scenario Simulation: Use forecasting models to comprehensively analyze data collected from multiple sources to predict dynamic changes in market demand. Use scenario simulation technology to construct different market scenarios and analyze demand changes under different market scenarios. Use a real-time data feedback mechanism to adjust the forecasting model based on real-time market feedback.

[0147] S3, resource optimization and allocation: Based on the demand forecast results provided by the intelligent forecasting module, the vegetable planting plan, planting area allocation, supply chain network design, and storage inventory levels are dynamically adjusted;

[0148] S4, Precision Delivery Implementation: Based on the output of resource optimization allocation, responsible for formulating and implementing delivery plans, using real-time traffic data and distribution networks to select delivery routes;

[0149] S5, User Interaction and Feedback Collection: Provides a user interface that allows consumers to view the types and quantities of vegetables that are about to arrive, and make reservations and purchases. By collecting user feedback and purchase history, it provides consumer behavior data to optimize prediction accuracy and delivery efficiency.

[0150] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Within the scope of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0151] The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A precise distribution system of fresh vegetables from farms based on intelligent algorithms, characterized by: It includes data collection module, intelligent prediction module, resource optimization and allocation module, precise distribution module and user interaction module, among which; The data collection module is responsible for collecting data from multiple sources, including farm vegetable growth data, climate and environmental data, market demand data, and consumer behavior data; The intelligent forecasting module uses a forecasting model to comprehensively analyze data from multiple sources to predict market demand dynamics. It uses scenario simulation technology to construct market scenarios, analyze demand changes, and provide decision support for resource optimization. The intelligent forecasting module also includes a real-time data feedback mechanism to adjust the forecasting model and consumer behavior analysis based on real-time market feedback. The resource optimization and allocation module dynamically adjusts vegetable planting plans, planting area allocation, supply chain network design, and warehouse inventory levels based on the demand forecast results provided by the intelligent forecast module to minimize costs and time while meeting market demand; The precise distribution module is responsible for implementing the distribution plan based on the output of the resource optimization and allocation module, and selecting the distribution route by using real-time traffic data and distribution network analysis; The user interaction module provides a user interface that allows consumers to view the types and quantities of vegetables that are about to arrive, make reservations and purchases, and collect user feedback and purchase history to provide valuable consumer behavior data for the intelligent prediction module; The prediction model adopts a factor decomposition machine model, and the factor decomposition machine model includes: Introducing the time factor: By introducing the time factor to reflect the impact of different time periods on the demand for agricultural products, the calculation formula is: in, represents the demand forecast value based on product characteristics and time factors, v prod represents the product feature vector, T is the total number of time periods, v t The vector representation of the t-th time period, x prod and x t are indicator variables for product and time period, respectively; Introducing geographic location coding: By introducing geographic location coding, we can capture the differences in demand for agricultural products in different regions. The calculation formula is: in, represents the final predicted value after considering the geographic location encoding, L is the total number of geographic locations, v locl The vector representing the lth geographical location, x locl is the indicator variable for geographic location l.

2. The farm fresh vegetable precise distribution system based on intelligent algorithm according to claim 1 is characterized in that: The data collection module includes: Farm vegetable growth data collection: A sensor network installed on the farm collects real-time data on vegetable growth, including plant growth rate, leaf area index, soil moisture, and root zone temperature, and transmits the collected data. Climate and environmental data collection: Combined with weather station and satellite data, climate and environmental data around the farm and within a wide area are collected. Climate and environmental data include temperature, precipitation, wind speed, and relative humidity. Market demand data collection: Market demand data is collected through historical sales records, transaction data from online market platforms, and sales reports provided by partner retailers. Market demand data includes sales data, market trends and seasonal demand, competition analysis, and macroeconomic and social factors; Consumer behavior data collection: Collect users' purchase history, evaluation feedback, and browsing habits, and combine social media tools to obtain consumers' preferences for agricultural products, purchase intentions, and opinions on brand and quality from public social networks and forums.

3. The farm fresh vegetable precise distribution system based on intelligent algorithm according to claim 2 is characterized in that: The intelligent prediction module includes: Comprehensive analysis of multi-source data: Comprehensively collect data from multiple sources from the data collection module, and use data cleaning and pre-processing technology to ensure data quality and consistency; Prediction model construction: Build a prediction model based on the comprehensive analysis data, identify patterns and trends in the data, and predict the dynamic changes in market demand; Application of scenario simulation technology: Build multiple market scenarios through scenario simulation technology, and use forecasting models to analyze demand changes under various market scenarios; Real-time data feedback mechanism: The intelligent forecasting module integrates a real-time data feedback mechanism to monitor market feedback and sales data in real time. By analyzing real-time data, it automatically adjusts and optimizes the forecasting model. Consumer Behavior Analysis: Analyze unstructured data from social media, online reviews, and user feedback using natural language processing (NLP) and sentiment analysis techniques to understand consumer behavior and preferences.

4. The farm fresh vegetable precise distribution system based on intelligent algorithm according to claim 3 is characterized in that: The scenario simulation technology applications include: Scenario definition: Define multiple market scenarios, including economic fluctuations, seasonal changes, and changes in consumer trends. Under each scenario, set parameters and indicators to simulate different market environments and consumer behavior patterns; Data preparation: For each market scenario, collect and prepare relevant historical and forecast data, including historical sales data, seasonal factors, economic indicators, and consumer research data; Scenario simulation: Utilizing scenario simulation technology, according to each defined market scenario, by adjusting the corresponding parameters and indicators, the market environment under the corresponding scenario is simulated, including economic fluctuation scenario, seasonal change scenario and consumption trend change scenario, among which; The economic fluctuation scenario simulates the impact of different economic environments on vegetable demand by adjusting the values ​​of economic indicators; The seasonal change scenario simulates the impact of seasonal factors on vegetable demand based on the climate characteristics of different seasons and changes in consumer purchasing habits; The consumption trend change scenario simulates the potential impact of the changing trend on vegetable demand based on the changing trend of consumer preferences; Demand change analysis: Apply the factor decomposition machine prediction model, use the various scenario parameters obtained from scenario simulation as input, calculate the vegetable demand forecast value under each scenario through the prediction model, compare the demand forecast results under different scenarios, and understand the impact of economic fluctuations, seasonal changes, and changes in consumption trends on vegetable demand.

5. The farm fresh vegetable precise distribution system based on intelligent algorithm according to claim 4 is characterized in that: The consumer behavior analysis includes: Data collection: Collect unstructured text data from online reviews on social media platforms, e-commerce websites, and direct user feedback; Text preprocessing: This cleanses text data and reduces noise for subsequent processing by performing basic NLP operations such as stop word removal, stemming, and part-of-speech tagging. Sentiment analysis: Apply sentiment analysis technology to judge the sentiment tendency of the preprocessed text, and use logistic regression to calculate the sentiment score S(d) of text d. The calculation formula is: Among them, x1,…,x n is the eigenvector, β0,β1,…,β n It is the weight parameter learned through training data; Consumer Preference Extraction: Based on sentiment analysis results, extract and summarize consumer preferences and demands for agricultural products. Use the LDA topic model to identify the main topics and preferences in the reviews. Given a word w in document d, the topic distribution of word w is calculated as: p(z|d,w)∝p(z|d)·p(w|z); Here, p(z|d) is the distribution of topic z in document d, and p(w|z) is the distribution of word w under topic z.

6. The farm fresh vegetable precise distribution system based on intelligent algorithm according to claim 5 is characterized in that: The resource optimization configuration module includes: Demand forecast result reception: receiving information on vegetable types, expected demand, and demand fluctuations provided by the intelligent forecast module; Adjustment of vegetable planting plan: Based on the forecast results, calculate the optimal planting ratio and planting area of ​​various vegetables. The calculation formula is: A opt =D pred / Y avg ; Among them, A opt is the optimized planting area, D pred is the forecast demand, Y avg is the average yield per unit area; Supply chain network optimization: Analyze the logistics cost and time between each supply chain node, optimize the logistics path and supply chain structure, and the calculation formula is: C min =min∑ i,j (T ij ·C ij ); Among them, C min represents the minimum logistics cost, T ij is the transportation time from node i to node j, C ij is the corresponding unit cost; Warehouse inventory level optimization: Using forecasted demand and historical sales data, determine the optimal inventory level for each warehouse location to reduce inventory costs and the risk of unsold goods. The calculation formula is: Among them, S opt is the optimized inventory level, σ is the safety stock coefficient, D var is the variance of demand fluctuations.

7. The farm fresh vegetable precise distribution system based on intelligent algorithm according to claim 6 is characterized in that: The precise distribution module includes: Receive delivery plan: Receive the delivery plan, which includes the type, quantity, destination and scheduled delivery time of vegetables to be delivered; Real-time traffic data acquisition: Real-time collection of traffic data, including road conditions, traffic restrictions, and estimated travel times, using various traffic information sources, including GPS navigation and traffic management department data; Distribution network analysis: Analyze the distribution network structure, including warehouse locations, distribution point distribution, and transportation routes, to determine distribution path options; Delivery route selection: Combining real-time traffic data and distribution network analysis, we use optimization algorithms to determine the delivery route; Delivery execution and monitoring: Execute delivery tasks based on the selected delivery route and monitor the delivery status in real time.

8. The farm fresh vegetable precise distribution system based on intelligent algorithm according to claim 7 is characterized in that: The calculation formula of the optimization algorithm is: Among them, P best represents the optimal delivery path, is the set of all delivery routes, T i and C i are the estimated travel time and delivery cost of path i, respectively, and n is the number of paths.

9. A method for accurately distributing fresh vegetables from farms based on an intelligent algorithm, implemented by a system for accurately distributing fresh vegetables from farms based on an intelligent algorithm according to any one of claims 1 to 8, characterized in that: The following steps are involved: S1, data collection: Collect data from multiple sources, including farm vegetable growth data, climate and environmental data, market demand data, and consumer behavior data; S2, Demand Forecasting and Scenario Simulation: Use forecasting models to comprehensively analyze data collected from multiple sources to predict dynamic changes in market demand. Use scenario simulation technology to construct different market scenarios and analyze demand changes under different market scenarios. Use a real-time data feedback mechanism to adjust the forecasting model based on real-time market feedback. S3, resource optimization and allocation: Based on the demand forecast results provided by the intelligent forecasting module, the vegetable planting plan, planting area allocation, supply chain network design, and storage inventory levels are dynamically adjusted; S4, Precision Delivery Implementation: Based on the output of resource optimization allocation, responsible for formulating and implementing delivery plans, using real-time traffic data and distribution networks to select delivery routes; S5, User Interaction and Feedback Collection: Provides a user interface that allows consumers to view the types and quantities of vegetables that are about to arrive, and make reservations and purchases. By collecting user feedback and purchase history, it provides consumer behavior data to optimize prediction accuracy and delivery efficiency.

Images